{
  "generated": "2026-09-18",
  "source": "https://github.com/mvalentsev/awesome-free-ai-coding",
  "feed": "https://mvalentsev.github.io/awesome-free-ai-coding/feed.xml",
  "entries": [
    {
      "id": "openrouter-free",
      "name": "OpenRouter (free models)",
      "category": "aggregator",
      "url": "https://openrouter.ai",
      "source_urls": [
        "https://openrouter.ai/docs/faq",
        "https://openrouter.ai/docs/api_reference/limits",
        "https://openrouter.ai/docs/cookbook/coding-agents/claude-code-integration"
      ],
      "card_required": false,
      "offering": "One API key for a rotating set of :free model variants, open-weight and stealth models among them",
      "limits": "20 requests per minute on any :free id, 50 requests per day, and 1,000 per day once the account has purchased at least 10 credits all-time. Those four figures are in the page only as JS constants — FREE_MODEL_RATE_LIMIT_RPM, FREE_MODEL_NO_CREDITS_RPD, FREE_MODEL_HAS_CREDITS_RPD and FREE_MODEL_CREDITS_THRESHOLD — and the table that should show them serves empty cells to anything reading the HTML. OpenRouter's FAQ says its free models \"have low rate limits\" and \"are usually not suitable for production use\", warns that a negative credit balance can produce errors \"including for free models\", and notes a 429 may come from the upstream provider rather than the platform (read 2026-08-14)",
      "models": [
        {
          "family": "nemotron-3-ultra",
          "released": "2026-03",
          "aa_model": "nvidia-nemotron-3-ultra-550b-a55b"
        },
        {
          "family": "gemma-4",
          "released": "2026-04"
        }
      ],
      "api": {
        "base_url": "https://openrouter.ai/api/v1",
        "key_url": "https://openrouter.ai/settings/keys",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "nvidia/nemotron-3-ultra-550b-a55b:free",
          "nvidia/nemotron-3-super-120b-a12b:free",
          "nvidia/nemotron-3.5-lightning:free",
          "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
          "nvidia/nemotron-3.5-content-safety:free",
          "google/gemma-4-31b-it:free",
          "google/gemma-4-26b-a4b-it:free",
          "cohere/north-mini-code:free",
          "poolside/laguna-s-2.1:free",
          "poolside/laguna-xs-2.1:free",
          "thinkingmachines/inkling:free",
          "thinkingmachines/inkling-small:free",
          "dots-studio/dots-3-note-preview:free",
          "inclusionai/ling-3.0-flash-fin:free",
          "inclusionai/ling-3.0-flash-sante:free",
          "liquid/lfm-2.5-2.6b:free",
          "inclusionai/ling-3.0-flash-vl:free",
          "nex-agi/nex-n2.5-pro:free",
          "nex-agi/nex-n2.5-mini:free",
          "z-ai/glm-5.2:free",
          "openrouter/free"
        ],
        "anthropic_base_url": "https://openrouter.ai/api",
        "note": "pick models with the :free suffix: every id carrying it is priced 0/0, twenty on 2026-09-16, and the lane rotates, so a new id waits two weeks for the Models column. Six are not coding models: openrouter/free is the free-models router, nemotron-3.5-content-safety a guardrail, ling-3.0-flash-fin and ling-3.0-flash-sante finance- and health-tuned, nemotron-3-nano-omni a perception sub-agent, and LiquidAI warns lfm-2.5-2.6b off agentic coding. For Claude Code, OpenRouter's cookbook sets ANTHROPIC_BASE_URL to https://openrouter.ai/api with ANTHROPIC_API_KEY empty and a :free id as ANTHROPIC_MODEL"
      },
      "probe": {
        "type": "api-models",
        "endpoint": "https://openrouter.ai/api/v1/models",
        "keywords": [],
        "free_marker": ":free",
        "dead_markers": [],
        "require_zero_price": true,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-19",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 10,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/openrouter-free/"
    },
    {
      "id": "google-ai-studio",
      "name": "Google AI Studio (Gemini API)",
      "category": "api-free-tier",
      "url": "https://aistudio.google.com",
      "source_urls": [
        "https://ai.google.dev/gemini-api/docs/pricing",
        "https://ai.google.dev/gemini-api/docs/rate-limits"
      ],
      "card_required": false,
      "offering": "Free tier on the Gemini API, priced model by model rather than as one account quota",
      "limits": "Google prices the free tier per model: its pricing page reads \"Free of charge\" for input, output and context caching on Gemini 3.8 Flash — the newest of them, \"our most intelligent Flash model, engineered for long-horizon software engineering\", free in the same column that prices it at $0.75/$3.75 per 1M on the paid tier (read 2026-09-08) — and on 3.7 Flash, 3.6 Flash, 3.5 Flash, 3.5 Flash-Lite, 3.1 Flash-Lite, 3 Flash Preview, 2.5 Pro and 2.5 Flash, with \"Not available\" in the same column for Gemini 3.1 Pro Preview, Omni Flash Preview and the Live previews. A new generation arrives here as an addition: every Flash before it kept its free column when 3.8 landed. What the free tier costs instead is one row lower in each table: \"Used to improve our products\" is Yes on the free tier and No on the paid one. The per-model RPM/TPM/RPD figures are no longer published anywhere a probe can read — the rate-limits page keeps only the usage-tier table, whose free row reads \"Active project or free trial\", and sends you to aistudio.google.com/rate-limit, which needs a sign-in (read 2026-08-14)",
      "models": [
        {
          "family": "gemini-3.8-flash",
          "tier": "strong",
          "released": "",
          "aa_model": "gemini-3-8-flash"
        },
        {
          "family": "gemini-3.7-flash",
          "tier": "strong",
          "released": "",
          "aa_model": "gemini-3-7-flash"
        },
        {
          "family": "gemini-3.5-flash-lite",
          "released": "",
          "aa_model": "gemini-3-5-flash-lite"
        },
        {
          "family": "gemini-2.5-pro",
          "released": "",
          "aa_model": "gemini-2-5-pro"
        }
      ],
      "api": {
        "base_url": "https://generativelanguage.googleapis.com/v1beta/openai/",
        "key_url": "https://aistudio.google.com/apikey",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [],
        "note": "pass the key as Bearer"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://ai.google.dev/gemini-api/docs/pricing",
        "keywords": [
          "gemini-2.5-flash",
          "free of charge"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-19",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 10,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/google-ai-studio/"
    },
    {
      "id": "groq-free",
      "name": "Groq",
      "category": "api-free-tier",
      "url": "https://groq.com",
      "source_urls": [
        "https://console.groq.com/docs/rate-limits"
      ],
      "card_required": false,
      "offering": "Fast inference against a free plan Groq publishes as a per-model rate table",
      "limits": "Groq states the free plan as a table rather than one quota, in RPM / RPD / TPM / TPD: 30 / 1K / 8K / 200K on openai/gpt-oss-120b, gpt-oss-20b, gpt-oss-safeguard-20b, qwen/qwen3.6-27b and qwen/qwen3.8-27b, 30 / 14.4K / 15K / 500K on the two meta-llama/llama-prompt-guard classifiers, 30 / 250 / 70K on groq/compound and compound-mini, 20 / 2K on the two whisper models and 10 / 100 / 1.2K / 3.6K on the two canopylabs/orpheus voices (read 2026-09-08). Those thirteen rows are the whole free plan, with no Llama among them — the Llama ids in the page's API samples are not on it. Groq calls the table \"a high level summary and there may be exceptions\", and points at the limits page in an account for the exact figures",
      "models": [
        {
          "family": "gpt-oss",
          "released": "2025-08"
        },
        {
          "family": "qwen3.6",
          "released": ""
        },
        {
          "family": "qwen3.8-27b",
          "tier": "strong",
          "released": "",
          "aa_model": "qwen3-8-27b"
        }
      ],
      "api": {
        "base_url": "https://api.groq.com/openai/v1",
        "key_url": "https://console.groq.com/keys",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "openai/gpt-oss-120b",
          "openai/gpt-oss-20b",
          "qwen/qwen3.6-27b",
          "qwen/qwen3.8-27b"
        ],
        "note": "the chat models Groq's own Free Plan Limits table names; its safeguard and prompt-guard classifiers, compound systems, whisper and orpheus rows are left out"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://console.groq.com/docs/rate-limits",
        "keywords": [
          "free plan limits",
          "qwen/qwen3.8-27b"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-19",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 20,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/groq-free/"
    },
    {
      "id": "mistral-free",
      "name": "Mistral AI Studio",
      "category": "api-free-tier",
      "url": "https://mistral.ai",
      "source_urls": [
        "https://mistral.ai/pricing",
        "https://docs.mistral.ai/admin/billing-usage/subscriptions",
        "https://docs.mistral.ai/getting-started/quickstarts/studio/activate-and-generate-api-key",
        "https://docs.mistral.ai/admin/billing-usage/usage-limits"
      ],
      "card_required": false,
      "offering": "Mistral's Free plan — API keys with $10 a month of included usage, shared by the API, Studio and the Vibe coding CLI, no card",
      "limits": "The Free card on mistral.ai/pricing lists \"Limited coding sessions\", \"Test Mistral models in Studio\" and \"$10 /mo in API credits\", where Pro's card says $30. The docs say where the allowance goes: \"Mistral plans are global: the same plan applies across Vibe, Studio, and API usage\", \"Free mode is the default state for new accounts\", and \"Each Mistral plan includes monthly usage that is shared across Studio, the API, and Vibe Code. Usage consumes this monthly allowance first\" — past it, usage \"can stop until the next billing period\" unless pay-as-you-go is switched on. The quickstart asks for nothing more: \"Free mode: API access is enabled by default with no credit card required.\" What $10 buys is on the same page: \"For example, Mistral Large costs $0.5 /M tokens in and $1.5 /M tokens out.\" Free mode also has the lowest rate limits — requests per second, tokens per minute and tokens per month, shown only inside the account — and API calls may be used to improve Mistral's services unless the Admin panel's `Anonymous improvement data` toggle is off.",
      "models": [],
      "api": {
        "base_url": "https://api.mistral.ai/v1",
        "key_url": "https://console.mistral.ai/api-keys",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [],
        "note": "Free mode is on by default for a new account; create the key under Studio › API Keys. A key made under Code › Vibe CLI is a plan key that spends the plan's Vibe budget, which Mistral tells API users to avoid"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://mistral.ai/pricing",
        "keywords": [
          "$10 /mo in API credits",
          "Test Mistral models in Studio"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-19",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 78,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/mistral-free/"
    },
    {
      "id": "github-models",
      "name": "GitHub Models",
      "category": "api-free-tier",
      "url": "https://github.com/marketplace/models",
      "source_urls": [
        "https://docs.github.com/en/github-models",
        "https://github.blog/changelog/2026-06-16-github-models-is-no-longer-available-to-new-customers/",
        "https://github.blog/changelog/2026-07-01-github-models-is-being-fully-retired-on-july-30-2026/",
        "https://models.inference.ai.azure.com"
      ],
      "card_required": false,
      "offering": "Free playground+API for catalog models with GitHub account",
      "limits": "Per-model rate limits, free tier; closed to new customers on 2026-06-16 and fully retired (playground, catalog, inference API, BYOK) on 2026-07-30",
      "models": [
        {
          "family": "gpt-4.1",
          "released": "2025-04",
          "aa_model": "gpt-4-1"
        }
      ],
      "api": {
        "base_url": "https://models.github.ai/inference",
        "key_url": "https://github.com/settings/personal-access-tokens",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [],
        "note": "GitHub PAT with models:read scope; model ids namespaced (openai/...)"
      },
      "probe": {
        "type": "api-models",
        "endpoint": "https://models.github.ai/catalog/models",
        "keywords": [],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-19",
      "last_verified": "2026-07-30",
      "retired_on": "2026-06-16",
      "probe_failures": 1,
      "provisional": false,
      "rank": 80,
      "archived": true,
      "archived_because": "vendor-announced shutdown on 2026-06-16",
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/github-models/"
    },
    {
      "id": "cloudflare-workers-ai",
      "name": "Cloudflare Workers AI",
      "category": "api-free-tier",
      "url": "https://workers.cloudflare.com",
      "source_urls": [
        "https://developers.cloudflare.com/workers-ai/platform/pricing/",
        "https://developers.cloudflare.com/workers-ai/platform/limits/"
      ],
      "card_required": false,
      "offering": "10k neurons/day free",
      "limits": "Cloudflare's free allocation \"allows anyone to use a total of 10,000 Neurons per day at no charge\", which at its own $0.011 per 1,000 Neurons is about $0.11 of inference a day. \"All limits reset daily at 00:00 UTC\", and past the cap \"further operations will fail with an error\" rather than being billed. Rate limits are per task type — 300 requests per minute for Text Generation. Three catalog models sit outside the free lane whatever the neuron count: the same page notes that @cf/moonshotai/kimi-k2.6, @cf/moonshotai/kimi-k2.7-code and @cf/zai-org/glm-5.2 \"require a paid billing method\" (read 2026-08-14)",
      "models": [
        {
          "family": "llama-4",
          "released": "2025-04"
        }
      ],
      "api": {
        "base_url": "https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/v1",
        "key_url": "https://dash.cloudflare.com/profile/api-tokens",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [],
        "note": "substitute {account_id} with your Cloudflare account ID"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://developers.cloudflare.com/workers-ai/platform/pricing/",
        "keywords": [
          "10,000 neurons per day",
          "free allocation"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-19",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 40,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/cloudflare-workers-ai/"
    },
    {
      "id": "ollama-cloud",
      "name": "Ollama Cloud",
      "category": "api-free-tier",
      "url": "https://ollama.com/cloud",
      "source_urls": [
        "https://ollama.com/cloud"
      ],
      "card_required": false,
      "offering": "Cloud-hosted open models on a $0 plan that grants starter usage credits for a starter subset of the catalog",
      "limits": "The $0 plan is a wallet rather than a lane: \"Starter usage credits included\" and \"Includes access to starter models\", with \"Add credits to unlock all models\" under them. Neither figure is published — no credit amount and no starter-model list — and every cloud model carries a per-million-token price on the same page (gpt-oss:20b $0.07 in / $0.30 out, kimi-k3 $3.00 / $15.00). Free gets 1 concurrent request against Pro's 3, and the included usage \"resets monthly from the date you signed up\" without rolling over. The starter set can only be measured: on 2026-09-02 a key on the $0 plan got answers from gpt-oss:120b, gemma4:31b and nemotron-3-ultra and 402 Payment Required from minimax-m3, so the edge of the set is not the price — nemotron-3-ultra is inside at $0.10/$3.00, minimax-m3 outside at $0.60/$2.40. Read 2026-09-02",
      "models": [],
      "api": {
        "base_url": "https://ollama.com/v1",
        "key_url": "https://ollama.com/settings/keys",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "gpt-oss:120b",
          "gemma4:31b",
          "nemotron-3-ultra"
        ],
        "note": "the three ids left are the ones a key on the $0 plan actually answered on 2026-09-02, in that order of speed; minimax-m3 was dropped from this list because the same key gets 402 Payment Required for it. Which models the starter credits reach is published nowhere, so this list is measured rather than read, and /v1/models still lists the whole catalog, starter and metered alike"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://ollama.com/cloud",
        "keywords": [
          "Starter usage credits included",
          "Includes access to starter models"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "catalog": "https://ollama.com/v1/models",
        "machinery_keywords": []
      },
      "first_seen": "2026-07-19",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 92,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/ollama-cloud/"
    },
    {
      "id": "opencode",
      "name": "opencode",
      "category": "agent-cli",
      "url": "https://opencode.ai",
      "source_urls": [
        "https://opencode.ai/docs/zen/",
        "https://opencode.ai/docs/",
        "https://github.com/anomalyco/opencode/issues/49590#issuecomment-5723721001",
        "https://dev.meta.ai/docs/reasoning.md"
      ],
      "card_required": false,
      "offering": "Open-source coding agent whose opencode Zen gateway prices a rotating set of models at zero — Big Pickle, MiMo-V2.5, Ling 3.0 Flash Fin, Nemotron 3 Ultra, Nemotron 3.5 Lightning, Muse Spark 1.3 Contributor — inside OpenCode only, no sign-in; any provider via BYOK",
      "limits": "The free ids work inside OpenCode and nowhere else. Since 2026-09-17 Zen has answered every other client with `403 FreeTierError: OpenCode's free tier can only be used from within OpenCode`, and on 2026-09-18 an OpenCode maintainer wrote \"You cannot use the free tier in other harnesses (this is only a limitation for the free tier nothing else)\", so this row publishes no base URL. Inside OpenCode the ids are `opencode/<model-id>`, and all six answered the official 1.18.31 CLI, signed out, on 2026-09-18. Zen calls each one \"available on OpenCode for a limited time\", and the price is data: of the free models \"collected data may be used to improve the model\", the NVIDIA-backed ones are \"Trial use only — do not submit personal or confidential data\", and Muse Spark 1.3 Contributor trades \"heavily discounted token pricing in exchange for permission to use your prompts and completions to train future Meta models\". Mind the suffix: plain muse-spark-1.3 is a paid row; the contributor id's best allowed effort, xhigh, scores 45 on the Artificial Analysis Intelligence Index — max is \"Standard-tier `muse-spark-1.3` only\". Billing is for the metered ids. Read 2026-09-18",
      "models": [
        {
          "family": "big-pickle",
          "released": ""
        },
        {
          "family": "mimo-v2.5",
          "released": "",
          "aa_model": "mimo-v2-5-0424"
        },
        {
          "family": "ling-3.0-flash-fin",
          "released": "",
          "aa_model": "ling-3-0-flash-fin"
        },
        {
          "family": "nemotron-3-ultra",
          "released": "",
          "aa_model": "nvidia-nemotron-3-ultra-550b-a55b"
        },
        {
          "family": "nemotron-3.5-lightning",
          "released": "",
          "aa_model": "nemotron-3-5-lightning"
        },
        {
          "family": "muse-spark-1.3-contributor",
          "tier": "frontier",
          "released": "2026-09",
          "aa_model": "muse-spark-1-3-xhigh"
        }
      ],
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://opencode.ai/docs/zen/",
        "keywords": [
          "big pickle",
          "mimo-v2.5-free"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-19",
      "last_verified": "2026-09-14",
      "probe_failures": 1,
      "provisional": false,
      "rank": 10,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/opencode/"
    },
    {
      "id": "kilo-code",
      "name": "Kilo Code",
      "category": "agent-cli",
      "url": "https://kilo.ai",
      "source_urls": [
        "https://kilo.ai/pricing",
        "https://api.kilo.ai/api/gateway/models",
        "https://kilo.ai/docs/gateway/authentication",
        "https://kilocode.ai"
      ],
      "card_required": false,
      "offering": "Open-source VS Code / JetBrains / CLI agent whose $0 plan routes \"Auto Free\" to the models the Kilo Gateway marks free; the same gateway serves them to any OpenAI client without a key, with BYOK and local models alongside",
      "limits": "$0 a month, and no account for the free lane: \"The gateway allows unauthenticated access for free models only. Anonymous requests are identified by IP address and are subject to rate limiting (200 requests per hour per IP)\". The lane is whatever the gateway marks isFree — 20 ids on 2026-09-16, Nemotron 3 Ultra, Step 3.7 Flash and Laguna S 2.1 among them — and it rotates within days, so an id waits two weeks before it joins the Models column. It costs something other than money: every free id carries mayTrainOnYourPrompts, which almost no metered id does. Auto Free routes over the free models the catalog's autoRouting list names. Everything else runs on pay-as-you-go credits or a Kilo Pass subscription. Read 2026-09-16",
      "models": [
        {
          "family": "nemotron-3-ultra",
          "released": "2026-03",
          "aa_model": "nvidia-nemotron-3-ultra-550b-a55b"
        },
        {
          "family": "nemotron-3-super",
          "released": "2026-03",
          "aa_model": "nvidia-nemotron-3-super-120b-a12b"
        },
        {
          "family": "north-mini-code",
          "released": "2026-06",
          "aa_model": "north-mini-code"
        },
        {
          "family": "step-3.7-flash",
          "released": "2026-06",
          "aa_model": "step-3-7-flash"
        },
        {
          "family": "laguna-s-2.1",
          "released": "2026-07"
        },
        {
          "family": "laguna-xs-2.1",
          "released": "2026-07"
        }
      ],
      "api": {
        "base_url": "https://api.kilo.ai/api/gateway",
        "key_url": "https://app.kilo.ai/profile",
        "auth": "none",
        "openai_compatible": true,
        "model_ids": [
          "kilo-auto/free",
          "openrouter/free",
          "nvidia/nemotron-3-ultra-550b-a55b:free",
          "nvidia/nemotron-3-super-120b-a12b:free",
          "nvidia/nemotron-3.5-lightning:free",
          "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
          "nvidia/nemotron-3.5-content-safety:free",
          "cohere/north-mini-code:free",
          "stepfun/step-3.7-flash:free",
          "poolside/laguna-s-2.1:free",
          "poolside/laguna-xs-2.1:free",
          "liquid/lfm-2.5-2.6b:free",
          "inclusionai/ling-3.0-flash-fin:free",
          "inclusionai/ling-3.0-flash-sante:free",
          "dots-studio/dots-3-note-preview:free",
          "thinkingmachines/inkling-small:free",
          "inclusionai/ling-3.0-flash-vl:free",
          "nex-agi/nex-n2.5-pro:free",
          "nex-agi/nex-n2.5-mini:free",
          "z-ai/glm-5.2:free"
        ],
        "note": "no key at all for the free ids, capped at 200 requests per hour per IP; a metered id answers 401 `You need to sign in to use this model`. Every id listed is one the catalog marks isFree and mayTrainOnYourPrompts. kilo-auto/free leads because it routes over the free models the catalog's autoRouting list names; it and openrouter/free are routers and nemotron-3.5-content-safety is a guardrail classifier, so none of the three is a coding model"
      },
      "probe": {
        "type": "api-models",
        "endpoint": "https://api.kilo.ai/api/gateway/models",
        "keywords": [],
        "free_marker": ":free",
        "dead_markers": [],
        "require_zero_price": true,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-19",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 20,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/kilo-code/"
    },
    {
      "id": "trae",
      "name": "Trae",
      "category": "trial",
      "url": "https://www.trae.ai",
      "source_urls": [
        "https://www.trae.ai/pricing"
      ],
      "card_required": false,
      "offering": "AI IDE whose Free plan runs Auto mode only — no model choice — on a monthly Basic usage allowance of a few dollars and 5,000 autocompletions",
      "limits": "Trae publishes the Free plan as words — \"Auto mode only\", \"Limited usage\", \"Limited Autocomplete\", \"Autocompletion 5000 / month\", \"Concurrent Cloud Tasks 2\" — and as numbers in the page payload, where basic_usage_limit is the dollar figure the paid plans print as \"$20 usage / month\". That figure depends on where the page is served: on 2026-09-16 a GitHub runner read $3 of Basic usage on Free and another network $1, with different paid-plan figures and prices too. Both versions carry 5,000 autocompletions and 1,000 advanced-model requests on Free. Auto mode picks the model, and which models it routes to is published nowhere. The probe reads the payload because trae.ai renders per request and its table can arrive without the Free column",
      "models": [],
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://www.trae.ai/pricing",
        "keywords": [],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": [
          "\"name\":\"Free\"",
          "\"auto_completion_limit\":5000",
          "\"advanced_model_request_limit\":1000"
        ]
      },
      "first_seen": "2026-07-19",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 70,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/trae/"
    },
    {
      "id": "windsurf",
      "name": "Devin Desktop (formerly Windsurf)",
      "category": "trial",
      "url": "https://devin.ai/desktop",
      "source_urls": [
        "https://devin.ai/pricing",
        "https://docs.devin.ai/desktop/accounts/quota",
        "https://docs.devin.ai/desktop/accounts/usage",
        "https://devin.ai/blog/windsurf-is-now-devin-desktop",
        "https://windsurf.com",
        "https://codeium.com"
      ],
      "card_required": false,
      "offering": "Free plan of Cognition's desktop coding agent — the IDE that shipped as Windsurf",
      "limits": "Cognition renamed Windsurf to Devin Desktop on 2 June 2026, and windsurf.com, windsurf.com/pricing and docs.windsurf.com redirect to devin.ai, whose every path now answers HTTP 429 with a Vercel Security Checkpoint (`Enable JavaScript to continue`), from CI and from a laptop alike, so the pricing page cannot be read. Cognition's docs are open and describe the $0 plan: a \"daily and weekly usage allowance that refreshes automatically\", where Free means \"Wait until your next daily or weekly reset\" and only the paid plans can buy their way past it. Which models that allowance reaches is published nowhere readable; the one tier-tagged model catalogue, docs.devin.ai/desktop/models, carried only Pro and Enterprise tiers when it was read (2026-08-19). Read 2026-09-16",
      "models": [],
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://docs.devin.ai/desktop/accounts/quota.md",
        "keywords": [
          "**Free**: Wait until your next daily or weekly reset",
          "daily and weekly usage allowance that refreshes automatically"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-19",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 50,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/windsurf/"
    },
    {
      "id": "mimo-code",
      "name": "MiMo Code",
      "category": "agent-cli",
      "url": "https://mimo.xiaomi.com/coder",
      "source_urls": [
        "https://raw.githubusercontent.com/XiaomiMiMo/MiMo-Code/main/README.md",
        "https://mimo.xiaomi.com/mimocode/start",
        "https://github.com/XiaomiMiMo/MiMo-Code/blob/main/packages/opencode/src/util/free-api-sunset.ts"
      ],
      "card_required": false,
      "offering": "Xiaomi's open-source (MIT) terminal coding agent; its built-in \"MiMo Auto\" channel used to run Xiaomi's MiMo models with no login, API key, or card",
      "limits": "Anonymous MiMo Auto channel ended 2026-07-26 10:00 UTC — the client blocks it past that timestamp (FREE_API_SUNSET_AT) and prompts: \"The free API service has ended\"; a paid Token Plan or a third-party API key is required now. The README stopped offering the channel; the landing page at mimo.xiaomi.com/coder still read 无需登录，开箱即用，免费体验 (no login, free to try) on 2026-09-17",
      "models": [
        {
          "family": "mimo-v2.5",
          "released": "",
          "aa_model": "mimo-v2-5-0424"
        }
      ],
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://raw.githubusercontent.com/XiaomiMiMo/MiMo-Code/main/README.md",
        "keywords": [
          "mimo auto",
          "mimo-v2.5"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-20",
      "last_verified": "2026-08-03",
      "retired_on": "2026-07-26",
      "probe_failures": 0,
      "provisional": false,
      "rank": 30,
      "archived": true,
      "archived_because": "vendor-announced shutdown on 2026-07-26",
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/mimo-code/"
    },
    {
      "id": "github-copilot-free",
      "name": "GitHub Copilot Free",
      "category": "trial",
      "url": "https://github.com/features/copilot",
      "source_urls": [
        "https://docs.github.com/en/copilot/get-started/plans",
        "https://docs.github.com/en/copilot/concepts/billing/usage-based-billing-for-individuals"
      ],
      "card_required": false,
      "offering": "Free Copilot plan for individual developers in VS Code, JetBrains, Visual Studio and CLI; completions, limited chat and agent usage",
      "limits": "GitHub folded its Copilot billing-concepts page into the plans page on or before 2026-08-20 and restated the figures there. Inline suggestions are \"limited to 2000 completions per month on Copilot Free\"; for everything agentic, \"Copilot Free and Copilot Student both have an allowance of AI credits\" — an allowance GitHub numbers for every paid plan (1,500 monthly credits on Pro, 7,000 on Pro+, 20,000 on Max) and leaves unnumbered for Free, whose row in the plans table reads only \"An allowance of GitHub AI Credits\" and \"Limited\" agents. Model choice is not offered: \"on Copilot Free and Copilot Student plans, access to models is available through auto model selection only\". The plan is still scoped to developers no employer covers — \"Copilot Free plans are only available to individual developers who don't have access to Copilot through an organization or enterprise\" — but the list of business features it withholds went with the old page and is not on this one (read 2026-08-20)",
      "models": [],
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://docs.github.com/en/copilot/get-started/plans",
        "keywords": [
          "2000 completions per month",
          "Copilot Free and Copilot Student both have an allowance of AI credits"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-20",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 10,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/github-copilot-free/"
    },
    {
      "id": "google-jules",
      "name": "Google Jules",
      "category": "trial",
      "url": "https://jules.google/",
      "source_urls": [
        "https://jules.google/docs/usage-limits"
      ],
      "card_required": false,
      "offering": "Free tier of Google's async cloud coding agent powered by Gemini 2.5 Pro; connects to GitHub repos and works autonomously",
      "limits": "15 tasks per rolling 24 hours and 3 concurrent tasks, against 100 and 15 on Jules in Pro and 300 and 60 on Jules in Ultra. The same table pins the free plan to Gemini 2.5 Pro while both paid rows read \"starting with Gemini 3 Pro\". Upgrading runs through a Google AI plan, \"currently available only for individual Google Accounts (ending in @gmail.com)\"; task limits are \"not shared or pooled\" on a family plan; and Google states it \"may adjust limits and features as we learn how people are using the product\" (read 2026-08-14)",
      "models": [
        {
          "family": "gemini-2.5",
          "released": ""
        }
      ],
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://jules.google/docs/usage-limits",
        "keywords": [
          "concurrent tasks",
          "gemini 2.5 pro"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-20",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 30,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/google-jules/"
    },
    {
      "id": "kiro",
      "name": "Kiro",
      "category": "trial",
      "url": "https://kiro.dev/",
      "source_urls": [
        "https://kiro.dev/pricing/",
        "https://kiro.dev/docs/models"
      ],
      "card_required": false,
      "offering": "Perpetual free tier of AWS's spec-driven agentic IDE (successor to Amazon Q Developer) with Claude Sonnet 4.5 and open-weight models",
      "limits": "50 credits/month; requires social login or AWS Builder ID; credits do not roll over; not available in AWS GovCloud, and free-tier requests are always served from the US. Kiro's docs settle what those credits reach, in a table with a Free column: ticked for Claude Sonnet 4.5 and 4.0, Auto, GLM-5, Qwen3 Coder Next, DeepSeek 3.2 and MiniMax M2.5 and M2.1; blank for Claude Sonnet 4.6 and 5, every Opus, Haiku 4.5 and all three GPT-5.6 tiers. The pricing page contradicts itself on exactly that point — its plan card and footnote both say Sonnet 4.5, its FAQ prose says the free tier includes Sonnet 4.6 — so read the docs table, not the FAQ (checked 2026-08-14)",
      "models": [
        {
          "family": "claude-sonnet-4.5",
          "released": "",
          "aa_model": "claude-4-5-sonnet"
        },
        {
          "family": "qwen3-coder",
          "released": ""
        },
        {
          "family": "deepseek-v3.2",
          "released": "",
          "aa_model": "deepseek-v3-2"
        },
        {
          "family": "minimax-2.1",
          "released": "",
          "aa_model": "minimax-m2-1"
        }
      ],
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://kiro.dev/pricing/",
        "keywords": [
          "kiro free",
          "50 credits"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-20",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 20,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/kiro/"
    },
    {
      "id": "cursor-hobby",
      "name": "Cursor (Hobby)",
      "category": "trial",
      "url": "https://cursor.com/",
      "source_urls": [
        "https://cursor.com/pricing",
        "https://cursor.com/help/models-and-usage/usage-limits",
        "https://cursor.com/help/account-and-billing/pricing"
      ],
      "card_required": false,
      "offering": "Permanent free Hobby plan of the Cursor AI IDE with limited Agent requests and Tab completions, no credit card",
      "limits": "Cursor publishes no figure for Hobby anywhere. Its pricing card reads \"No credit card required\", \"Limited Agent requests\" and \"Access to Composer\"; the plan table in its own help centre prints \"Limited\" in the included-usage column where Pro reads $20 and Ultra $400; and the help page adds only that \"the Hobby plan gives you access to Cursor's core features with limited usage. You can use Agent, Chat, and Tab completions with the Auto model\". Usage \"resets monthly with your billing cycle\" and \"does not roll over\"; at the cap Cursor shows a notification and offers on-demand billing or an upgrade. Which models Hobby reaches is never enumerated, and Cursor Router has not reached individual plans yet (read 2026-08-14)",
      "models": [],
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://cursor.com/pricing",
        "keywords": [
          "\"name\":\"hobby\",\"price\":\"0\"",
          "limited agent requests"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-20",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 40,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/cursor-hobby/"
    },
    {
      "id": "openai-codex-cli",
      "name": "OpenAI Codex CLI",
      "category": "agent-cli",
      "url": "https://learn.chatgpt.com/docs/codex/cli",
      "source_urls": [
        "https://learn.chatgpt.com/docs/pricing",
        "https://github.com/openai/codex"
      ],
      "card_required": false,
      "offering": "Open-source coding CLI, free by signing in with a $0 ChatGPT Free account; local coding tasks included on all plans",
      "limits": "Free ChatGPT plan carries the smallest allowance; shared 5-hour rolling + weekly rate limits; local tasks only",
      "models": [
        {
          "family": "gpt-5.6",
          "tier": "strong",
          "released": "",
          "aa_model": "gpt-5-6-terra"
        }
      ],
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://learn.chatgpt.com/docs/pricing",
        "keywords": [
          "codex are included in your chatgpt free"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-20",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 40,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/openai-codex-cli/"
    },
    {
      "id": "nvidia-nim",
      "name": "NVIDIA NIM (build.nvidia.com)",
      "category": "api-free-tier",
      "url": "https://build.nvidia.com",
      "source_urls": [
        "https://build.nvidia.com/explore/discover",
        "https://forums.developer.nvidia.com/t/api-credits-for-build-nvidia-com/306633"
      ],
      "card_required": false,
      "offering": "Free hosted NIM endpoints for 100+ models via the free NVIDIA Developer Program (OpenAI-compatible at integrate.api.nvidia.com/v1)",
      "limits": "Free to start with no card — the account is gated by phone/business-email verification, and access is metered in API credits rather than left open: NVIDIA staff describe the catalog as \"a trial experience of NVIDIA NIM limited to 5000 free API credits\", 1000 granted on sign-up. That answer is from 2024 and NVIDIA publishes no current figure; reports since put the ceiling at a ~40 req/min rate limit instead. Production use needs NVIDIA AI Enterprise either way. The catalog renames ids without notice, so copy them from it rather than from an older guide",
      "models": [
        {
          "family": "nemotron",
          "released": "2026-03"
        }
      ],
      "api": {
        "base_url": "https://integrate.api.nvidia.com/v1",
        "key_url": "https://build.nvidia.com",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "deepseek-ai/deepseek-v4-flash-0731",
          "nvidia/nemotron-nano-3-30b-a3b",
          "meta/muse-glimmer-30b"
        ],
        "note": "the catalog endpoint answers unauthenticated, which is what the probe reads — it confirms NVIDIA still hosts these models, not that your account still has credits to call them with, and it publishes no price field at all, so hosting is the only question it can answer"
      },
      "probe": {
        "type": "api-models",
        "endpoint": "https://integrate.api.nvidia.com/v1/models",
        "keywords": [],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-20",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 70,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/nvidia-nim/"
    },
    {
      "id": "zai-glm",
      "name": "Z.ai (Zhipu GLM)",
      "category": "api-free-tier",
      "url": "https://z.ai",
      "source_urls": [
        "https://docs.z.ai/guides/overview/pricing",
        "https://docs.z.ai/devpack/tool/claude"
      ],
      "card_required": false,
      "offering": "GLM Flash models free on the API, vision included (OpenAI-compatible at api.z.ai/api/paas/v4)",
      "limits": "GLM-4.7-Flash, GLM-4.5-Flash and the GLM-4.6V-Flash vision model are the three rows z.ai's own price table reads Free on all four columns — every other model there says \"Limited-time Free\" instead, including the flagship GLM-5.x. Rate-limited",
      "models": [
        {
          "family": "glm-4.7-flash",
          "released": "2026-01",
          "aa_model": "glm-4-7-flash"
        },
        {
          "family": "glm-4.5-flash",
          "released": "2025-07"
        },
        {
          "family": "glm-4.6v-flash",
          "released": "2026-01"
        }
      ],
      "api": {
        "base_url": "https://api.z.ai/api/paas/v4",
        "key_url": "https://z.ai/manage-apikey/apikey-list",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "glm-4.7-flash",
          "glm-4.5-flash",
          "glm-4.6v-flash"
        ],
        "anthropic_base_url": "https://api.z.ai/api/anthropic",
        "note": "the ids are the chat completion reference's own, where glm-4.7-flash and glm-4.5-flash sit in its model enum; Coding-Plan keys use https://api.z.ai/api/coding/paas/v4 instead. The Claude Code guide sets ANTHROPIC_BASE_URL to https://api.z.ai/api/anthropic with \"your_zai_api_key\" as the token and names Coding-Plan ids (glm-5.3, glm-5.3-flash); whether the free Flash ids answer on that route is not stated, and the route answers 401 keyless (2026-09-05)"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://docs.z.ai/guides/overview/pricing",
        "keywords": [
          "GLM-4.7-Flash</td><td style=\"text-align:left\">Free</td>",
          "GLM-4.5-Flash</td><td style=\"text-align:left\">Free</td>",
          "GLM-4.6V-Flash</td><td style=\"text-align:left\">Free</td>"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-20",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 30,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/zai-glm/"
    },
    {
      "id": "ovh-ai-endpoints",
      "name": "OVHcloud AI Endpoints",
      "category": "api-free-tier",
      "url": "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/catalog/",
      "source_urls": [
        "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/models",
        "https://docs.ovhcloud.com/en/guides/public-cloud/ai-machine-learning/ai-endpoints-getting-started",
        "https://www.ovhcloud.com/en/public-cloud/ai-endpoints/"
      ],
      "card_required": false,
      "offering": "EU-hosted serverless open-model API whose anonymous lane needs no signup, no key and no card (OpenAI-compatible)",
      "limits": "OVHcloud documents the anonymous lane: \"Anonymous: 2 requests per minute, per IP and per model. Authenticated with an API access key: 400 requests per minute, per PCI project and per model\", and its product page says \"Test all our models for free in a sandbox or via the API\". The limit is tighter in practice: at one call a minute per model from one address, Qwen3.8-27B answered five times out of six on 2026-09-14 and the gpt-oss and older Qwen ids once or twice, and on 2026-09-16 every id answered 429 from another network — a 429 is the quota, not a refusal. Qwen3.8-27B is also the one coding model the catalog prices at zero for keyed use; the others are billed per token once a key is in play. Read 2026-09-14",
      "models": [
        {
          "family": "gpt-oss",
          "released": "2025-08"
        },
        {
          "family": "qwen3.6",
          "released": ""
        },
        {
          "family": "qwen3.8-27b",
          "tier": "strong",
          "released": "",
          "aa_model": "qwen3-8-27b"
        },
        {
          "family": "qwen3-coder",
          "released": "2025-07"
        }
      ],
      "api": {
        "base_url": "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1",
        "auth": "none",
        "openai_compatible": true,
        "model_ids": [
          "Qwen3.8-27B",
          "gpt-oss-120b",
          "Qwen3.6-27B",
          "Qwen3-Coder-30B-A3B-Instruct"
        ],
        "note": "no key at all on the anonymous lane, which OVHcloud rate-limits at 2 requests per minute per IP per model — a 429 means wait about half a minute, not that the offer is gone. An API access key from a Public Cloud project raises that to 400 per minute and bills per token from then on, except on Qwen3.8-27B, which the catalog prices at zero"
      },
      "probe": {
        "type": "api-models",
        "endpoint": "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/models",
        "keywords": [],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-20",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 80,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/ovh-ai-endpoints/"
    },
    {
      "id": "pollinations",
      "name": "Pollinations.AI",
      "category": "api-free-tier",
      "url": "https://pollinations.ai",
      "source_urls": [
        "https://text.pollinations.ai/models",
        "https://raw.githubusercontent.com/pollinations/pollinations/master/APIDOCS.md"
      ],
      "card_required": false,
      "offering": "Open GenAI text API, no signup, OpenAI-compatible (POST text.pollinations.ai/openai)",
      "limits": "Anonymous 1 req/15s (no signup). The keyless catalog publishes exactly one model and tags it with the tier it belongs to — \"openai-fast\", described as \"GPT-OSS 20B Reasoning LLM (OVH)\", tier \"anonymous\", aliased to openai / gpt-oss / gpt-oss-20b. The documented free registration that lifts the rate to 1 req/5s is unreachable — its host stopped resolving on 2026-08-14",
      "models": [
        {
          "family": "gpt-oss",
          "released": "2025-08"
        }
      ],
      "api": {
        "base_url": "https://text.pollinations.ai/openai",
        "auth": "none",
        "openai_compatible": true,
        "model_ids": [],
        "note": "anonymous works and needs no key. The optional token that raises the rate limit has no working signup — auth.pollinations.ai, the host the vendor's own APIDOCS still sends you to, stopped resolving (NXDOMAIN from both Cloudflare and Google resolvers, 2026-08-14)"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://text.pollinations.ai/models",
        "keywords": [
          "\"tier\":\"anonymous\"",
          "GPT-OSS 20B"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-20",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 90,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/pollinations/"
    },
    {
      "id": "alibaba-model-studio",
      "name": "Alibaba Cloud Model Studio (DashScope, international)",
      "category": "api-free-tier",
      "url": "https://www.alibabacloud.com/en/product/modelstudio",
      "source_urls": [
        "https://www.alibabacloud.com/help/en/model-studio/model-pricing"
      ],
      "card_required": false,
      "offering": "Free quota for Qwen models on DashScope, international (Singapore) region; OpenAI-compatible",
      "limits": "1,000,000 free tokens per model, on the Singapore (international) region alone: \"the following models offer a free quota only in Singapore. No free quota is available in other regions\". The grant is \"valid for 90 days from the date of Model Studio activation, model release, or application approval, whichever is later\" (read 2026-09-16). Which ids carry it is read off the last column of each International table, \"Free quota\": the qwen3.8 generation — qwen3.8-max and qwen3.8-max-0902 at a $2/$6 list, qwen3.8-flash, qwen3.8-27b — qwen3-max, and the qwen3-coder line. qwen-long reads \"No free quota\", and the Global tables carry no free-quota column at all (ids read 2026-09-10)",
      "models": [
        {
          "family": "qwen3.8-max",
          "tier": "frontier",
          "released": "2026-09",
          "aa_model": "qwen3-8-max"
        },
        {
          "family": "qwen3-max",
          "released": "2026-04",
          "aa_model": "qwen3-max"
        },
        {
          "family": "qwen3-coder",
          "released": "2025-07"
        }
      ],
      "api": {
        "base_url": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
        "key_url": "https://modelstudio.console.alibabacloud.com",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [],
        "note": "international (Singapore) endpoint; keys are region-specific"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://www.alibabacloud.com/help/en/model-studio/model-pricing",
        "keywords": [
          "free quota",
          "valid for 90 days"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-20",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 60,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/alibaba-model-studio/"
    },
    {
      "id": "huggingface-inference",
      "name": "Hugging Face Inference Providers",
      "category": "aggregator",
      "url": "https://huggingface.co/docs/inference-providers",
      "source_urls": [
        "https://huggingface.co/docs/inference-providers/pricing"
      ],
      "card_required": false,
      "offering": "Routed access to 200+ models across providers (Groq, Cerebras, Together, etc.) with a free HF account",
      "limits": "Free users get $0.10/month credits (subject to change); credits apply only on HF-routed requests. There is no free model list to publish — the credit is spent at each provider's own rate across everything the router reaches, so which models it buys depends on their price, not on a tier (read 2026-08-14)",
      "models": [],
      "api": {
        "base_url": "https://router.huggingface.co/v1",
        "key_url": "https://huggingface.co/settings/tokens",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [],
        "note": "chat-only; model ids namespaced (openai/gpt-oss-120b)"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://huggingface.co/docs/inference-providers/pricing",
        "keywords": [
          "monthly credits",
          "$0.10, subject to change"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-20",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 80,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/huggingface-inference/"
    },
    {
      "id": "upstage",
      "name": "Upstage (Solar API)",
      "category": "trial",
      "url": "https://console.upstage.ai/",
      "source_urls": [
        "https://console.upstage.ai/docs/getting-started",
        "https://console.upstage.ai/"
      ],
      "card_required": false,
      "offering": "Upstage Solar LLM API; $10 free credit on signup, no card",
      "limits": "$10 signup credit (see console for validity); pay-as-you-go after. console.upstage.ai is a client-rendered docs site — 535 characters of text survive with its scripts removed — so \"$10 in free credit\" is read out of the payload the page ships rather than out of anything a reader sees, and it is declared as a machinery keyword to say so. Neither upstage.ai/pricing nor the Solar Pro product page carries the phrase at all (all three read 2026-09-08)",
      "models": [
        {
          "family": "solar-pro-3",
          "released": "",
          "aa_model": "solar-pro-3"
        },
        {
          "family": "solar-mini",
          "released": "",
          "aa_model": "solar-mini"
        }
      ],
      "api": {
        "base_url": "https://api.upstage.ai/v1",
        "key_url": "https://console.upstage.ai/api-keys",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [],
        "note": ""
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://console.upstage.ai/docs/getting-started",
        "keywords": [],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": [
          "$10 in free credit"
        ]
      },
      "first_seen": "2026-07-19",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 80,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/upstage/"
    },
    {
      "id": "cohere",
      "name": "Cohere (trial keys)",
      "category": "api-free-tier",
      "url": "https://cohere.com",
      "source_urls": [
        "https://docs.cohere.com/docs/rate-limits",
        "https://cohere.com/pricing",
        "https://docs.cohere.com/docs/north-mini-code-1.0",
        "https://docs.cohere.com/docs/models"
      ],
      "card_required": false,
      "offering": "Cohere Command models via free trial API keys that never expire, plus North Mini Code — a 30B/3B Apache-2.0 coding model Cohere prices at zero on every key type",
      "limits": "Trial keys are \"limited to 1,000 API calls a month\" and rate-limited per model — 20 req/min on every Chat model, Command A and North Mini Code included, with Rerank at 10/min, Tokenize at 100/min, Embed at 2,000 inputs/min and audio transcription at 5/min. Two things that page does not say. Cohere's pricing page states that trial keys \"are not permitted to be used for production or commercial purposes\", and that every account \"begins as a personal account and only has access to Trial API keys\" — so the 1,000 calls are for evaluation, not for a product. And the North Mini Code page states that \"for both trial keys and production keys, North Mini Code is free until rate limits are reached\", which makes the one model here built for agentic coding the one that stays free on a paid key too (read 2026-08-14)",
      "models": [
        {
          "family": "command-a",
          "released": "",
          "aa_model": "command-a"
        },
        {
          "family": "north-mini-code",
          "released": "",
          "aa_model": "north-mini-code"
        }
      ],
      "api": {
        "base_url": "https://api.cohere.com/compatibility/v1",
        "key_url": "https://dashboard.cohere.com/api-keys",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "north-mini-code-1-0",
          "command-a-03-2025"
        ],
        "note": "OpenAI-compatible endpoint; native API lives at https://api.cohere.com/v2. Both ids are the Model ID Cohere's own model pages publish — north-mini-code-1-0 is the free-on-any-key one"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://docs.cohere.com/docs/rate-limits",
        "keywords": [
          "trial keys",
          "1,000"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-22",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 75,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/cohere/"
    },
    {
      "id": "qoder",
      "name": "Qoder",
      "category": "trial",
      "url": "https://qoder.com",
      "source_urls": [
        "https://docs.qoder.com/account/pricing"
      ],
      "card_required": false,
      "offering": "Alibaba's agentic coding IDE + CLI; Pro trial with credits on signup, then a free plan with basic models",
      "limits": "The free plan is \"basic models for limited user messages\" plus limited completions and next edits and BYOK, and the daily cap on those basic models carries no published number: \"basic models have a daily limit; if you reach this limit, you'll need to wait until the next day to continue using the service\". What is quantified is the trial that comes with it — a 2-week Pro trial carrying 300 credits, unlimited completions and next edits, chat, agent, Experts Mode, Quest, Repo Wiki and Knowledge Card. Paid plans buy premium-model credits (2,000/month on Pro) that reset to zero when the subscription period ends, and running out of them drops you back to the same basic models (read 2026-08-14)",
      "models": [],
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://docs.qoder.com/account/pricing",
        "keywords": [
          "300 credits",
          "14-day pro trial"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-22",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 60,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/qoder/"
    },
    {
      "id": "charm-hyper",
      "name": "Crush + Charm Hyper",
      "category": "agent-cli",
      "url": "https://hyper.charm.land",
      "source_urls": [
        "https://hyper.charm.land/faq",
        "https://github.com/charmbracelet/crush"
      ],
      "card_required": false,
      "offering": "Charm's Crush terminal agent with Hyper, its official hosted model gateway; the free plan includes monthly Hypercredits, zero data retention",
      "limits": "100 Hypercredits (≈$5) refreshed monthly; Hyper is in private beta (sign up from Crush or the site)",
      "models": [],
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://hyper.charm.land/faq",
        "keywords": [
          "100 hypercredits",
          "refreshing monthly"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-22",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 50,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/charm-hyper/"
    },
    {
      "id": "vercel-ai-gateway",
      "name": "Vercel AI Gateway",
      "category": "aggregator",
      "url": "https://vercel.com/ai-gateway",
      "source_urls": [
        "https://vercel.com/docs/ai-gateway/pricing",
        "https://vercel.com/docs/ai-gateway/openai-compat",
        "https://vercel.com/docs/ai-gateway/sdks-and-apis/anthropic-messages-api"
      ],
      "card_required": false,
      "offering": "One OpenAI-compatible endpoint for 360+ models, with $5 of gateway credits included every month and five language models that never touch the credit",
      "limits": "$5 of gateway credit a month at provider list rates, renewed monthly, with lower per-model rate limits and no BYOK; buying credits ends the monthly free credit. A handful of language models are priced 0 in and 0 out and never draw on the credit — Laguna S 2.1 Free and the Ling 3.0 Flash Fin, Sante and VL rows, each with and without its -free suffix, on 2026-09-12. Mind the suffix: poolside/laguna-s-2.1 without it costs $0.10/$0.20 per 1M tokens",
      "models": [
        {
          "family": "laguna-s-2.1",
          "released": "2026-07"
        },
        {
          "family": "ling-3.0-flash-fin",
          "released": "2026-09",
          "aa_model": "ling-3-0-flash-fin"
        }
      ],
      "api": {
        "base_url": "https://ai-gateway.vercel.sh/v1",
        "key_url": "https://vercel.com/dashboard/ai-gateway/api-keys",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "poolside/laguna-s-2.1-free",
          "inclusionai/ling-3.0-flash-fin",
          "inclusionai/ling-3.0-flash-fin-free",
          "inclusionai/ling-3.0-flash-sante",
          "inclusionai/ling-3.0-flash-sante-free",
          "inclusionai/ling-3.0-flash-vl",
          "inclusionai/ling-3.0-flash-vl-free"
        ],
        "anthropic_base_url": "https://ai-gateway.vercel.sh",
        "note": "every id listed is priced 0 in and 0 out and draws nothing from the $5 credit; any other Free-Tier-eligible model spends it. Zero-priced ids come and go within days, so a new one waits two weeks for the Models column. spacexai/grok-stt also shows a zero but is speech-to-text billed per second of audio. The same key serves the Anthropic Messages format at https://ai-gateway.vercel.sh, which Vercel's docs give as Claude Code's ANTHROPIC_BASE_URL with ANTHROPIC_API_KEY empty"
      },
      "probe": {
        "type": "api-models",
        "endpoint": "https://ai-gateway.vercel.sh/v1/models",
        "keywords": [],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": true,
        "machinery_keywords": []
      },
      "first_seen": "2026-08-03",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 50,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/vercel-ai-gateway/"
    },
    {
      "id": "bazaarlink",
      "name": "BazaarLink",
      "category": "aggregator",
      "url": "https://bazaarlink.ai",
      "source_urls": [
        "https://bazaarlink.ai/free",
        "https://bazaarlink.ai/en/docs"
      ],
      "card_required": false,
      "offering": "OpenAI-compatible gateway to a 173-id catalog whose free page counts two models on 2026-09-14 — Qwen3.7 Flash and DeepSeek V4 Flash 0731 — beside the auto:free router",
      "limits": "BazaarLink prints the figures on its free page: 10 requests per minute and 50 per day, ×1 for an account without credit and ×2 for one that has topped up, against the models it counts as free. Past the quota \"requests on free-quota models continue at the normal paid rate if you have credit; otherwise they are rate-limited until the quota resets\"; everything else in the catalog is metered at list rates. The free ids are Qwen3.7 Flash and the 0731 revision of DeepSeek V4 Flash, under the catalog's own id deepseek/deepseek-v4-flash-0731free:free, described as \"Rate-limited free tier.\" and listed on the free page as \"Deepseek V4 Flash 0731free\" at $0 against $0.20/$0.40, beside a metered deepseek-v4-flash-0731free twin at those rates",
      "models": [
        {
          "family": "qwen3.7-flash",
          "released": "2026-07"
        }
      ],
      "api": {
        "base_url": "https://api.bazaarlink.ai/v1",
        "key_url": "https://bazaarlink.ai/keys",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "qwen/qwen3.7-flash:free",
          "deepseek/deepseek-v4-flash-0731free:free",
          "auto:free"
        ],
        "note": "only the two :free ids and auto:free cost nothing — the plain qwen3.7-flash beside the first is the metered twin ($0.03/$0.13 per 1M), and deepseek-v4-flash-0731free without the suffix is metered at $0.20/$0.40. auto:free picks a free model for you, and on a funded account it can fall through to the paid routing table \"unless paid fallback is disabled\""
      },
      "probe": {
        "type": "api-models",
        "endpoint": "https://api.bazaarlink.ai/v1/models",
        "keywords": [],
        "free_marker": ":free",
        "dead_markers": [],
        "require_zero_price": true,
        "machinery_keywords": []
      },
      "first_seen": "2026-08-03",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 60,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/bazaarlink/"
    },
    {
      "id": "tokenrouter",
      "name": "TokenRouter (PaleBlueDot)",
      "category": "aggregator",
      "url": "https://www.tokenrouter.com",
      "source_urls": [
        "https://api.tokenrouter.com/api/pricing"
      ],
      "card_required": false,
      "offering": "One zero-priced id — Nemotron 3 Nano Omni, in the default group — inside a 140-row catalog that meters the rest",
      "limits": "the free id sits in the default group and publishes no request cap; of the other 139 rows on 2026-09-16, 138 are metered and stealth/ox-alpha is priced 0 without the free marker the lane is read by. Two free ids have come and gone beside it: the zero-priced Kimi K3 this entry was registered for — moonshotai/kimi-k3-free had left the catalog by 2026-08-14 and only the paid moonshotai/kimi-k3 remains — and z-ai/glm-5.3-free, which stood beside Nemotron from 2026-09-02 and had left by 2026-09-16, while z-ai/glm-5.3, glm-5.3-fast and glm-5.3-flash stayed metered",
      "models": [
        {
          "family": "nemotron-3-nano-omni",
          "released": "2026-04",
          "aa_model": "nemotron-3-nano-omni-30b-a3b"
        }
      ],
      "api": {
        "base_url": "https://api.tokenrouter.com/v1",
        "key_url": "https://www.tokenrouter.com/console/token",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free"
        ],
        "note": "one id in the catalog is priced 0 under the free marker, and it is the whole free lane here — nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free, alone on 2026-08-14 and again on 2026-09-16; z-ai/glm-5.3-free stood beside it from 2026-09-02 until it left the catalog between the 2026-09-14 and 2026-09-16 reads. PaleBlueDot AI runs this gateway on tokenrouter.com; same-name gateways on other TLDs are separate services and their keys do not work here"
      },
      "probe": {
        "type": "api-models",
        "endpoint": "https://api.tokenrouter.com/api/pricing",
        "keywords": [],
        "free_marker": "free",
        "dead_markers": [],
        "require_zero_price": true,
        "machinery_keywords": []
      },
      "first_seen": "2026-08-05",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 70,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/tokenrouter/"
    },
    {
      "id": "sambanova-cloud",
      "name": "SambaNova Cloud",
      "category": "api-free-tier",
      "url": "https://cloud.sambanova.ai",
      "source_urls": [
        "https://docs.sambanova.ai/docs/en/models/rate-limits"
      ],
      "card_required": false,
      "offering": "Open models on SambaNova's RDU hardware, OpenAI-compatible; the free tier is the one that applies while no payment method is linked, so linking a card is what ends it",
      "limits": "20 req/min, 20 req/day and 200,000 tokens/day per model on the free tier; five models carry it (DeepSeek V3.1/V3.2, Llama 3.3 70B, gpt-oss-120b, Gemma 4)",
      "models": [
        {
          "family": "deepseek",
          "released": "2025-12"
        },
        {
          "family": "gpt-oss",
          "released": "2025-08"
        },
        {
          "family": "gemma-4",
          "released": "2026-04"
        }
      ],
      "api": {
        "base_url": "https://api.sambanova.ai/v1",
        "key_url": "https://cloud.sambanova.ai/apis",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "DeepSeek-V3.1",
          "Meta-Llama-3.3-70B-Instruct",
          "gpt-oss-120b"
        ],
        "note": "model ids are case-sensitive; the catalog publishes list prices for every row, so the free tier is a quota rather than a zero-priced lane"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://docs.sambanova.ai/docs/en/models/rate-limits",
        "keywords": [
          "no payment method linked with your account",
          "Meta-Llama-3.3-70B-Instruct",
          "200000"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "catalog": "https://api.sambanova.ai/v1/models",
        "machinery_keywords": []
      },
      "first_seen": "2026-08-06",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 50,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/sambanova-cloud/"
    },
    {
      "id": "routeway",
      "name": "Routeway",
      "category": "aggregator",
      "url": "https://routeway.ai",
      "source_urls": [
        "https://api.routeway.ai/v1/models",
        "https://routeway.ai/docs",
        "https://docs.routeway.ai/getting-started/rate-limits"
      ],
      "card_required": false,
      "offering": "OpenAI-compatible gateway whose :free lane rotates — three zero-priced ids on 2026-09-16, Meta's Muse Glimmer 30B, DeepSeek V4 Flash and MiniMax M2.7 — beside 257 metered rows in the same catalog",
      "limits": "Free models — every id ending :free — are capped at 5 requests per minute and 200 per day and answer 429 past either; the pay-as-you-go ids beside them have no API-level rate limits, only edge DDoS protection (docs.routeway.ai, read 2026-08-30). The lane itself rotates: ten zero-priced ids on 2026-08-14, three on 2026-09-16, with ids joining and leaving within days while their metered twins stay. The gateway publishes no legal entity or terms of service and is supported through Discord alone: a fallback lane, not a dependency",
      "models": [
        {
          "family": "deepseek-v4-flash",
          "tier": "strong",
          "released": "2026-04",
          "aa_model": "deepseek-v4-flash"
        },
        {
          "family": "minimax-m2.7",
          "released": "2026-03",
          "aa_model": "minimax-m2-7"
        },
        {
          "family": "muse-glimmer-30b",
          "released": "2026-08",
          "aa_model": "muse-glimmer"
        }
      ],
      "api": {
        "base_url": "https://api.routeway.ai/v1",
        "key_url": "https://routeway.ai/dashboard/keys",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "muse-glimmer-30b:free",
          "deepseek-v4-flash:free",
          "minimax-m2.7:free"
        ],
        "note": "the three :free ids are every zero-priced row in the catalog on 2026-09-16, all marked available; only the :free suffix is free, and the same catalog meters Claude and GPT at list rates. An id joins the Models column only after two weeks in the lane, since every family there is re-checked on every run and three misses archive the row"
      },
      "probe": {
        "type": "api-models",
        "endpoint": "https://api.routeway.ai/v1/models",
        "keywords": [],
        "free_marker": ":free",
        "dead_markers": [],
        "require_zero_price": true,
        "machinery_keywords": []
      },
      "first_seen": "2026-08-06",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 40,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/routeway/"
    },
    {
      "id": "requesty",
      "name": "Requesty",
      "category": "aggregator",
      "url": "https://www.requesty.ai",
      "source_urls": [
        "https://www.requesty.ai/pricing",
        "https://docs.requesty.ai/quickstart",
        "https://router.requesty.ai/v1/models",
        "https://docs.requesty.ai/integrations/claude-code"
      ],
      "card_required": false,
      "offering": "OpenAI-compatible router over a 690+ model catalog with routing, caching and fallbacks; twelve rows in it are priced 0 and the free plan is the same gateway restricted to those",
      "limits": "Free plan is $0 with no credit card — 200 requests a day, free models only, with routing, caching, fallbacks, spend tracking and EU data residency included; past that the same key moves to pay-as-you-go",
      "models": [
        {
          "family": "nemotron-3-ultra",
          "released": "2026-03",
          "aa_model": "nvidia-nemotron-3-ultra-550b-a55b"
        },
        {
          "family": "nemotron-3-super",
          "released": "2026-03",
          "aa_model": "nvidia-nemotron-3-super-120b-a12b"
        },
        {
          "family": "gemma-4",
          "released": "2026-04"
        },
        {
          "family": "ling-3.0-tiny",
          "released": "2026-08",
          "aa_model": "ling-3-0-tiny"
        },
        {
          "family": "muse-glimmer-30b",
          "released": "2026-08",
          "aa_model": "muse-glimmer"
        },
        {
          "family": "nemotron-3.5-lightning",
          "released": "2026-08",
          "aa_model": "nemotron-3-5-lightning"
        }
      ],
      "api": {
        "base_url": "https://router.requesty.ai/v1",
        "key_url": "https://app.requesty.ai/api-keys",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "nvidia/nemotron-3-ultra-550b-a55b",
          "nvidia/nemotron-3-super-120b-a12b",
          "nvidia/nemotron-3-nano-30b-a3b",
          "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning",
          "nvidia/nemotron-3.5-content-safety",
          "novita/inclusionai/ling-3.0-tiny",
          "google/gemma-4-31b-it",
          "poolside/laguna-xs.2",
          "poolside/laguna-m.1",
          "mistral/leanstral-1-5",
          "nvidia/muse-glimmer-30b",
          "nvidia/nemotron-3.5-lightning-30b-a3b"
        ],
        "anthropic_base_url": "https://router.requesty.ai",
        "note": "the twelve ids listed are every row the catalog prices at 0, and the free plan serves those alone; ids carry no :free suffix, so the price is the only thing separating them from the metered rows. Every NVIDIA and Poolside row is marked data_used_for_training with 30-day retention, and nemotron-3.5-content-safety is a guardrail classifier. For Claude Code, the guide sets ANTHROPIC_BASE_URL to https://router.requesty.ai (router.eu.requesty.ai for EU residency)"
      },
      "probe": {
        "type": "api-models",
        "endpoint": "https://router.requesty.ai/v1/models",
        "keywords": [],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": true,
        "machinery_keywords": []
      },
      "first_seen": "2026-08-11",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 20,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/requesty/"
    },
    {
      "id": "antigravity",
      "name": "Google Antigravity",
      "category": "agent-cli",
      "url": "https://antigravity.google",
      "source_urls": [
        "https://antigravity.google/pricing",
        "https://antigravity.google/docs/plans",
        "https://antigravity.google/docs/models",
        "https://developers.googleblog.com/an-important-update-transitioning-gemini-cli-to-antigravity-cli/"
      ],
      "card_required": false,
      "offering": "Google's agent-first IDE and CLI, and where the Gemini CLI free tier went — Gemini CLI and the Code Assist IDE extensions stopped serving free, AI Pro and Ultra users on 2026-06-18. The $0 Individual plan carries the same agent models the paid ones do",
      "limits": "$0/month, no subscription. The plan's own bullet reads \"Agent model: access to Gemini 3.8 Flash, Gemini 3.7 Flash, Gemini 3.6 Flash, Gemini 3.1 Pro, Claude Sonnet & Opus 4.6, gpt-oss-120b\" (read 2026-09-03; Gemini 3.5 Flash stood there until 2026-08-31 and three newer Flash generations have taken its place), with unlimited Tab completions, unlimited Command requests and \"Basic weekly rate limits\". The docs' availability table ticks all seven models in its Free column, and gives the Claude and GPT models a weekly allowance of their own, apart from the Gemini one. Google publishes no figure for either: \"The baseline rate limits are primarily determined to the degree we have capacity, and exist to prevent abuse\"",
      "models": [
        {
          "family": "gemini-3.1-pro",
          "tier": "strong",
          "released": "",
          "aa_model": "gemini-3-1-pro-preview"
        },
        {
          "family": "gemini-3.8-flash",
          "tier": "strong",
          "released": "",
          "aa_model": "gemini-3-8-flash"
        },
        {
          "family": "gemini-3.7-flash",
          "tier": "strong",
          "released": "",
          "aa_model": "gemini-3-7-flash"
        },
        {
          "family": "gemini-3.6-flash",
          "tier": "strong",
          "released": "",
          "aa_model": "gemini-3-6-flash"
        },
        {
          "family": "claude-opus-4.6",
          "released": "",
          "aa_model": "claude-opus-4-6"
        },
        {
          "family": "claude-sonnet-4.6",
          "released": "",
          "aa_model": "claude-sonnet-4-6"
        },
        {
          "family": "gpt-oss",
          "released": "2025-08"
        }
      ],
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://antigravity.google/pricing",
        "keywords": [
          "$0/month",
          "gpt-oss-120b",
          "basic weekly rate limits"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-08-11",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 25,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/antigravity/"
    },
    {
      "id": "sea-lion",
      "name": "SEA-LION (AI Singapore)",
      "category": "api-free-tier",
      "url": "https://sea-lion.ai",
      "source_urls": [
        "https://sea-lion.ai/try-sea-lion/",
        "https://docs.sea-lion.ai/guides/inferencing/api"
      ],
      "card_required": false,
      "offering": "AI Singapore's open Southeast-Asian model family behind a first-party OpenAI-compatible API — the vendor hosting its own weights rather than a gateway reselling somebody else's",
      "limits": "Free API meant for prototyping — rate limited at 10 calls/min per user, with no credit or token budget published and no expiry stated; production use is pointed at cloud partners (AWS, Cloudflare, GCP, IBM, NVIDIA, Qualcomm) instead. The two surfaces do not overlap — the page that calls the API free names no model, and the docs page that names aisingapore/Qwen-SEA-LION-v4.5-27B-IT — and dates the 10 RPM limit to 04 Jun 2026 — never says free",
      "models": [],
      "api": {
        "base_url": "https://api.sea-lion.ai/v1",
        "key_url": "https://playground.sea-lion.ai/key-manager",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "aisingapore/Qwen-SEA-LION-v4.5-27B-IT",
          "aisingapore/Llama-SEA-LION-v3.5-70B-R"
        ],
        "note": "the key manager calls it a Trial API Key but publishes no expiry and no credit balance — the documented ceiling is the 10 calls/min rate limit. /v1/models needs the key, so the probe reads the offer page"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://sea-lion.ai/try-sea-lion/",
        "keywords": [
          "10 calls/min",
          "prototype and test with our free api"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-08-11",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 85,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/sea-lion/"
    },
    {
      "id": "ai21-labs",
      "name": "AI21 Labs (Jamba)",
      "category": "trial",
      "url": "https://www.ai21.com",
      "source_urls": [
        "https://www.ai21.com/pricing/",
        "https://docs.ai21.com/august-deprecation-notice",
        "https://docs.ai21.com/docs/jamba-foundation-models.md",
        "https://docs.ai21.com/docs/create-api-key.md",
        "https://docs.ai21.com/docs/usage-cost.md",
        "https://app.ai21.com/"
      ],
      "card_required": false,
      "offering": "AI21's Jamba models on a no-card trial credit — hybrid Mamba/attention models built for 256K-token context. The trial was AI21 Studio's, and the vendor sunset Studio's Jamba API on 2026-08-09",
      "limits": "Retired. The $10 no-card trial belonged to AI21 Studio, and Studio is gone: on 2026-09-05 every studio.ai21.com route landed on the www.ai21.com homepage, and the catalog route answered 410 `This API has been retired. The AI21 Gateway is available at https://app.ai21.com`. The vendor's notice named the day: \"On August 9, 2026, we will officially deprecate and sunset the following APIs in our platform: Jamba API, AI21 Maestro API, File library\". What stands at app.ai21.com is not a model API but a bring-your-own-key gateway in front of OpenAI and Anthropic, with nothing AI21-hosted or free to call",
      "models": [
        {
          "family": "jamba-mini",
          "released": "2026-01"
        },
        {
          "family": "jamba-large",
          "released": "2025-07"
        }
      ],
      "api": {
        "base_url": "https://api.ai21.com/studio/v1",
        "key_url": "https://studio.ai21.com/sign-up",
        "auth": "api-key",
        "openai_compatible": false,
        "model_ids": [
          "jamba-mini",
          "jamba-large"
        ],
        "note": "the Jamba API these ids belong to was sunset by the vendor on 2026-08-09; on 2026-09-05 /studio/v1/models answered 410 and the replacement at api.ai21.com/gateway/v1 is a bring-your-own-key proxy, not a Jamba endpoint. Never OpenAI-compatible, so it never entered the generated configs"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://www.ai21.com/pricing/",
        "keywords": [
          "$10 credits for 7 days",
          "No credit card needed",
          "Jamba Mini"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-08-14",
      "last_verified": "2026-09-03",
      "retired_on": "2026-08-09",
      "probe_failures": 0,
      "provisional": false,
      "rank": 90,
      "archived": true,
      "archived_because": "vendor-announced shutdown on 2026-08-09",
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/ai21-labs/"
    },
    {
      "id": "codegpt",
      "name": "CodeGPT",
      "category": "agent-cli",
      "url": "https://www.codegpt.co",
      "source_urls": [
        "https://www.codegpt.co/pricing"
      ],
      "card_required": false,
      "offering": "VS Code / JetBrains coding agent whose $0 plan includes model usage rather than only BYOK — a small daily allowance on its own Economy models, plus BYOK across 15+ providers and local models (Ollama, LM Studio) beside it",
      "limits": "10 free interactions a day on Economy models, described as free forever, plus a one-off $1.00 welcome credit for the premium ones, cut from $1.50 between the scheduled run of 2026-09-10 and a second read that evening; the pricing page says plainly \"No credit card required\". Unlimited use of the same Economy models is the paid Professional plan at $9-10/mo. CodeGPT does not publish which models the Economy tier routes to, so this row names none",
      "models": [],
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://www.codegpt.co/pricing",
        "keywords": [
          "10 free interactions every day on Economy models",
          "$1.00 welcome credit for premium models"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-08-14",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 60,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/codegpt/"
    },
    {
      "id": "aihubmix",
      "name": "AIHubMix (free models)",
      "category": "aggregator",
      "url": "https://aihubmix.com",
      "source_urls": [
        "https://docs.aihubmix.com/en/blogs/free-ai-models",
        "https://aihubmix.com/api/v1/models",
        "https://docs.aihubmix.com/en/api/Claude-Code"
      ],
      "card_required": false,
      "offering": "One OpenAI-compatible gateway over 800+ models, dozens of which the platform prices at 0 and subsidises itself — GLM-5.3 and Kimi K3 coding routes among them — with an Anthropic-format /v1/messages too, so a free id can back Claude Code",
      "limits": "per-model caps, spelled out in each model's catalog description: \"each account is limited to 5 requests per minute, 500 requests per day, and 1 million tokens per day\" on the GPT and coding routes (read 2026-09-02); the vendor states the quotas reset daily with no trial expiry and no payment method on file. The caveats differ by half of the lane — the GPT rows are \"the OpenAI model deployed on Azure\" behind Azure's content filter, the Gemini rows are \"provided only for trial use; stability cannot be guaranteed, and you may encounter 429 errors\", and nemotron-3.5-content-safety-free is a guardrail classifier. Every free id carries a -free suffix and the paid twin beside it is metered at list rates",
      "models": [
        {
          "family": "glm-5.3",
          "tier": "frontier",
          "released": "",
          "aa_model": "glm-5-3"
        },
        {
          "family": "kimi-k3",
          "tier": "frontier",
          "released": "",
          "aa_model": "kimi-k3"
        },
        {
          "family": "glm-5",
          "released": "2026-02",
          "aa_model": "glm-5"
        },
        {
          "family": "mimo-v2.5",
          "released": "",
          "aa_model": "mimo-v2-5-0424"
        },
        {
          "family": "north-mini-code",
          "released": "2026-06",
          "aa_model": "north-mini-code"
        },
        {
          "family": "gpt-oss",
          "released": "2025-08"
        }
      ],
      "api": {
        "base_url": "https://aihubmix.com/v1",
        "key_url": "https://aihubmix.com/token",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "coding-glm-5.2-free",
          "coding-glm-5.1-free",
          "coding-kimi-k3-free",
          "kimi-for-coding-free",
          "xiaomi-mimo-v2.5-free",
          "north-mini-code-free",
          "gpt-oss-20b-free",
          "ling-3.0-tiny-free",
          "nemotron-3-ultra-550b-a55b-free",
          "gemma-4-31b-it-free",
          "agents-a1-free",
          "coding-glm-4.6-free",
          "coding-glm-4.7-free",
          "coding-glm-5-free",
          "coding-glm-5-turbo-free",
          "coding-glm-5.3-flash-free",
          "coding-glm-5.3-free",
          "coding-minimax-m2-free",
          "coding-minimax-m2.1-free",
          "coding-minimax-m2.5-free",
          "coding-minimax-m2.7-free",
          "coding-minimax-m3-free",
          "dots-3-note-preview-free",
          "gemini-3-flash-preview-free",
          "gemini-3.5-flash-lite-free",
          "gemini-3.6-flash-free",
          "gemini-3.7-flash-free",
          "gemini-3.8-flash-free",
          "gemma-4-26b-a4b-it-free",
          "glm-4.7-flash-free",
          "gpt-4.1-free",
          "gpt-4.1-mini-free",
          "gpt-4.1-nano-free",
          "gpt-4o-free",
          "gpt-5.5-free",
          "hy3-free",
          "intern-s2-free",
          "k2.6-code-preview-free",
          "laguna-s-2.1-free",
          "laguna-xs-2.1-free",
          "lfm-2.5-2.6b-free",
          "ling-3.0-flash-free",
          "mimo-v2-flash-free",
          "minimax-m2.7-free",
          "nemotron-3-nano-30b-a3b-free",
          "nemotron-3-nano-omni-30b-a3b-reasoning-free",
          "nemotron-3-super-120b-a12b-free",
          "nemotron-3.5-content-safety-free",
          "nemotron-3.5-lightning-free",
          "nemotron-nano-12b-v2-vl-free",
          "nemotron-nano-9b-v2-free",
          "union-alpha-free",
          "xiaomi-mimo-v2-omni-free",
          "xiaomi-mimo-v2-pro-free",
          "xiaomi-mimo-v2.5-pro-free",
          "ox-alpha"
        ],
        "ignored_ids": [
          "gpt-image-2-free",
          "gemini-3.1-flash-image-preview-free",
          "qwen3.6-plus-preview-free",
          "gpt-live-transcribe"
        ],
        "anthropic_base_url": "https://aihubmix.com",
        "note": "every id the catalog prices at 0 is listed or ignored on purpose, 60 rows on 2026-09-17; free ids carry a -free suffix beside a metered twin. ox-alpha is a codename the catalog resolves: \"This model actually points to glm-5.3-flash\". Ignored: gpt-image-2-free and gemini-3.1-flash-image-preview-free generate images, qwen3.6-plus-preview-free says it was \"removed from the platform\", and gpt-live-transcribe is speech-to-text. For Claude Code, ANTHROPIC_BASE_URL is https://aihubmix.com, as its Claude Code guide sets it"
      },
      "probe": {
        "type": "api-models",
        "endpoint": "https://aihubmix.com/api/v1/models",
        "keywords": [],
        "free_marker": "free",
        "dead_markers": [],
        "require_zero_price": true,
        "machinery_keywords": []
      },
      "first_seen": "2026-08-14",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 30,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/aihubmix/"
    },
    {
      "id": "inception-labs",
      "name": "Inception Labs (Mercury)",
      "category": "trial",
      "url": "https://platform.inceptionlabs.ai",
      "source_urls": [
        "https://docs.inceptionlabs.ai/get-started",
        "https://docs.inceptionlabs.ai/resources/faq",
        "https://docs.inceptionlabs.ai/get-started/models",
        "https://docs.inceptionlabs.ai/get-started/rate-limits"
      ],
      "card_required": false,
      "offering": "A signup grant on the Mercury diffusion models — Mercury 2.5 and Mercury 2 for chat, Mercury Edit 2 for fill-in-the-middle and code edits; the last is the reason this row is here, since an FIM endpoint is what an IDE completion plugin actually calls",
      "limits": "100 million tokens on every new account, no payment details required, and the grant does not refill. The FAQ calls it a one-time credit \"shared across all models rather than granted per model\", so Mercury 2.5 spends the same balance as Mercury 2. Past it the account moves to pay-as-you-go: $0.25 per 1M input and $0.75 per 1M output on Mercury 2 and Mercury Edit 2, a list $0.20/$0.75 on Mercury 2.5 that the launch promotion is discounting 80% to $0.04/$0.15 (2026-09-10). The Free tier's own ceiling is per minute rather than per month — 1,000 requests, 1,000,000 input tokens and 100,000 output tokens",
      "models": [
        {
          "family": "mercury-2.5",
          "released": "2026-09"
        },
        {
          "family": "mercury-2",
          "released": "",
          "aa_model": "mercury-2"
        },
        {
          "family": "mercury-edit-2",
          "released": ""
        }
      ],
      "api": {
        "base_url": "https://api.inceptionlabs.ai/v1",
        "key_url": "https://platform.inceptionlabs.ai",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "mercury-2.5",
          "mercury-2",
          "mercury-edit-2"
        ],
        "note": "mercury-2.5 and mercury-2 answer /v1/chat/completions and are the two ids /v1/models lists; mercury-edit-2 answers /v1/fim/completions and /v1/edit/completions instead and is absent from that catalog by design, so an OpenAI-shaped chat client cannot call it — point an autocomplete plugin at it, not a chat agent"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://docs.inceptionlabs.ai/get-started",
        "keywords": [
          "100 million free tokens",
          "no payment details required"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-08-14",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 90,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/inception-labs/"
    },
    {
      "id": "poolside",
      "name": "Poolside Platform",
      "category": "api-free-tier",
      "url": "https://poolside.ai",
      "source_urls": [
        "https://docs.poolside.ai/get-started/quickstart",
        "https://docs.poolside.ai/api/overview"
      ],
      "card_required": false,
      "offering": "Free self-serve developer access to the Laguna coding models, direct from the vendor whose models this list already carries second-hand through OpenRouter and Kilo Gateway",
      "limits": "Poolside publishes none. Its quickstart offers \"fast, free developer access\" as the recommended of four access paths, with the organisation's own deployment a separate enterprise one, but poolside.ai/pricing is a 404 and no page on the docs site states a quota, a rate limit or a duration. Treat it as unquantified rather than as generous",
      "models": [],
      "api": {
        "base_url": "https://inference.poolside.ai/v1",
        "key_url": "https://platform.poolside.ai",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "poolside/laguna-s-2.1",
          "poolside/laguna-xs-2.1"
        ],
        "note": "the two ids come from docs.poolside.ai/api/overview, a different page from the one the probe reads — the vendor documents no free-versus-paid split for Platform keys anywhere, so this row claims no free models and names none in its column. The key is created by signing in to Poolside Platform, whose dashboard sits behind a Cloudflare check no probe can read"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://docs.poolside.ai/get-started/quickstart",
        "keywords": [
          "Choose this option for fast, free developer access",
          "fastest way to get a free Poolside API key"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-08-14",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 96,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/poolside/"
    },
    {
      "id": "sensenova",
      "name": "SenseNova (SenseTime 商汤)",
      "category": "api-free-tier",
      "url": "https://www.sensenova.cn",
      "source_urls": [
        "https://www.sensenova.cn/token-plan"
      ],
      "card_required": false,
      "offering": "SenseTime's own SenseNova models behind an OpenAI-compatible url, free for everyone while the token plan is in public beta",
      "limits": "The plan page says 公测期完全免费开放，付费档位即将上线 — free during the public beta, paid tiers coming — at ¥0/month: 60,000 积分 / 5 小时, a rolling 60,000 credits per five hours, 特殊模型除外, with 最多 20 个 API Key and the tier marked 限时放量. The Free card names the two models it covers, SenseNova 6.8 Flash Lite and SenseNova U1 Fast. Signup needs a phone number; whether a non-mainland one is accepted could not be verified from any served page",
      "models": [],
      "api": {
        "base_url": "https://token.sensenova.cn/v1",
        "key_url": "https://platform.sensenova.cn",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [],
        "note": "the base url is not printed on any server-rendered page — it is taken from the vendor's console docs and corroborated directly, since token.sensenova.cn/v1/models answers 401 `Authorization Not Found` in an OpenAI-shaped envelope. The callable ids live only in that JavaScript console, which no probe here can read, so none are published; the plan page names \"SenseNova 6.8 Flash Lite\" in prose alone."
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://www.sensenova.cn/token-plan",
        "keywords": [
          "公测期完全免费开放，付费档位即将上线",
          "60,000 积分 / 5 小时"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-08-14",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 88,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/sensenova/"
    },
    {
      "id": "hetzner-inference",
      "name": "Hetzner Inference API",
      "category": "api-free-tier",
      "url": "https://docs.hetzner.com/general/company-and-policy/experiments/inference/",
      "source_urls": [
        "https://docs.hetzner.com/general/company-and-policy/experiments/inference/",
        "https://experiments.hetzner.com/inference",
        "https://inference.hetzner.com/api/v1/models"
      ],
      "card_required": false,
      "offering": "OpenAI-compatible API on Hetzner's own EU hardware, free for as long as the experiment runs",
      "limits": "Hetzner answers it in its own FAQ: \"As long as the Inference API remains in experimental status, it is free of charge. Should this status change, we will notify you in advance via email with detailed information.\" Published per API key: 4M input and 100k output tokens per 60s, plus 10 requests per 60s, HTTP 429 over either. No daily, monthly or lifetime cap is published and no end date is named — the same page calls the service experimental, \"provided for experimental purposes only\" and offered as is, with performance and availability not guaranteed and no backups. A Hetzner account is needed to mint a token and the docs do not say whether a payment method is required; Hetzner's own fraud-prevention page offers a card charge as one of several verification routes (read 2026-08-30)",
      "models": [
        {
          "family": "qwen3.6",
          "released": ""
        },
        {
          "family": "qwen3.8-27b",
          "tier": "strong",
          "released": "",
          "aa_model": "qwen3-8-27b"
        }
      ],
      "api": {
        "base_url": "https://inference.hetzner.com/api/v1",
        "key_url": "https://experiments.hetzner.com/inference",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "Qwen/Qwen3.6-35B-A3B-FP8",
          "Qwen3.8-27B"
        ],
        "note": "both ids are 262K-context and take text and images; /v1/models, /v1/completions and /v1/chat/completions are the whole surface. The key is minted in the Inference tab of experiments.hetzner.com, which is a client-rendered page behind a Hetzner login — the readable copy of the terms is the docs page this row probes"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://docs.hetzner.com/general/company-and-policy/experiments/inference/",
        "keywords": [
          "remains in experimental status, it is free of charge",
          "https://inference.hetzner.com/api/v1"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-08-30",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 55,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/hetzner-inference/"
    },
    {
      "id": "uncloseai",
      "name": "uncloseai (unturf)",
      "category": "api-free-tier",
      "url": "https://uncloseai.com",
      "source_urls": [
        "https://uncloseai.com/",
        "https://hermes.ai.unturf.com/v1/models"
      ],
      "card_required": false,
      "offering": "Keyless OpenAI-compatible chat endpoint — no signup, no key, no account",
      "limits": "No quota is published anywhere on the site. The offer is a sentence — \"we offer free AI services powered by multiple AI models and a TTS (text-to-speech) endpoint … embodying the principles of both free as in beer & free as in freedom\" — and the page names three endpoints, of which one serves text today: hermes.ai.unturf.com/v1 answered a keyless chat completion on 2026-08-30, while qwen.ai.unturf.com/v1 answers 403 `Access denied - This endpoint is closed`. The served id is not the one the page's own examples call, and the vendor says so — \"See our Model Discovery docs to query the current model IDs being hosted\" — so the id lives in api.model_ids and the Free models column stays empty",
      "models": [],
      "api": {
        "base_url": "https://hermes.ai.unturf.com/v1",
        "auth": "none",
        "openai_compatible": true,
        "model_ids": [
          "Lorbus/Qwen3.6-27B-int4-AutoRound"
        ],
        "note": "anonymous: the catalog and chat/completions both answer with no Authorization header at all. One id is served at a time and it rotates — the endpoint is named after Hermes and serves a Qwen build today — so treat the id as this week's, not the offer"
      },
      "probe": {
        "type": "api-models",
        "endpoint": "https://hermes.ai.unturf.com/v1/models",
        "keywords": [],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-08-30",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 97,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/uncloseai/"
    },
    {
      "id": "regolo",
      "name": "Regolo AI",
      "category": "trial",
      "url": "https://regolo.ai/pricing/",
      "source_urls": [
        "https://api.regolo.ai/v1/models",
        "https://docs.regolo.ai/"
      ],
      "card_required": false,
      "offering": "EU (Italian) zero-retention inference; a month of full model access on a daily token allowance, no card",
      "limits": "\"Start your 30-day free trial ... No credit card required, no commitment\": the trial card names \"1 month duration\" (\"Full access for 30 days, then choose a plan\"), \"1M tokens per day\" and \"Stricter rate limits\" with \"Fair usage throttling applies\", against \"All Core Models\", which on the same page is every chat model in the library table (each marked Included under Core). Nothing survives the 30 days — the page names no grant after it, only paid plans — and the daily figure is the only number the trial publishes. One model is priced at €0.00 in and out outside any trial, the in-house brick-v1-beta (read 2026-09-16)",
      "models": [
        {
          "family": "glm-5",
          "released": "",
          "aa_model": "glm-5"
        },
        {
          "family": "gpt-oss",
          "released": ""
        },
        {
          "family": "qwen3.8-27b",
          "tier": "strong",
          "released": "",
          "aa_model": "qwen3-8-27b"
        },
        {
          "family": "llama-3.3",
          "released": "",
          "aa_model": "llama-3-3-instruct-70b"
        },
        {
          "family": "apertus-70b",
          "released": "",
          "aa_model": "apertus-70b-instruct"
        }
      ],
      "api": {
        "base_url": "https://api.regolo.ai/v1",
        "key_url": "https://dashboard.regolo.ai",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "glm5.2",
          "gpt-oss-120b",
          "qwen3.8-27b",
          "Llama-3.3-70B-Instruct",
          "apertus-70b",
          "brick-v1-beta"
        ],
        "note": "GET /v1/models is public and needs no key, but it publishes ids only — the prices and the trial terms are on the pricing page this row probes. brick-v1-beta is the one id priced at zero on that page"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://regolo.ai/pricing/",
        "keywords": [
          "1M tokens per day",
          "No credit card required, no commitment"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "catalog": "https://api.regolo.ai/v1/models",
        "machinery_keywords": []
      },
      "first_seen": "2026-08-30",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 75,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/regolo/"
    },
    {
      "id": "freebuff",
      "name": "Freebuff",
      "category": "agent-cli",
      "url": "https://freebuff.com",
      "source_urls": [
        "https://freebuff.com/",
        "https://freebuff.com/cli",
        "https://freebuff.com/terms-of-service"
      ],
      "card_required": false,
      "offering": "Ad-funded coding agent — CLI, desktop, web, cloud and chat — with no API key and no card; GLM 5.3 Flash by default, with DeepSeek V4.1 Flash, GPT-5.6 Luna and MiMo 2.5 in the picker",
      "limits": "\"Freebuff is supported by text ads.\" The free allowance is a daily budget of Freebucks spent on one-hour model sessions, set by where you connect from: 100 a day in the US, 70 or 40 in 23 other named countries (Canada, the UK, Ireland, Australia, New Zealand, South Korea and much of Western and Northern Europe), and 25 anywhere else or over a VPN, where Freebuff runs in limited mode. 100 Freebucks buy 20 hours of GLM 5.3 Flash, 10 of MiMo 2.5, 6 of DeepSeek V4.1 Flash or 5 of GPT-5.6 Luna; they refill at midnight Pacific and do not carry over. \"Freebuff collects prompts, messages, code, files, repository data, and agent traces when you use features that need them\", and DeepSeek V4.1 Flash and Muse Spark 1.2 are marked \"May use data for AI training\". Solar Pro 4 (\"Limited-time trial\") and the queued Muse Spark 1.2 stay out of the models column. Read 2026-09-16",
      "models": [
        {
          "family": "glm-5.3-flash",
          "tier": "strong",
          "released": "",
          "aa_model": "glm-5-3-flash"
        },
        {
          "family": "deepseek-v4.1-flash",
          "tier": "strong",
          "released": "",
          "aa_model": "deepseek-v4-1-flash"
        },
        {
          "family": "gpt-5.6-luna",
          "tier": "strong",
          "released": "",
          "aa_model": "gpt-5-6-luna"
        },
        {
          "family": "mimo-v2.5",
          "released": "",
          "aa_model": "mimo-v2-5-0424"
        }
      ],
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://freebuff.com/",
        "keywords": [
          "Freebuff is supported by text ads",
          "Freebucks every day"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-09-02",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 28,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/freebuff/"
    },
    {
      "id": "meganova",
      "name": "MegaNova",
      "category": "aggregator",
      "url": "https://meganova.ai",
      "source_urls": [
        "https://docs.meganova.ai/free-model-quota",
        "https://docs.meganova.ai/tiers/tier-1.md",
        "https://docs.meganova.ai/legal-docs/terms-of-service.md",
        "https://api.meganova.ai/v1/models"
      ],
      "card_required": false,
      "offering": "OpenAI-compatible gateway whose no-card Tier 1 account gets 50 free requests a day on each of Mistral Small 3.2 and the house Manta routers — 550 a day across its free rows",
      "limits": "Tier 1 is \"Free registration — no credit card required\", with \"Free Access Models (<100B), including Manta Mini\". The Free Model Quota table gives a Tier 1 account 50 requests a day (\"50 RPD (Requests Per Day)\") on each of Mistral-Small-3.2-24B, Manta Mini and Manta Flash, and on several roleplay fine-tunes, an embedding model and a reranker — \"Total Free Quota per day 550\", with a \"daily reset at 00:00 UTC\" — and 0 on GLM-4.7-Flash and Manta Pro until a \"$1 deposit\" moves the account to Tier 2. The terms say \"Free modules are for evaluation and interactive use only and are not designed for production or unattended batch workloads\". The operator is Nebula Nova Inc., a Delaware corporation. Read 2026-09-16",
      "models": [
        {
          "family": "mistral-small-3.2",
          "released": "2025-06",
          "aa_model": "mistral-small-3-2"
        }
      ],
      "api": {
        "base_url": "https://api.meganova.ai/v1",
        "key_url": "https://www.meganova.ai/api-keys",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "mistralai/Mistral-Small-3.2-24B-Instruct-2506",
          "meganova-ai/manta-mini-1.0",
          "meganova-ai/manta-flash-1.0"
        ],
        "ignored_ids": [
          "zai-org/GLM-4.7-Flash",
          "meganova-ai/manta-pro-1.0",
          "Systran/faster-whisper-large-v3",
          "Qwen/Qwen3-Embedding-8B",
          "BAAI/bge-reranker-v2-m3",
          "BruhzWater/Sapphira-L3.3-70b-0.1",
          "FallenMerick/MN-Violet-Lotus-12B",
          "Steelskull/L3.3-MS-Nevoria-70b",
          "Sao10K/L3-70B-Euryale-v2.1",
          "Sao10K/L3-8B-Stheno-v3.2"
        ],
        "note": "the three ids listed are the chat rows a Tier 1 account can call for free; ten more zero-priced rows are ignored on purpose — zai-org/GLM-4.7-Flash and manta-pro-1.0 have a Tier 1 quota of 0, faster-whisper, Qwen3-Embedding-8B and bge-reranker-v2-m3 are not chat models, and five are roleplay fine-tunes (four of Llama, one of Mistral NeMo). Manta Mini and Manta Flash are MegaNova's own routers, tagged best_role_play in the catalog, so Mistral Small 3.2, at 8,192 tokens of context, is the one named coding model on the lane"
      },
      "probe": {
        "type": "api-models",
        "endpoint": "https://api.meganova.ai/v1/models",
        "keywords": [],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": true,
        "machinery_keywords": []
      },
      "first_seen": "2026-09-02",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 85,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/meganova/"
    },
    {
      "id": "llmtr",
      "name": "LLMTR",
      "category": "aggregator",
      "url": "https://llmtr.com",
      "source_urls": [
        "https://llmtr.com/docs/migration/openai-openrouter/",
        "https://llmtr.com/docs/en/billing/",
        "https://llmtr.com/docs/en/gateway/poolside-laguna/",
        "https://llmtr.com/privacy",
        "https://llmtr.com/v1/models"
      ],
      "card_required": false,
      "offering": "Turkish OpenAI-compatible gateway whose free rows answer on a zero balance — thirteen zero-priced chat ids on 2026-09-16, Nemotron 3 Ultra, Qwen3.6 27B and Agnes 3.0 Flash among them",
      "limits": "A new account calls the free rows before any top-up: the migration guide says \"Model kataloğunda ücretsiz olarak işaretlenen bir chat modelini seçin\" (pick a chat model marked free in the catalog), and \"Bu adım, sıfır bakiye ile gateway ve kullanım kaydı akışının çalıştığını doğrular\" (this step checks that the gateway and usage logging work on a zero balance). Four free rows carry a daily quota whose figure is published nowhere (Nemotron 3 Ultra and Super, Qwen3.6 27B, Ling 3.0 Flash Fin); Laguna XS 2.1 is free because \"Poolside serves these models free on its own inference API\", with \"no extra token allowance to track\"; three rows are free \"22 Eylul 2026'ya kadar\" (until 22 September 2026), and dots-3-note-preview closes on 30 September 2026. Paid use is prepaid credit: \"An 8% platform margin is added on top of the requested top-up amount\" and \"We never modify model prices\". The privacy page says prompt and response bodies are not written permanently to its usage and billing database (\"kalıcı olarak yazılmaz\"). Read 2026-09-16",
      "models": [
        {
          "family": "nemotron-3-ultra",
          "released": "2026-03",
          "aa_model": "nvidia-nemotron-3-ultra-550b-a55b"
        },
        {
          "family": "qwen3.6",
          "released": "2026-04"
        }
      ],
      "api": {
        "base_url": "https://llmtr.com/v1",
        "key_url": "https://llmtr.com/dashboard/api-keys",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "nvidia/nemotron-3-ultra-550b-a55b",
          "nvidia/nemotron-3-super-120b-a12b",
          "qwen/qwen3.6-27b-free",
          "poolside/laguna-xs-2.1",
          "inclusionai/ling-3.0-flash-fin",
          "dots-studio/dots-3-note-preview",
          "openai/gpt-oss-safeguard-20b",
          "qwen/qwen3.8-flash-free",
          "inclusionai/ling-3.0-flash-vl",
          "inclusionai/ling-3.0-flash-sante",
          "agnes/agnes-3.0-flash",
          "agnes/agnes-2.5-flash",
          "motif/motif-3"
        ],
        "ignored_ids": [
          "liquid/lfm-2.5-embedding-350m-free"
        ],
        "note": "the thirteen ids are every chat row the public catalog prices at 0 on 2026-09-16, motif/motif-3 created that evening. qwen/qwen3.8-flash-free, inclusionai/ling-3.0-flash-vl and inclusionai/ling-3.0-flash-sante are free only until 22 September 2026, and dots-studio/dots-3-note-preview closes on 30 September 2026. nvidia/nemotron-3-ultra-550b-a55b is the free daily-quota row and its -262k twin the metered one; openai/gpt-oss-safeguard-20b is a content classifier rather than a coding model. liquid/lfm-2.5-embedding-350m-free is ignored as an embeddings row"
      },
      "probe": {
        "type": "api-models",
        "endpoint": "https://llmtr.com/v1/models",
        "keywords": [],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": true,
        "machinery_keywords": []
      },
      "first_seen": "2026-09-02",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 45,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/llmtr/"
    },
    {
      "id": "qodo",
      "name": "Qodo",
      "category": "trial",
      "url": "https://www.qodo.ai",
      "source_urls": [
        "https://www.qodo.ai/pricing/",
        "https://www.qodo.ai/terms-of-use/"
      ],
      "card_required": false,
      "offering": "Agentic PR code review plus Git and IDE integrations on a 14-day Pro Team trial with unlimited reviews and credits and no card",
      "limits": "\"Free 14 Day Trial no credit card\" with \"Unlimited reviews\" and \"Unlimited credits\" is the whole free offer on the pricing page, and the FAQ beside it says so: \"Is there a free plan? We don't offer a permanent free tier. After your trial, pick a paid plan to keep reviewing.\" The plan it trials is \"Pro Team $30\", \"$.012/credit, pooled across the team\", \"Designed for up to 30 users\", \"Monthly billing • no commitment\". The Terms grant Qodo a licence to use customer data \"to train and improve the Platform's, the Qodo Models and Services' performance\", while the pricing FAQ says \"Qodo does not train models on your code\". A standing free lane exists for one audience: \"Qualified open source projects can apply to the Qodo for Open Source program for free access\". Which models the trial runs on is not stated. Read 2026-09-16",
      "models": [],
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://www.qodo.ai/pricing/",
        "keywords": [
          "Free 14 Day Trial",
          "Unlimited credits"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-09-02",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 85,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/qodo/"
    },
    {
      "id": "codebuddy",
      "name": "CodeBuddy (Tencent)",
      "category": "trial",
      "url": "https://www.codebuddy.ai",
      "source_urls": [
        "https://www.codebuddy.ai/docs/ide/Account/pricing",
        "https://www.codebuddy.ai/docs/ide/Account/Subscription",
        "https://www.codebuddy.ai/document/term"
      ],
      "card_required": false,
      "offering": "Tencent's VS Code / JetBrains / CLI coding agent whose Free plan carries 100 credits a month, a daily activity bonus of 30 and 250 welcome credits, with every model open while the promotion runs",
      "limits": "The docs price table gives Free \"Base Credits / Month 100\", a \"Promotional Bonus (Limited-Time Offer)\" of 30 credits a day, 5,000 completions a month (\"unlimited during the promotional period\") and auto routing (\"all models available during the promotional period\"); \"Standard quotas resume when the promotion ends\", and \"The end date of this promotion will be announced separately\". \"Base and bonus credits are issued monthly and are valid for that month; they do not roll over\", and \"New users receive 250 credits immediately upon their first sign-in. The credits are valid for 14 days\". No card for Free — only the 7-day Pro trial asks for one. The docs name no model for the plan. The terms are Tencent Cloud International Pte. Ltd.'s and require users \"at least 18 years old\". Read 2026-09-02",
      "models": [],
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://www.codebuddy.ai/docs/ide/Account/pricing",
        "keywords": [
          "100 credits",
          "Base and bonus credits are issued monthly and are valid for that month",
          "Individual Plans"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-09-02",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": false,
      "rank": 65,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/codebuddy/"
    },
    {
      "id": "freeinference",
      "name": "FreeInference (Harvard SEAS)",
      "category": "api-free-tier",
      "url": "https://freeinference.org",
      "source_urls": [
        "https://freeinference.org/",
        "https://doc.freeinference.org/models",
        "https://doc.freeinference.org/claude-code.html",
        "https://freeinference.org/terms",
        "https://freeinference.org/v1/models"
      ],
      "card_required": false,
      "offering": "Harvard SEAS's MadSys Lab serving open models — DeepSeek V4 Flash, GLM-5.1, GLM 5.3 Flash, MiniMax M3, Qwen3.6 35B — free to every account behind both an OpenAI-shaped and an Anthropic-shaped endpoint, with a documented Claude Code setup",
      "limits": "No quota figure is published: the landing page says \"Free to use\", \"No credit card required\" and \"Generous quota for research and prototyping\", and the terms say \"Quotas, rate limits, model access, and usage limits may change based on usage, demand, infrastructure capacity, abuse prevention, operational needs, and individual or aggregate activity\". It is \"an experimental research service\", and prompts are not private: \"All prompts and responses may be logged for research purposes\" and \"sanitized prompts and responses, usage statistics, and routing metrics — may be published or open-sourced\". The models page splits the catalog: \"Free accounts can use models marked Free. Models marked Pro require a Pro-enabled key\" — seven chat ids Free and three Pro (glm-5.2, glm-5.3, kimi-k2.7-code), read 2026-09-05",
      "models": [
        {
          "family": "deepseek-v4-flash",
          "tier": "strong",
          "released": "",
          "aa_model": "deepseek-v4-flash"
        },
        {
          "family": "glm-5.1",
          "released": "",
          "aa_model": "glm-5-1"
        },
        {
          "family": "glm-5.3-flash",
          "tier": "strong",
          "released": "",
          "aa_model": "glm-5-3-flash"
        },
        {
          "family": "minimax-m3",
          "tier": "strong",
          "released": "",
          "aa_model": "minimax-m3"
        },
        {
          "family": "qwen3.6",
          "released": ""
        }
      ],
      "api": {
        "base_url": "https://freeinference.org/v1",
        "key_url": "https://freeinference.org",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "deepseek-v4-flash",
          "qwen3.6-35b",
          "diffusiongemma"
        ],
        "anthropic_base_url": "https://freeinference.org/anthropic",
        "note": "the three ids are the chat rows the keyless catalog at freeinference.org/v1/models returned on 2026-09-05 (bge-m3, the fourth, is an embedding model); the docs mark four more chat ids Free, which stay out of the generated configs until a keyed read confirms them. The catalog's prices are upstream reference accounting, \"not fees charged by FreeInference to users\". The same key serves https://freeinference.org/anthropic, which the docs give as Claude Code's ANTHROPIC_BASE_URL"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://doc.freeinference.org/models",
        "keywords": [
          "free accounts can use models marked"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "catalog": "https://freeinference.org/v1/models",
        "machinery_keywords": []
      },
      "first_seen": "2026-09-05",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": true,
      "rank": 91,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/freeinference/"
    },
    {
      "id": "opentyphoon",
      "name": "OpenTyphoon (SCB 10X)",
      "category": "api-free-tier",
      "url": "https://opentyphoon.ai",
      "source_urls": [
        "https://docs.opentyphoon.ai/en/faq/",
        "https://docs.opentyphoon.ai/en/rate-limits/",
        "https://api.opentyphoon.ai/v1/models"
      ],
      "card_required": false,
      "offering": "Thai-tuned open models from SCB 10X, the venture arm of Siam Commercial Bank, behind an OpenAI-compatible API whose FAQ calls it a research showcase and free to use",
      "limits": "Rate limits are the published ceiling — 5 requests per second and 200 per minute on typhoon-v2.5-30b-a3b-instruct, 2 and 20 on typhoon-ocr — with no token, daily or monthly cap stated; higher limits are by email \"with details about your use case, expected volume, and requirements\". The FAQ answers the price in one sentence, \"The Typhoon API is a research showcase and free to use\", and names the trade in the next: \"Yes, we are collecting usage data from the Typhoon API\", used \"to improve the model and the API\" and, it says, never shared with third parties. Production use is pointed elsewhere — \"please support us by using the API through Together AI\" — and the paid API Pro that ran there sunset on 2025-12-31 with an AWS successor announced for Q1 2026 that had not appeared by this read (2026-09-05). A key is minted in the playground after signing up; no card is mentioned on any page read",
      "models": [],
      "api": {
        "base_url": "https://api.opentyphoon.ai/v1",
        "key_url": "https://playground.opentyphoon.ai/api-key",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "typhoon-v2.5-30b-a3b-instruct"
        ],
        "note": "the one chat id in the keyless catalog on 2026-09-05; the other five rows are OCR (typhoon-ocr, typhoon-ocr-v1.5, typhoon-ocr-preview) and speech (typhoon-asr-realtime, typhoon-isan-asr-realtime). Typhoon 2.5 is a Qwen3-30B-A3B fine-tune for Thai, so it is a Qwen-class coder that also reads Thai; the Free models column stays empty because the FAQ the probe reads names no model"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://docs.opentyphoon.ai/en/faq/",
        "keywords": [
          "the typhoon api is a research showcase and",
          "free to use"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "catalog": "https://api.opentyphoon.ai/v1/models",
        "machinery_keywords": []
      },
      "first_seen": "2026-09-05",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": true,
      "rank": 86,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/opentyphoon/"
    },
    {
      "id": "ibm-watsonx-ai",
      "name": "IBM watsonx.ai (Lite plan)",
      "category": "api-free-tier",
      "url": "https://www.ibm.com/products/watsonx-ai",
      "source_urls": [
        "https://www.ibm.com/docs/en/watsonx/saas?topic=cloud-watsonxai-runtime-plans",
        "https://www.ibm.com/docs/en/watsonx/saas?topic=tutorials-signing-up-watsonx",
        "https://www.ibm.com/products/watsonx-ai/pricing"
      ],
      "card_required": true,
      "offering": "IBM's watsonx.ai Runtime on its Lite plan — 300,000 tokens a month of foundation-model inference (Granite, Llama, Mistral and other hosted models) on IBM Cloud, a plan IBM's own docs call free and never bill",
      "limits": "\"300,000 tokens per month\", \"20 CUH per month\" of compute and \"2 inference requests per second\", on \"A free plan with limited capacity\" — the Lite plan of watsonx.ai Runtime as its service-plans page reads on 2026-09-16, with no expiry named. The card is taken at the door and not charged: the sign-up doc says \"For your IBM Cloud account, you enter your email address, personal information, and credit card information, which is used to verify your identity\" and \"Lite plans do not incur charges\". Which foundation models the 300,000 tokens reach is on a separate docs page the probe does not read, which is why the Free models column is empty",
      "models": [],
      "api": {
        "base_url": "https://us-south.ml.cloud.ibm.com/ml/v1",
        "key_url": "https://cloud.ibm.com/iam/apikeys",
        "auth": "api-key",
        "openai_compatible": false,
        "model_ids": [],
        "note": "not OpenAI-shaped: the API key is exchanged for an IAM bearer token, chat is POST /ml/v1/text/chat with a project_id in the body and a version date in the query, and the host is per region (us-south.ml.cloud.ibm.com is Dallas). LiteLLM's watsonx provider and the ibm-watsonx-ai SDK wrap it; a plain OpenAI client cannot"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://www.ibm.com/docs/en/watsonx/saas?topic=cloud-watsonxai-runtime-plans",
        "keywords": [
          "300,000 tokens per month",
          "2 inference requests per second"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-09-05",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": true,
      "rank": 98,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/ibm-watsonx-ai/"
    },
    {
      "id": "sarvam",
      "name": "Sarvam AI",
      "category": "trial",
      "url": "https://www.sarvam.ai",
      "source_urls": [
        "https://docs.sarvam.ai/api/getting-started/pricing.md",
        "https://docs.sarvam.ai/api/getting-started/ratelimits.md",
        "https://docs.sarvam.ai/api-reference/authentication.md",
        "https://docs.sarvam.ai/api-reference/beta-apis.md"
      ],
      "card_required": false,
      "offering": "India's Sarvam AI credits every new account ₹100 that never expire, spendable on any of its APIs — including its own Sarvam-105B chat model on an OpenAI-shaped endpoint",
      "limits": "\"Every new user receives ₹100 worth of free credits to explore all our APIs\", and the credits \"are universal and never expire\". Sarvam-105B costs ₹29.28 in and ₹73.2 out per 1M tokens, so the grant is about 3 million input tokens, and the Starter plan allows 40 chat requests a minute. DeepSeek V4 Flash, GLM 5.3 and Gemma 4 31B are served only on /v2/chat/completions, a beta that is \"not enabled by default with standard API subscription keys\" and is granted per key on request. No page read mentions a card (2026-09-16)",
      "models": [
        {
          "family": "sarvam-105b",
          "released": "",
          "aa_model": "sarvam-105b"
        }
      ],
      "api": {
        "base_url": "https://api.sarvam.ai/v1",
        "key_url": "https://dashboard.sarvam.ai",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "sarvam-105b",
          "sarvam-105b-conversations"
        ],
        "note": "the vendor's own header is api-subscription-key, and the same key is accepted as \"Authorization: Bearer\" on every endpoint. /v1/chat/completions serves only sarvam-105b and sarvam-105b-conversations; the open models are on the /v2 beta, whitelisted per key. Prices are in rupees"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://docs.sarvam.ai/api/getting-started/pricing.md",
        "keywords": [
          "₹100 worth of free credits"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-09-05",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": true,
      "rank": 88,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/sarvam/"
    },
    {
      "id": "standardcompute",
      "name": "Standard Compute",
      "category": "trial",
      "url": "https://standardcompute.com",
      "source_urls": [
        "https://standardcompute.com/free-trial",
        "https://standardcompute.com/pricing",
        "https://standardcompute.com/integrations/claude-code"
      ],
      "card_required": false,
      "offering": "A one-time $0.25 of smart-routed compute on a flat-rate agent gateway, no card — a real key on both wires, OpenAI-compatible Chat Completions and an Anthropic Messages base Claude Code takes as it is",
      "limits": "\"Eligible new accounts receive $0.25 of trial compute after activation. This is a finite platform compute allowance. It is not a recurring free tier, a fixed token count, or a value measured at another provider's prices\" — the free-trial page, \"Updated September 5, 2026\", read here 2026-09-16; the pricing FAQ adds \"with no card required\". It does not refill, no card is asked for, and it is discretionary: \"Access is subject to eligibility and availability\", with a support address for accounts whose dashboard does not offer it. What the quarter buys is on no page — a flat-rate router publishes no per-token price, and the only conversion the site offers is its own marketing arithmetic, a $20 monthly compute budget on the paid Starter plan that its pricing table says does the work of up to $60 a month of direct API use. The vendor sets the expectation itself: \"Start with one small request that lets you check the connection and response\", while \"a longer coding-quality comparison may need a paid allowance\". It is the smallest offer on this list — a connection test, not a working allowance",
      "models": [],
      "api": {
        "base_url": "https://api.stdcmpt.com/v1",
        "key_url": "https://standardcompute.com/signup",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "anthropic/claude-standardcompute",
          "StandardCompute"
        ],
        "anthropic_base_url": "https://api.stdcmpt.com",
        "note": "one key, two wires: https://api.stdcmpt.com/v1 for OpenAI-shaped clients and https://api.stdcmpt.com for Claude Code — \"For Claude Code, use https://api.stdcmpt.com without /v1\". /v1/models is keyless and lists the pool the router picks from, 40 unpriced ids on 2026-09-07 with Claude, GPT and Grok among them; requests are smart-routed across it unless a call pins one id. The two ids here are the router's own"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://standardcompute.com/free-trial",
        "keywords": [
          "$0.25 of trial compute",
          "no card required"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-09-07",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": true,
      "rank": 95,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/standardcompute/"
    },
    {
      "id": "routerplex",
      "name": "RouterPlex",
      "category": "trial",
      "url": "https://routerplex.com",
      "source_urls": [
        "https://routerplex.com/",
        "https://docs.routerplex.com/",
        "https://routerplex.com/terms",
        "https://docs.routerplex.com/claude-code"
      ],
      "card_required": false,
      "offering": "A one-time $1 of test credit on a prepaid reseller that bills 54 chat models at vendor list prices with 0% markup, no card — one key on both wires, OpenAI-compatible Chat Completions and an Anthropic Messages base Claude Code takes as it is",
      "limits": "\"$1 test credit for your first integration after email verification. No card required\" on the home page, and the docs quickstart: \"Eligible verified accounts receive $1 in test credit once\" — read 2026-09-11. What the dollar buys is the list price of whatever it is spent on: the home page states \"vendor list prices with 0% markup\", so at deepseek-v4-flash it is an afternoon of work and at claude-opus-5 a handful of turns. The terms (last updated July 13, 2026) narrow it: \"Until an account makes its first paid top-up, promotional credit may be usable only with a subset of models and at reduced rate limits\", \"no promotional credit is guaranteed\", and one account per person. Which models the subset holds is on no page. Continuing costs a top-up \"from $5 by card or $12 by crypto\"; purchased credit does not expire. No legal entity is named on /terms or /about — the terms speak of \"upstream providers\" whose \"own usage policies\" apply — and /v1/models answers 403 without a key, so nothing here is read off the catalog. A connection test with a little work in it, one step above the smallest trial on this list",
      "models": [],
      "api": {
        "base_url": "https://api.routerplex.com/v1",
        "key_url": "https://routerplex.com/sign-up",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "deepseek-v4-flash",
          "glm-5.3-flash",
          "claude-sonnet-4-6"
        ],
        "anthropic_base_url": "https://api.routerplex.com",
        "note": "ids are the catalog page's own spellings (routerplex.com/models, 54 chat ids on 2026-09-11); the vendor's Claude Code page sets ANTHROPIC_BASE_URL=https://api.routerplex.com and ANTHROPIC_MODEL=claude-sonnet-4-6 (guide reviewed 2026-09-13), the Anthropic SDK appending /v1/messages itself. /v1/models is keyed, so none of these ids is checked against a catalog, and which of them the promotional credit can call is not published"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://routerplex.com/",
        "keywords": [
          "$1 test credit",
          "No card required"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-09-11",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": true,
      "rank": 93,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/routerplex/"
    },
    {
      "id": "cline",
      "name": "Cline",
      "category": "agent-cli",
      "url": "https://cline.bot",
      "source_urls": [
        "https://docs.cline.bot/getting-started/free-models",
        "https://api.cline.bot/api/v1/ai/cline/recommended-models",
        "https://docs.cline.bot/getting-started/cline-provider"
      ],
      "card_required": false,
      "offering": "Open-source coding agent for VS Code, JetBrains and the terminal; signing in to its own Cline provider unlocks a rotating set of free models, each with a daily allowance, beside pay-as-you-go credits, the $9.99 ClinePass plan and BYOK",
      "limits": "\"Cline periodically offers free model promotions that let you try select models at no cost, up to a limited usage quota\", and \"Free models are available to any user with a Cline account\" — a sign-in with Google, GitHub or email, no card. No figure is published; the quota is counted per model and per day, which is how Cline's clients word the stop: `You've reached today's free usage limit for this model`. The lane is the free list the model picker reads, keyless at api.cline.bot, and it turns over \"on a rotating, limited-time basis\" — ids change within a day, so only Laguna S 2.1, in the lane since July, is in the Models column. The free-models page states two limits outright: \"Free model usage is not supported through the Cline API. Free models are only available in the Cline IDE Extension and CLI\", and \"Free model usage may be used to help improve model performance and quality\". Read 2026-09-14",
      "models": [
        {
          "family": "laguna-s-2.1",
          "released": "2026-07"
        }
      ],
      "probe": {
        "type": "api-models",
        "endpoint": "https://api.cline.bot/api/v1/ai/cline/recommended-models",
        "keywords": [],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": [],
        "lane": "free"
      },
      "first_seen": "2026-09-14",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": true,
      "rank": 29,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/cline/"
    },
    {
      "id": "agnes-ai",
      "name": "Agnes AI",
      "category": "api-free-tier",
      "url": "https://agnes-ai.com",
      "source_urls": [
        "https://wiki.agnes-ai.com/en/docs/pricing",
        "https://wiki.agnes-ai.com/en/docs/faqs",
        "https://wiki.agnes-ai.com/en/docs/tokenplan"
      ],
      "card_required": false,
      "offering": "Agnes AI's own models behind an OpenAI-compatible API, with its Flash text models charged at zero today and image generation free beside them",
      "limits": "\"Is the API free to use? Yes. Our core AI models are free to use indefinitely\", the FAQ says, and the pricing page shows the mechanism: agnes-2.5-flash and agnes-3.0-flash list at $0.05 in / $0.15 out per 1M and are charged $0 — \"Cached input, input tokens, and output tokens are currently free for agnes-2.5-flash and agnes-3.0-flash\" — while agnes-2.5-pro bills $0.45/$0.90 and the pro beta $0.10/$0.30. The page is candid that the zero is a current price rather than a contract: \"Promotional end dates are subject to Agnes AI platform announcements and your account bill\". The ceiling is a rate, not a quota: a key that is neither on a paid Token Plan nor enterprise-verified gets 30 requests a minute allowed and 20 effective on text models (Token Plan FAQ, effective 2026-06-22), and no daily figure is published. Image models are free at every resolution too. The terms are governed by Singapore law. The docs live on wiki.agnes-ai.com. Read 2026-09-14",
      "models": [
        {
          "family": "agnes-3.0-flash",
          "tier": "strong",
          "released": "",
          "aa_model": "agnes-3-0-flash"
        },
        {
          "family": "agnes-2.5-flash",
          "released": ""
        }
      ],
      "api": {
        "base_url": "https://apihub.agnes-ai.com/v1",
        "key_url": "https://platform.agnes-ai.com",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "agnes-3.0-flash",
          "agnes-2.5-flash"
        ],
        "note": "the quickstart sends its chat completion to apihub.agnes-ai.com/v1/chat/completions with a Bearer key from the Agnes AI Platform dashboard; free and Token Plan keys draw on separate limit pools, and creating more keys of one type does not stack RPM"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://wiki.agnes-ai.com/en/docs/pricing",
        "keywords": [
          "Cached input, input tokens, and output tokens are currently free for",
          "agnes-3.0-flash"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-09-14",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": true,
      "rank": 87,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/agnes-ai/"
    },
    {
      "id": "yolo-auto",
      "name": "Yolo-Auto",
      "category": "api-free-tier",
      "url": "https://yolo-auto.com",
      "source_urls": [
        "https://yolo-auto.com/",
        "https://yolo-auto.com/pricing",
        "https://yolo-auto.com/models",
        "https://yolo-auto.com/docs",
        "https://yolo-auto.com/free-llm-api",
        "https://yolo-auto.com/about",
        "https://yolo-auto.com/terms",
        "https://huggingface.co/Qwen/Qwen3.8-Flash-Next"
      ],
      "card_required": false,
      "offering": "One model, Qwen3.8 Flash — Qwen's open-weight Qwen3.8-Flash-Next — served on the vendor's own flat-rate API for coding agents; the free plan is a small daily allowance with no card",
      "limits": "\"15 free requests a day. No card required.\" on the home page and \"No card required, free forever\" on the Free plan card, at 128K context, against $19/mo Builder and $39/mo Pro — a handful of agent turns a day. The model is Qwen3.8 Flash, id qwen3.8-flash, charted with Artificial Analysis scores for Qwen3.8-Flash-Next, the mixture-of-experts Qwen published open-weight on 2026-08-24 (about 180B parameters, 10 of 512 experts active). Yolo-Auto \"runs the model-serving stack rather than reselling a third-party model API\". The FAQ calls the free tier \"for testing\" where the plan card says \"free forever\", and the terms forbid using \"multiple accounts ... to combine capacity\". Sign-in is through Google, GitHub or Discord, and prompt and response bodies are \"not routinely retained\". Read 2026-09-17",
      "models": [
        {
          "family": "qwen3.8-flash",
          "tier": "strong",
          "released": "2026-08",
          "aa_model": "qwen3-8-flash-next"
        }
      ],
      "api": {
        "base_url": "https://yolo-auto.com/v1",
        "key_url": "https://yolo-auto.com/app",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "qwen3.8-flash"
        ],
        "note": "qwen3.8-flash is the one id the Free plan serves, \"the recommended model for coding, text, and tool use\" in the docs; qwen3.8-27b, the id this row carried until 2026-09-16, is still accepted from clients already configured with it, and yolo is a paid-only route whose server-side target can change. /v1/models and /v1/usage answer 401 without a key, and the free plan's context is 128K where Pro's is 256K"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://yolo-auto.com/",
        "keywords": [
          "15 free requests a day",
          "No card required, free forever"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-09-14",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": true,
      "rank": 99,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/yolo-auto/"
    },
    {
      "id": "jetbrains-ai",
      "name": "JetBrains AI (AI Free)",
      "category": "trial",
      "url": "https://www.jetbrains.com/ai/",
      "source_urls": [
        "https://www.jetbrains.com/help/ai-assistant/licensing-and-subscriptions.html",
        "https://lp.jetbrains.com/ai-ides-faq/",
        "https://www.jetbrains.com/help/ai-assistant/jetbrains-ai-subscription.html"
      ],
      "card_required": false,
      "offering": "AI Free in JetBrains IDEs — unlimited code completion on JetBrains' Mellum model and 3 AI Credits ($3) of cloud models every 30 days for chat and agents",
      "limits": "JetBrains' plans table lists \"AI Free Free 3 AI Credits per 30-days\" beside AI Pro's 10 for $10, and \"Each AI Credit equals $1 USD\"; one credit is \"about: ~10 requests to generate code in AI Chat. ~40 requests to generate code in the editor\", and the quota resets every 30 days from first use. AI Free also carries \"Unlimited code completion (powered by JetBrains’ Mellum model)\" and unlimited local models through Ollama or LM Studio. It needs an IDE licence: \"AI Free is available to all users with active JetBrains IDE licenses, including educational licenses, classroom licenses, open source licenses, IDE trial licenses\", but not in IntelliJ IDEA without Ultimate, PyCharm without Pro, or Android Studio — for someone paying nothing, an educational or open-source licence, or the free non-commercial licence of RustRover, WebStorm and Rider. Only the optional 30-day AI Pro trial asks for a card. The tier is \"only available in the serviceable territories, with the exception of Mainland China\". Read 2026-09-14",
      "models": [],
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://lp.jetbrains.com/ai-ides-faq/",
        "keywords": [
          "Unlimited code completion (powered by JetBrains’ Mellum model)",
          "A limited cloud quota for third-party models"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-09-14",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": true,
      "rank": 55,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/jetbrains-ai/"
    },
    {
      "id": "zed",
      "name": "Zed",
      "category": "trial",
      "url": "https://zed.dev",
      "source_urls": [
        "https://zed.dev/pricing",
        "https://zed.dev/docs/account/plans-and-pricing"
      ],
      "card_required": false,
      "offering": "Open-source code editor with a hosted AI agent: a 14-day Pro trial with $5 of GPT-5.6 Luna and unlimited edit predictions, no card, then 2,000 accepted edit predictions on the $0 Personal plan",
      "limits": "\"We offer a 14-day free trial of Pro with $5 of GPT-5.6 Luna usage and unlimited accepted edit predictions. No credit card is required. The trial ends when you use the $5 balance or 14 days pass, whichever comes first.\" \"GPT-5.6 Luna is the only hosted model available during the free trial\", and the balance is shared with Delta, Zed's other app. Trials \"automatically convert to Zed Free\" — the $0 Personal plan, whose \"2,000 accepted edit predictions\" carry no period on the page; Pro is $10 a month with $5 of monthly token credit. Read 2026-09-16",
      "models": [
        {
          "family": "gpt-5.6-luna",
          "tier": "strong",
          "released": "",
          "aa_model": "gpt-5-6-luna"
        }
      ],
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://zed.dev/pricing",
        "keywords": [
          "14-day free trial of Pro with $5 of GPT-5.6 Luna usage",
          "2,000 accepted edit predictions"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-09-16",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": true,
      "rank": 80,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/zed/"
    },
    {
      "id": "token-harbor",
      "name": "Token Harbor",
      "category": "aggregator",
      "url": "https://tokenharbor.ai",
      "source_urls": [
        "https://tokenharbor.ai/pricing",
        "https://tokenharbor.ai/faq",
        "https://tokenharbor.ai/terms",
        "https://tokenharbor.ai/models"
      ],
      "card_required": false,
      "offering": "OpenAI-compatible gateway with a $0 plan: explicit :free ids for DeepSeek V4.1 Flash, DeepSeek V4 Flash and MiMo V2.5 on a value-based allowance, no card",
      "limits": "\"Free $0 / month Try Token Harbor with a free allowance and a rotating model lineup\" and \"No card required\", and the FAQ: \"Token Harbor provides free access to selected models through explicit :free model IDs. Your first free request starts a personal rolling 7-day period. The allowance is value-based rather than a fixed request count\" — no figure is published, and the pricing card calls the same allowance \"Included every month (4 weeks)\". \"Free routes are disabled by default\" until you consent to them, and \"Token Harbor may retain prompts and responses sent through explicit free routes after you opt in\". The operator is Token Harbor PTE. LTD. Read 2026-09-16",
      "models": [
        {
          "family": "deepseek-v4.1-flash",
          "tier": "strong",
          "released": "",
          "aa_model": "deepseek-v4-1-flash"
        },
        {
          "family": "mimo-v2.5",
          "released": "",
          "aa_model": "mimo-v2-5-0424"
        }
      ],
      "api": {
        "base_url": "https://tokenharbor.ai/v1",
        "key_url": "https://tokenharbor.ai/dashboard/api-keys",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "deepseek-v4.1-flash:free",
          "deepseek-v4-flash:free",
          "mimo-v2.5:free"
        ],
        "note": "the :free suffix selects the free route, which has to be switched on in the dashboard first; /v1/models needs a key, so the ids are the free rows the models page publishes (2026-09-16)"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://tokenharbor.ai/pricing",
        "keywords": [
          "Try Token Harbor with a free allowance and a rotating model lineup",
          "Included every month (4 weeks)"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-09-16",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": true,
      "rank": 75,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/token-harbor/"
    },
    {
      "id": "nous-portal",
      "name": "Nous Portal (Hermes Agent)",
      "category": "aggregator",
      "url": "https://portal.nousresearch.com",
      "source_urls": [
        "https://portal.nousresearch.com/",
        "https://hermes-agent.nousresearch.com/docs/guides/run-nemotron-3-ultra-free",
        "https://inference-api.nousresearch.com/v1/models"
      ],
      "card_required": false,
      "offering": "Nous Research's inference portal behind its Hermes Agent: a $0 Free plan limited to the models it prices at zero — eight on 2026-09-16, Step 3.7 Flash and Laguna S 2.1 among them — on an OpenAI-compatible API",
      "limits": "The portal's plan table reads \"Free $0 Free models only Standard rate limits $0 monthly credits Try Hermes\", and the Hermes Agent guide has you \"create a Nous Portal account (or sign in), choose the Free plan, and authorize Hermes\" — \"The :free tag is what keeps it on the no-cost plan\". No rate-limit figure is published and no page read mentions a card. The keyless catalog prices eight rows at zero; a call without a key answers HTTP 402 with a payment offer, so the free models want the portal's key. Read 2026-09-16",
      "models": [
        {
          "family": "step-3.7-flash",
          "released": "",
          "aa_model": "step-3-7-flash"
        },
        {
          "family": "laguna-s-2.1",
          "released": ""
        }
      ],
      "api": {
        "base_url": "https://inference-api.nousresearch.com/v1",
        "key_url": "https://portal.nousresearch.com",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "stepfun/step-3.7-flash:free",
          "poolside/laguna-s-2.1:free",
          "poolside/laguna-xs-2.1:free",
          "inclusionai/ling-3.0-flash-fin:free",
          "inclusionai/ling-3.0-flash-sante:free",
          "upstage/solar-pro4:free",
          "meituan/longcat-2.0:free",
          "stealth/union-alpha"
        ],
        "note": "every id the keyless catalog prices at 0 on 2026-09-16; stealth/union-alpha is a stealth model without the :free suffix, and solar-pro4 is a limited-time trial on other gateways"
      },
      "probe": {
        "type": "api-models",
        "endpoint": "https://inference-api.nousresearch.com/v1/models",
        "keywords": [],
        "free_marker": ":free",
        "dead_markers": [],
        "require_zero_price": true,
        "machinery_keywords": []
      },
      "first_seen": "2026-09-16",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": true,
      "rank": 65,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/nous-portal/"
    },
    {
      "id": "amazon-q-developer",
      "name": "Amazon Q Developer",
      "category": "agent-cli",
      "url": "https://aws.amazon.com/q/developer/",
      "source_urls": [
        "https://aws.amazon.com/q/developer/pricing/",
        "https://aws.amazon.com/q/developer/"
      ],
      "card_required": false,
      "offering": "AWS's coding assistant in the IDE and the CLI; its perpetual Free Tier gives a Builder ID user 50 agentic requests a month",
      "limits": "\"Amazon Q Developer offers a perpetual Free Tier with monthly limits available to users logged in as an AWS Identity and Access Management (IAM) user or AWS Builder ID user\", and \"Free Tier limits in the IDE are available only to Builder ID users\". The Free column reads \"50 agentic requests per month\" for Q&A chat and agentic coding in the IDE plugins and CLI, plus 1,000 lines of code a month of Java upgrade transformation; the plan summary says \"Access latest Claude models\" without naming them. Pro is $19 a month per user. The end is scheduled: \"On April 30, 2027, AWS will discontinue support for Amazon Q Developer IDE plugins\", pointing to Kiro, which this list carries separately. Read 2026-09-16",
      "models": [],
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://aws.amazon.com/q/developer/pricing/",
        "keywords": [
          "50 agentic requests per month",
          "perpetual Free Tier with monthly limits"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-09-16",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": true,
      "rank": 45,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/amazon-q-developer/"
    },
    {
      "id": "llm7",
      "name": "LLM7.io",
      "category": "api-free-tier",
      "url": "https://llm7.io",
      "source_urls": [
        "https://docs.llm7.io/limits.md",
        "https://docs.llm7.io/guides/models.md",
        "https://docs.llm7.io/quickstart.md",
        "https://github.com/chigwell/llm7.io/blob/main/TERMS.md"
      ],
      "card_required": false,
      "offering": "OpenAI-compatible API with an anonymous tier — no account, no key — of 500,000 tokens a day on its turbo models, GLM 5.3 Flash, MiniMax M2.7 and Codestral among them; a free token doubles it",
      "limits": "The limits page gives anonymous callers 1 request a second, 10 a minute and 60 an hour, and \"500,000 tokens per 24 hours\"; a free token from dash.llm7.io raises that to 40 a minute, 100 an hour and \"1,000,000 tokens per 24 hours\", and Pro is $12 a month. The free models are a tier of the catalog — \"`turbo` models are fast models available to anonymous and free-token users\" — though two turbo rows marked usage_based_only, DeepSeek V4 Flash and Gemini 3.1 Flash Lite, answered a keyless call with 401 `Missing API key.` The operator publishes terms, last updated 9 August 2026, and names no upstream for any model. Read 2026-09-16",
      "models": [],
      "api": {
        "base_url": "https://api.llm7.io/v1",
        "key_url": "https://dash.llm7.io",
        "auth": "none",
        "openai_compatible": true,
        "model_ids": [
          "GLM-5.3-Flash",
          "minimax-m2.7",
          "codestral-latest",
          "mistral-Nemo-Instruct-2407"
        ],
        "note": "no key for the anonymous tier — OpenAI SDKs want some api_key, and the quickstart passes `unused`. The ids listed are the turbo rows that answered a keyless call on 2026-09-16; DeepSeek-V4-Flash-0731 and gemini-3.1-flash-lite need a token"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://docs.llm7.io/limits.md",
        "keywords": [
          "500,000 tokens per 24 hours",
          "1,000,000 tokens per 24 hours"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "catalog": "https://api.llm7.io/v1/models",
        "machinery_keywords": []
      },
      "first_seen": "2026-09-16",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": true,
      "rank": 45,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/llm7/"
    },
    {
      "id": "fireworks-ai",
      "name": "Fireworks AI",
      "category": "trial",
      "url": "https://fireworks.ai",
      "source_urls": [
        "https://fireworks.ai/pricing",
        "https://docs.fireworks.ai/faq-new/billing-pricing/what-happens-when-i-finish-my-1-dollar-credit",
        "https://docs.fireworks.ai/guides/quotas_usage/account-quotas",
        "https://docs.fireworks.ai/serverless/pricing",
        "https://docs.fireworks.ai/getting-started/quickstart"
      ],
      "card_required": false,
      "offering": "Serverless inference on open-weight models — Kimi K3, GLM 5.3, DeepSeek V4.1 Flash among them — with a one-time $1 of credit that is spent without a card, at 10 requests a minute until a payment method is added",
      "limits": "The pricing page offers \"Get started with $1 in free credits\", and the billing FAQ says what happens to an account \"Without payment method\" when the dollar runs out: \"Your account will be suspended until you add a payment method\". Until then the account quotas put \"No payment method or no credits\" at 10 RPM, against 6,000 RPM with a payment method and credits. No page gives the dollar an expiry or makes it recur, and beyond it Fireworks \"operates on a pre-paid credits billing system\". The dollar buys list prices, per 1M input and output tokens: DeepSeek V4.1 Flash $0.22 and $0.66, GLM 5.3 Flash $0.15 and $0.50, MiniMax M3 $0.30 and $1.20, Kimi K3 $3.00 and $15.00 — about 4.5M input tokens on DeepSeek V4.1 Flash, about 330K on Kimi K3. Read 2026-09-17",
      "models": [],
      "api": {
        "base_url": "https://api.fireworks.ai/inference/v1",
        "key_url": "https://app.fireworks.ai/settings/users/api-keys",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "accounts/fireworks/models/deepseek-v4p1-flash",
          "accounts/fireworks/models/glm-5p3-flash",
          "accounts/fireworks/models/minimax-m3",
          "accounts/fireworks/models/glm-5p3",
          "accounts/fireworks/models/kimi-k3"
        ],
        "anthropic_base_url": "https://api.fireworks.ai/inference",
        "note": "ids are accounts/fireworks/models/ plus the slug the serverless pricing page links, read 2026-09-17; /inference/v1/models answers 401 without a key, so none is read off a catalog. The quickstart gives the Anthropic SDK base_url https://api.fireworks.ai/inference, which is Claude Code's ANTHROPIC_BASE_URL, the client appending /v1/messages"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://fireworks.ai/pricing",
        "keywords": [
          "Get started with $1 in free credits"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-09-17",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": true,
      "rank": 92,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/fireworks-ai/"
    },
    {
      "id": "vlm-run-gateway",
      "name": "VLM Run Gateway",
      "category": "api-free-tier",
      "url": "https://vlm.run",
      "source_urls": [
        "https://docs.vlm.run/gateway/authentication",
        "https://docs.vlm.run/gateway/rate-limits.md",
        "https://docs.vlm.run/gateway/faq.md",
        "https://docs.vlm.run/gateway/models",
        "https://docs.vlm.run/gateway/introduction"
      ],
      "card_required": false,
      "offering": "OpenAI-compatible gateway for vision and language models whose models on VLM Run's own GPUs, Qwen3.8 27B among them, answer anonymous callers — no signup, no key — at 100 requests a day per IP, in alpha",
      "limits": "The authentication page says it plainly: \"The VLM Run Gateway serves anonymous callers on a small free quota, keyed by client IP\", and \"Every GPU-served model is public and reachable anonymously\", while \"The routed models carry the paid access tier\". The rate-limit table gives the anonymous tier \"10/min, 30/hr, 100/day\" per client IP, the three windows stacking, against 240 a minute with a key. The FAQ calls the gateway alpha, with a model catalog kept intentionally small: its chat models on VLM Run GPUs are Qwen3.8 27B and Qwen3.5 0.8B, beside OCR, embedding and speech models. The published request schema has no tools field, yet a keyless call carrying one tool was answered with a tool call on 2026-09-17. The operator is Autonomi AI Inc.; its terms render only in a browser. Read 2026-09-17",
      "models": [
        {
          "family": "qwen3.8-27b",
          "tier": "strong",
          "released": "",
          "aa_model": "qwen3-8-27b"
        }
      ],
      "api": {
        "base_url": "https://gateway.vlm.run/v1/openai",
        "key_url": "https://app.vlm.run",
        "auth": "none",
        "openai_compatible": true,
        "model_ids": [
          "qwen/qwen3.8-27b"
        ],
        "note": "no key: a call with no Authorization header is anonymous, and `Bearer vlmrun` is the explicit anonymous form for a client that needs a non-empty key; 10 a minute, 30 an hour and 100 a day per IP. qwen/qwen3.5-0.8b is the other chat model on VLM Run's GPUs, and the routed ids in the same catalog, Kimi K3 among them, answer `403 model_not_entitled` without a paid organization"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://docs.vlm.run/gateway/models",
        "keywords": [
          "qwen/qwen3.8-27b"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "catalog": "https://gateway.vlm.run/v1/openai/models",
        "machinery_keywords": []
      },
      "first_seen": "2026-09-17",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": true,
      "rank": 79,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/vlm-run-gateway/"
    },
    {
      "id": "tencent-tokenhub",
      "name": "Tencent Cloud TokenHub",
      "category": "api-free-tier",
      "url": "https://cloud.tencent.com/document/product/1823",
      "source_urls": [
        "https://cloud.tencent.com/document/product/1823/130053",
        "https://cloud.tencent.com/document/product/1823/130058",
        "https://cloud.tencent.com/document/product/378/3629",
        "https://cloud.tencent.com/document/product/1823/130051",
        "https://cloud.tencent.com/document/product/1823/131903"
      ],
      "card_required": false,
      "offering": "Tencent Cloud's model platform — Hy3, Kimi K3, GLM-5.3 and MiniMax-M3 among its models — with a one-time grant of a million tokens on its language models, valid a year and no card, on an account that has passed Tencent Cloud real-name verification",
      "limits": "The free package page, updated 2026-09-04, gives each main account one grant while the promotion runs, 本期活动时间截至 2026 年 12 月 31 日 (until 31 December 2026): 所有语言模型均提供 100 万 Tokens 的免费体验额度，有效期 1 年, a million tokens on every language model, valid a year from claiming. The same page says the grant works at main-account level with 同一账号下的所有模型共享额度 (all models on the account sharing it) beside 免费体验包每个账号每个模型仅可领取一次 (once per model per account), so whether the million is per model or shared is not settled there, and the figures are 以控制台显示为准 (as the console shows). When the grant is spent the service stops unless post-payment is switched on, so nothing is billed without it. The quickstart requires registering on Tencent Cloud and passing 实名认证, real-name verification, and personal verification is for 中国大陆、中国香港、中国澳门、中国台湾居民 — residents of mainland China, Hong Kong, Macau and Taiwan; other identity documents are sent to the international site. Read 2026-09-17",
      "models": [],
      "api": {
        "base_url": "https://tokenhub.tencentmaas.com/v1",
        "key_url": "https://console.cloud.tencent.com/tokenhub/apikey",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "kimi-k3",
          "glm-5.3",
          "hy3",
          "minimax-m3"
        ],
        "anthropic_base_url": "https://tokenhub.tencentmaas.com",
        "note": "ids are the models page's model column (调用参数), read 2026-09-17; /v1/models answers 401 without a key, so none is read off a catalog. The Claude Code guide sets ANTHROPIC_BASE_URL=https://tokenhub.tencentmaas.com with ANTHROPIC_MODEL=hy3"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://cloud.tencent.com/document/product/1823/130053",
        "keywords": [
          "100 万 Tokens 的免费体验额度",
          "2026 年 12 月 31 日"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-09-17",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": true,
      "rank": 89,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/tencent-tokenhub/"
    },
    {
      "id": "bytez",
      "name": "Bytez",
      "category": "api-free-tier",
      "url": "https://bytez.com",
      "source_urls": [
        "https://docs.bytez.com/model-api/docs/billing.md",
        "https://docs.bytez.com/model-api/docs/billing",
        "https://docs.bytez.com/model-api/docs/get-started.md"
      ],
      "card_required": false,
      "offering": "Serverless API over open models, whose Free plan grants $1 of credit every four weeks for open models of up to 7B parameters, one request at a time, with no billing",
      "limits": "The billing page's Free card reads \"$0 / month - Get $1 in free credits\", \"Run open models up to 7B parameters\", \"1 concurrent request (open models)\" and \"Credits refresh every 4 weeks\", and the billing cycle adds that \"Credits expire 4 weeks after grant\", with no billing on the plan. The card also lists \"Access all closed model providers\", but the get-started guide says a closed-source model needs \"an account with the model provider\" and is \"billed directly by the provider\", so the free dollar reaches only the open models of 7B parameters or fewer — Qwen3 4B, the docs' own example, is one. An open model above 7B needs at least $10 of credit bought in the last four weeks, on the $3 a month plan. Read 2026-09-17",
      "models": [],
      "api": {
        "base_url": "https://api.bytez.com/models/v2/openai/v1",
        "key_url": "https://bytez.com/api",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "Qwen/Qwen3-4B"
        ],
        "note": "model ids are Hugging Face ids, Qwen/Qwen3-4B being the docs' example; the OpenAI SDK examples pass the key as the api key and the docs' curl sends it bare in Authorization. /v1/models answers 401 without a key, and closed-source models need a provider key of your own"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://docs.bytez.com/model-api/docs/billing.md",
        "keywords": [
          "$0 / month - Get $1 in free credits",
          "Run open models up to 7B parameters"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-09-17",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": true,
      "rank": 99,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/bytez/"
    },
    {
      "id": "arli-ai",
      "name": "Arli AI",
      "category": "api-free-tier",
      "url": "https://www.arliai.com",
      "source_urls": [
        "https://www.arliai.com/pricing",
        "https://www.arliai.com/docs/textgen",
        "https://www.arliai.com/quick-start",
        "https://api.arliai.com/model/all"
      ],
      "card_required": false,
      "offering": "OpenAI-compatible inference on open models and their fine-tunes, whose Free plan tries each model five times every two days at 12K tokens of context, one request at a time",
      "limits": "The pricing page's Free plan, \"Test out the Arli platform\" at $0, lists \"Delayed Response\", \"Max 12K context tokens\", \"1 request at a time\" and \"5 times / 2 days trial of all models\", and the text generation docs say the allowance recurs: \"Free accounts are able to use each model for a maximum of 5 requests every 2 days for testing purposes\". The keyless catalog at api.arliai.com/model/all listed 92 models on 2026-09-17 — DeepSeek-V4-Flash-0731, MiMo-V2.5, GLM-4.7 and Gemma-4-31B-it among them, most of the rest Qwen3.5 27B and Gemma 4 31B fine-tunes recommended for writing and roleplay. Past the trial the Personal Starter plan is $10 a month. Read 2026-09-17",
      "models": [],
      "api": {
        "base_url": "https://api.arliai.com/v1",
        "key_url": "https://www.arliai.com/account",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [],
        "note": "the quick-start calls it a drop-in OpenAI-API compatible endpoint and uses a placeholder model id; the catalog's names are the models page's, and the coding quick-start connects Roo Code and Kilo Code with a context window set to the model picked. /v1/chat/completions answers 401 without a key"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://www.arliai.com/pricing",
        "keywords": [
          "5 times / 2 days trial of all models",
          "Max 12K context tokens"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-09-17",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": true,
      "rank": 99,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/arli-ai/"
    },
    {
      "id": "opper",
      "name": "Opper",
      "category": "aggregator",
      "url": "https://opper.ai",
      "source_urls": [
        "https://opper.ai/pricing.md",
        "https://opper.ai/llms.txt",
        "https://docs.opper.ai/guides/claude-code-router.md"
      ],
      "card_required": false,
      "offering": "EU-hosted gateway over 700+ models whose free models — Gemma 4 31B and Gemma 4 26B on Google's route, Laguna S 2.1 and XS 2.1 through Poolside — answer an account with no card on file; every other model needs a card and credits",
      "limits": "The pricing FAQ: \"Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.\" The llms.txt names one of them — \"gemini/gemma-4-31b is a free model, so this call works before you add a card. It runs on a US-hosted route.\" — and the model directory at opper.ai/models flags five rows free: gemini/gemma-4-31b, gemini/gemma-4-26b-moe, poolside/laguna-s-2.1, poolside/laguna-xs-2.1 and Talkie 1930, a 13B model trained on pre-1931 text. The keyless catalog publishes no price for them, and no page gives the free models a quota or a rate limit. Paid usage is billed at provider rates with \"a 3% fee on credit purchases\". The operator is Opper Technology AB, in Sweden, on AWS Stockholm. Read 2026-09-17",
      "models": [
        {
          "family": "gemma-4-31b",
          "released": "",
          "aa_model": "gemma-4-31b"
        }
      ],
      "api": {
        "base_url": "https://api.opper.ai/v3/compat",
        "key_url": "https://platform.opper.ai/settings/api-keys",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "gemini/gemma-4-31b",
          "gemini/gemma-4-26b-moe",
          "poolside/laguna-s-2.1",
          "poolside/laguna-xs-2.1"
        ],
        "anthropic_base_url": "https://api.opper.ai/v3/compat",
        "note": "ids are four of the five rows the model directory flags free on 2026-09-17, checked against the keyless catalog at api.opper.ai/v3/models; opper/talkie-1930, an 8K-context period piece, is left out. The Claude Code guide sets ANTHROPIC_BASE_URL=https://api.opper.ai/v3/compat, the client appending /v1/messages"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://opper.ai/llms.txt",
        "keywords": [
          "gemini/gemma-4-31b is a free model",
          "the free models work in the playground and the API"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "catalog": "https://api.opper.ai/v3/models?limit=0",
        "machinery_keywords": []
      },
      "first_seen": "2026-09-17",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": true,
      "rank": 82,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/opper/"
    },
    {
      "id": "moark",
      "name": "Moark (Gitee AI)",
      "category": "aggregator",
      "url": "https://moark.com",
      "source_urls": [
        "https://moark.com/docs/FAQ",
        "https://moark.com/docs/getting-started",
        "https://moark.com/docs/integrations/Development-Tools/claude_code"
      ],
      "card_required": false,
      "offering": "Gitee's model platform, formerly Gitee AI — 200+ open models behind OpenAI- and Anthropic-compatible APIs — whose free experience token gives every user 100 calls a day across its featured models, with nothing bought",
      "limits": "The FAQ: 选择“免费体验访问令牌”即可享受免费体验，每位用户每日拥有 100 次免费调用次数 — take the free experience token and every user has 100 free calls a day — and a token past that answers `400` `已达到最大当日免费 API 使用次数，请购买资源后继续使用 API`. The Claude Code guide offers the same token to developers who have bought nothing, 仅供体验，每日调用次数有限 (for trying out, daily calls limited), and configures deepseek-v4-flash-0731. Which models the token reaches, 所有精选模型 (all featured models), is listed only on the client-rendered model square; the models marked 免费 there are another matter, needing a purchased resource package of any amount. Sign-in is with a Gitee account, and no page read says whether one can be opened with a phone number from outside mainland China. Read 2026-09-17",
      "models": [],
      "api": {
        "base_url": "https://api.moark.com/v1",
        "key_url": "https://moark.com/dashboard/tokens",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "deepseek-v4-flash-0731"
        ],
        "anthropic_base_url": "https://moark.com/anthropic",
        "note": "the FAQ gives the OpenAI base as https://api.moark.com/v1 and the Anthropic one as https://moark.com/anthropic, which the Claude Code guide sets as ANTHROPIC_BASE_URL with deepseek-v4-flash-0731 in every model slot; the id is checked against the keyless catalog at api.moark.com/v1/models"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://moark.com/docs/FAQ",
        "keywords": [
          "每位用户每日拥有 100 次免费调用次数"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "catalog": "https://api.moark.com/v1/models",
        "machinery_keywords": []
      },
      "first_seen": "2026-09-17",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": true,
      "rank": 88,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/moark/"
    },
    {
      "id": "mixlayer",
      "name": "Mixlayer",
      "category": "api-free-tier",
      "url": "https://www.mixlayer.com",
      "source_urls": [
        "https://www.mixlayer.com/pricing",
        "https://docs.mixlayer.com/credits-and-limits.md",
        "https://docs.mixlayer.com/introduction.md"
      ],
      "card_required": false,
      "offering": "Serverless open models priced per token, with one of them at $0 — Qwen3.5 4B as qwen/qwen3.5-4b-free, at 131K context — callable without prepaid credit",
      "limits": "The pricing page says \"Free models stay free; pay-as-you-go for everything else.\" and prices its one free row, qwen/qwen3.5-4b-free, at $0.00 in and out, 131K context, vision and text. The billing docs: \"Free models do not require prepaid credit.\" — a paid model on an empty prepaid balance answers `402`. Rate limits are set per organization and per model, and \"Mixlayer does not publish fixed limit values because limits can differ by organization and model\". The docs' introduction sends its first request to the free model. The operator is Mixlayer Labs Inc. Read 2026-09-17",
      "models": [
        {
          "family": "qwen3.5-4b",
          "released": "",
          "aa_model": "qwen3-5-4b"
        }
      ],
      "api": {
        "base_url": "https://models.mixlayer.ai/v1",
        "key_url": "https://console.mixlayer.com/app/api-keys",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "qwen/qwen3.5-4b-free"
        ],
        "note": "the id is the pricing page's and the docs' own example; /v1/models answers 401 without a key, so it is not read off a catalog"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://www.mixlayer.com/pricing",
        "keywords": [
          "qwen/qwen3.5-4b-free",
          "Free models stay free"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-09-17",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": true,
      "rank": 99,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/mixlayer/"
    },
    {
      "id": "blue-claw",
      "name": "Blue Claw Network",
      "category": "trial",
      "url": "https://blueclaw.network",
      "source_urls": [
        "https://blueclaw.network/",
        "https://blueclaw.network/quickstart",
        "https://blueclaw.network/how-it-works",
        "https://blueclaw.network/operators"
      ],
      "card_required": false,
      "offering": "OpenAI-compatible endpoint that routes calls to a network of independent GPU operators running open models; every new account starts with a $5 welcome credit, and no card is asked to start",
      "limits": "The home page: \"Every new account starts with a $5 welcome credit. After that, you run on prepaid USD credits — buy what you use, no subscriptions.\" and \"No credit card required to start.\" Sign-in is a six-digit code sent by email. No public page names the models or their prices — \"Live per-model pricing is on the Models page in the console\" — and the quick start calls the model auto. Calls go to \"a network of independent GPU operators\", partners running Livepeer orchestrators among them; Blue Claw \"does not log prompts, inputs, or outputs by default\" and offers \"No TEE, E2EE, or confidential-compute guarantee yet\". No page gives the credit an expiry. Read 2026-09-17",
      "models": [],
      "api": {
        "base_url": "https://openai.blueclaw.network/v1",
        "key_url": "https://portal.blueclaw.network/",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "auto"
        ],
        "note": "auto is the quick start's model and keys start with bc_; /v1/models answers 401 without a key, and the models behind auto are listed only in the console"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://blueclaw.network/",
        "keywords": [
          "Every new account starts with a $5 welcome credit",
          "No credit card required to start"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-09-17",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": true,
      "rank": 91,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/blue-claw/"
    },
    {
      "id": "abliteration-ai",
      "name": "abliteration.ai",
      "category": "trial",
      "url": "https://abliteration.ai",
      "source_urls": [
        "https://abliteration.ai/pricing",
        "https://docs.abliteration.ai/models.md",
        "https://docs.abliteration.ai/pricing.md",
        "https://docs.abliteration.ai/api-reference/credits/get-the-credit-balance-for-the-api-keys-organization.md",
        "https://docs.abliteration.ai/integrations/claude-code.md"
      ],
      "card_required": false,
      "offering": "OpenAI- and Anthropic-compatible API for three uncensored reasoning models, the large one derived from GLM-5.3, that opens with a one-credit free preview and no card",
      "limits": "The pricing FAQ: \"You can start with a one-credit free preview and no credit card. Sign in to use the Playground or API, inspect the available models, and add prepaid credit or a monthly plan when you are ready.\" No page says what a credit is worth; the credits endpoint reports the balance as \"Total credits available to the organization, in USD\". Usage is billed per token — abliterated-model $1.00 in and $3.00 out per million, abliterated-model-large-v2 and abliterated-model-large $3.00 and $5.00 — and plans start at $20 a month. The models \"think before answering by default\", stream and call tools, and abliterated-model-large-v2 is \"Derived from the open-weight GLM-5.3 model, further abliterated and fine-tuned by Abliteration AI\". The operator is Abliteration AI, Inc. Read 2026-09-17",
      "models": [],
      "api": {
        "base_url": "https://api.abliteration.ai/v1",
        "key_url": "https://abliteration.ai/console",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "abliterated-model-large-v2",
          "abliterated-model"
        ],
        "anthropic_base_url": "https://api.abliteration.ai",
        "note": "ids are the docs' models page, read 2026-09-17; /v1/models answers 401 without a key. The Claude Code guide sets ANTHROPIC_BASE_URL=https://api.abliteration.ai with an ak_ key as ANTHROPIC_AUTH_TOKEN, the client appending /v1/messages"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://abliteration.ai/pricing",
        "keywords": [
          "You can start with a one-credit free preview and no credit card"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-09-17",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": true,
      "rank": 94,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/abliteration-ai/"
    },
    {
      "id": "impossibl",
      "name": "Impossibl",
      "category": "trial",
      "url": "https://impossibl.com",
      "source_urls": [
        "https://impossibl.com/llms.txt",
        "https://api.impossibl.com/auth.md",
        "https://impossibl.com/docs/billing",
        "https://impossibl.com/docs/integrations"
      ],
      "card_required": false,
      "offering": "Prepaid gateway at provider list prices over 128 models, Claude, GPT, Gemini, DeepSeek and GLM among them, whose keyless sign-up funds an account with $0.05 and adds $1 once a person claims it by email — no card",
      "limits": "An account is one POST with no key, and the llms.txt says what it carries: \"an agent-created account has $0.05; claiming adds an extra $1\" — the claim is an email sign-in, the dollar \"granted once per human\". The billing page narrows it: \"Some models require a completed credit purchase and return 403 billing_required without one. Saving a card or having promotional credits does not satisfy that requirement.\" Which models those are is not published. What the credit buys is list price — \"Provider usage is billed at provider list prices with no usage markup\" — GLM-5.3-Flash at $0.15 in and $0.50 out per million tokens, Claude Opus 5 at $5 and $25 — and a top-up starts at $5 plus a 5% platform fee. Read 2026-09-17",
      "models": [],
      "api": {
        "base_url": "https://api.impossibl.com/v1",
        "key_url": "https://impossibl.com/dashboard",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "zai/glm-5.3-flash",
          "deepseek/deepseek-v4.1-flash",
          "qwen/qwen3.8-27b"
        ],
        "anthropic_base_url": "https://api.impossibl.com",
        "note": "ids are the keyless catalog's at api.impossibl.com/v1/models, 2026-09-17; which of them the promotional credit can call is not published. The Claude Code guide sets ANTHROPIC_BASE_URL=https://api.impossibl.com and clears ANTHROPIC_API_KEY so the bearer token is used"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://impossibl.com/llms.txt",
        "keywords": [
          "claiming adds an extra $1",
          "a $0.05 signup bonus"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "catalog": "https://api.impossibl.com/v1/models",
        "machinery_keywords": []
      },
      "first_seen": "2026-09-17",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": true,
      "rank": 94,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/impossibl/"
    },
    {
      "id": "the-grid",
      "name": "The Grid",
      "category": "trial",
      "url": "https://thegrid.ai",
      "source_urls": [
        "https://thegrid.ai/docs/start-here/quickstart.md",
        "https://thegrid.ai/llms.txt",
        "https://thegrid.ai/docs/api-reference/errors-and-rate-limits.md",
        "https://thegrid.ai/docs/instrument-specifications/current-instruments.md",
        "https://thegrid.ai/docs/integrations-and-best-practices/integrations/claude-code.md"
      ],
      "card_required": false,
      "offering": "OpenAI- and Anthropic-compatible inference market that sells quality tiers rather than model names — Agent Max was served by Claude Opus 5 in the 30 days to 2026-09-03 — with a $25 signup credit, for a limited time",
      "limits": "The quick start: \"New accounts get a $25 signup credit (limited time), enough for millions of test calls on\" text-prime, and its three steps from sign-up to a first call ask for no payment method — adding one is listed under what to do next. Concurrency counts deposits only, \"a signup bonus of $25 and a deposit of $20 only counts as $20\", and an account with $0 to $20 deposited gets 3 concurrent requests. A model name buys a specification: \"The specific model behind any given call can change between calls.\" The keyless catalog publishes what each tier delivered over 30 days to 2026-09-03 — Agent Max Claude Opus 5, Agent Prime MiniMax-M3, Agent Standard gpt-oss-120b — at market prices per million tokens. Read 2026-09-17",
      "models": [],
      "api": {
        "base_url": "https://api.thegrid.ai/v1",
        "key_url": "https://app.thegrid.ai/profile",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "agent-prime",
          "code-prime",
          "agent-max"
        ],
        "anthropic_base_url": "https://messages-beta.api.thegrid.ai",
        "note": "the ids are instruments from the keyless catalog at api.thegrid.ai/v1/models, where each carries the models it delivered; the Claude Code guide sets ANTHROPIC_BASE_URL=https://messages-beta.api.thegrid.ai, the Messages API in beta"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://thegrid.ai/docs/start-here/quickstart.md",
        "keywords": [
          "New accounts get a $25 signup credit"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "catalog": "https://api.thegrid.ai/v1/models",
        "machinery_keywords": []
      },
      "first_seen": "2026-09-17",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": true,
      "rank": 86,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/the-grid/"
    },
    {
      "id": "hpc-ai",
      "name": "HPC-AI Model APIs",
      "category": "trial",
      "url": "https://www.hpc-ai.com/model-apis",
      "source_urls": [
        "https://www.hpc-ai.com/model-apis",
        "https://www.hpc-ai.com/doc/docs/Model-APIs/User-Guides/Rate-Limit/",
        "https://www.hpc-ai.com/doc/docs/Model-APIs/User-Guides/QuickStart/",
        "https://www.hpc-ai.com/api/maas/v1/models"
      ],
      "card_required": false,
      "offering": "OpenAI-compatible APIs over 24 models, GLM 5.3 Flash, Kimi K3 and MiniMax M3 among them, with $2 of free credit for every user — $4 with the vendor's invite code — at 5 requests a minute until a first deposit",
      "limits": "The Model APIs page answers its FAQ \"Do you offer a free trial for users?\" in the page's data rather than its text: every user receives $2 \"in free credits. New accounts using the invite code\" HPCAI-MAPI get $4, and \"Supplies are limited\". The console's welcome message, shipped in the same page, reads \"Free credits have been added to your account — start calling open-source models right away.\" and \"Make your first deposit to unlock higher RPM limits.\" The keyless model list gives the L0 tier, an account before its first deposit, 5 requests and 2M tokens a minute on 23 of its 24 models (DeepSeek V4 Pro gets 0), and the rate-limit docs say the move to L1 \"is triggered by your first deposit rather than by spending\". The credit buys list prices, GLM 5.3 Flash at $0.15 in and $0.50 out per million tokens and Kimi K3 at $3 and $15. No page read asks for a card before the credit is spent, and none gives it an expiry. Read 2026-09-17",
      "models": [],
      "api": {
        "base_url": "https://api.hpc-ai.com/inference/v1",
        "key_url": "https://www.hpc-ai.com/models-console/api-key",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "zai-org/glm-5.3-flash",
          "moonshotai/kimi-k2.7-code",
          "minimax/minimax-m3"
        ],
        "note": "ids are the keyless model list's at www.hpc-ai.com/api/maas/v1/models, 2026-09-17, the quick start's own example being moonshotai/kimi-k2.7-code"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://www.hpc-ai.com/model-apis",
        "keywords": [
          "Do you offer a free trial for users?"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "catalog": "https://www.hpc-ai.com/api/maas/v1/models",
        "machinery_keywords": [
          "in free credits. New accounts using the invite code"
        ]
      },
      "first_seen": "2026-09-17",
      "last_verified": "2026-09-17",
      "probe_failures": 0,
      "provisional": true,
      "rank": 90,
      "archived": false,
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/hpc-ai/"
    },
    {
      "id": "mimocode",
      "name": "MiMoCode",
      "category": "agent-cli",
      "url": "https://mimocode.ai",
      "source_urls": [
        "https://mimocode.ai"
      ],
      "card_required": false,
      "offering": "Coding agent with free tier",
      "limits": "TBD by scout",
      "models": [],
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://mimocode.ai",
        "keywords": [
          "free"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-19",
      "last_verified": "2026-07-19",
      "delisted": {
        "on": "2026-07-19",
        "reason": "a placeholder from the list's first day — \"Coding agent with free tier\", limits \"TBD by scout\" — with no page behind the claim, taken off the same day as unverifiable"
      },
      "probe_failures": 0,
      "provisional": true,
      "rank": 100,
      "archived": true,
      "archived_because": "delisted on 2026-07-19: a placeholder from the list's first day — \"Coding agent with free tier\", limits \"TBD by scout\" — with no page behind the claim, taken off the same day as unverifiable",
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/mimocode/"
    },
    {
      "id": "aider",
      "name": "Aider",
      "category": "agent-cli",
      "url": "https://aider.chat/",
      "source_urls": [
        "https://aider.chat/",
        "https://aider.chat/docs/faq.html"
      ],
      "card_required": false,
      "offering": "Free, open-source terminal coding agent with tight git integration; BYOK — works with free-tier provider keys or local models via Ollama",
      "limits": "Tool is free and open-source; model usage is BYOK (no bundled free-model quota)",
      "models": [],
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://aider.chat/",
        "keywords": [
          "open source",
          "free"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-19",
      "last_verified": "2026-07-19",
      "delisted": {
        "on": "2026-07-19",
        "reason": "BYOK only — the tool is free and open source but bundles no model access of its own, and its docs send readers to other vendors' free tiers, which this list carries directly"
      },
      "probe_failures": 0,
      "provisional": false,
      "rank": 100,
      "archived": true,
      "archived_because": "delisted on 2026-07-19: BYOK only — the tool is free and open source but bundles no model access of its own, and its docs send readers to other vendors' free tiers, which this list carries directly",
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/aider/"
    },
    {
      "id": "puter-free",
      "name": "Puter.js (free LLM API)",
      "category": "api-free-tier",
      "url": "https://developer.puter.com/tutorials/free-llm-api/",
      "source_urls": [
        "https://developer.puter.com/tutorials/free-llm-api/"
      ],
      "card_required": false,
      "offering": "Browser SDK exposing hundreds of models (GPT, Claude, Gemini, Grok) at no developer cost via Puter's User-Pays model",
      "limits": "No API key or developer cost; usage billed to each end user's Puter account; per-model rate limits",
      "models": [],
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://developer.puter.com/tutorials/free-llm-api/",
        "keywords": [
          "free"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-19",
      "last_verified": "2026-07-19",
      "delisted": {
        "on": "2026-07-19",
        "reason": "a browser SDK billed to each end user's Puter account, with no HTTP endpoint a coding agent could call; the OpenAI-compatible endpoint read on 2026-09-14 needs a paid plan"
      },
      "probe_failures": 0,
      "provisional": true,
      "rank": 100,
      "archived": true,
      "archived_because": "delisted on 2026-07-19: a browser SDK billed to each end user's Puter account, with no HTTP endpoint a coding agent could call; the OpenAI-compatible endpoint read on 2026-09-14 needs a paid plan",
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/puter-free/"
    },
    {
      "id": "easy-gonka-api",
      "name": "Easy GonkaAI API",
      "category": "trial",
      "url": "https://gonka-api.org/",
      "source_urls": [
        "https://gonka-api.org/"
      ],
      "card_required": false,
      "offering": "Third-party OpenAI-compatible broker to the permissionless Gonka decentralized inference network (Qwen, Kimi and other open models)",
      "limits": "10M free tokens on signup (one-time trial, no card); paid usage billed in crypto",
      "models": [
        {
          "family": "minimax-m2",
          "released": ""
        },
        {
          "family": "kimi-k2",
          "released": ""
        }
      ],
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://gonka-api.org/",
        "keywords": [
          "free tokens"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-19",
      "last_verified": "2026-07-19",
      "delisted": {
        "on": "2026-07-19",
        "reason": "rejected for cause — its /for-agents page carried a prompt injection aimed at AI agents (auto-signup, credential exfiltration, referral spam)"
      },
      "probe_failures": 0,
      "provisional": true,
      "rank": 90,
      "archived": true,
      "archived_because": "delisted on 2026-07-19: rejected for cause — its /for-agents page carried a prompt injection aimed at AI agents (auto-signup, credential exfiltration, referral spam)",
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/easy-gonka-api/"
    },
    {
      "id": "deepseek",
      "name": "DeepSeek Platform",
      "category": "trial",
      "url": "https://platform.deepseek.com",
      "source_urls": [
        "https://api-docs.deepseek.com/quick_start/pricing/",
        "https://pricepertoken.com/endpoints/deepseek/free"
      ],
      "card_required": false,
      "offering": "Official DeepSeek API; every new account gets a one-time free token grant, no card required",
      "limits": "5M free tokens on signup (~30-day validity), then pay-as-you-go; no perpetually free models",
      "models": [
        {
          "family": "deepseek-chat",
          "released": ""
        },
        {
          "family": "deepseek-reasoner",
          "released": ""
        }
      ],
      "api": {
        "base_url": "https://api.deepseek.com",
        "key_url": "https://platform.deepseek.com/api_keys",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "deepseek-chat",
          "deepseek-reasoner"
        ],
        "note": ""
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://api-docs.deepseek.com/quick_start/pricing/",
        "keywords": [
          "deepseek-chat"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-22",
      "last_verified": "2026-07-23",
      "delisted": {
        "on": "2026-07-27",
        "reason": "the 5M-token signup grant was only ever reported by third parties, and DeepSeek's own pricing page prices every model and names no free grant"
      },
      "probe_failures": 0,
      "provisional": true,
      "rank": 15,
      "archived": true,
      "archived_because": "delisted on 2026-07-27: the 5M-token signup grant was only ever reported by third parties, and DeepSeek's own pricing page prices every model and names no free grant",
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/deepseek/"
    },
    {
      "id": "reka",
      "name": "Reka AI",
      "category": "api-free-tier",
      "url": "https://platform.reka.ai",
      "source_urls": [
        "https://reka.ai/news/end-of-summer-updates",
        "https://docs.reka.ai/pricing"
      ],
      "card_required": false,
      "offering": "Reka multimodal API (chat, research, vision) with free credits refreshed automatically every month",
      "limits": "$10 free credits at the start of every month, usable on any API feature",
      "models": [
        {
          "family": "reka-core",
          "released": ""
        },
        {
          "family": "reka-flash",
          "released": ""
        }
      ],
      "api": {
        "base_url": "https://api.reka.ai/v1",
        "key_url": "https://platform.reka.ai",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "reka-core",
          "reka-flash"
        ],
        "note": "OpenAI-style chat completions; research and vision endpoints go beyond the OpenAI schema"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://reka.ai/news/end-of-summer-updates",
        "keywords": [
          "free tier",
          "$10 in free credits"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-22",
      "last_verified": "2026-08-10",
      "delisted": {
        "on": "2026-08-11",
        "reason": "the $10 of free credits a month rested on one dated announcement post; no live Reka page corroborated a recurring grant, and the platform sells pay-as-you-go credits"
      },
      "probe_failures": 0,
      "provisional": false,
      "rank": 91,
      "archived": true,
      "archived_because": "delisted on 2026-08-11: the $10 of free credits a month rested on one dated announcement post; no live Reka page corroborated a recurring grant, and the platform sells pay-as-you-go credits",
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/reka/"
    },
    {
      "id": "novita",
      "name": "Novita AI",
      "category": "api-free-tier",
      "url": "https://novita.ai/",
      "source_urls": [
        "https://novita.ai/pricing"
      ],
      "card_required": false,
      "offering": "Inference cloud for 200+ open models; selected models priced Free plus a small signup trial credit",
      "limits": "Selected models priced Free on the pricing page (Ling-3.0-flash, Macaron V1 Venti); ~$0.5 trial credit valid 1 year",
      "models": [],
      "api": {
        "base_url": "https://api.novita.ai/openai",
        "key_url": "https://novita.ai/settings/key-management",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "deepseek/deepseek-v4-pro",
          "qwen/qwen3.7-max",
          "zai-org/glm-5.2"
        ],
        "note": ""
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://novita.ai/pricing",
        "keywords": [
          "ling-3.0-flash",
          "free"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-19",
      "last_verified": "2026-08-13",
      "delisted": {
        "on": "2026-08-14",
        "reason": "the free lane ended without an announcement — both models the row named free were billed, and not one of the 102 prices on novita.ai/pricing was zero"
      },
      "probe_failures": 0,
      "provisional": false,
      "rank": 96,
      "archived": true,
      "archived_because": "delisted on 2026-08-14: the free lane ended without an announcement — both models the row named free were billed, and not one of the 102 prices on novita.ai/pricing was zero",
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/novita/"
    },
    {
      "id": "longcat",
      "name": "LongCat API Platform",
      "category": "api-free-tier",
      "url": "https://longcat.chat/platform",
      "source_urls": [
        "https://longcat.chat/platform/docs/api-docs",
        "https://x.com/Meituan_LongCat/status/2019773072849637725"
      ],
      "card_required": false,
      "offering": "Meituan's LongCat platform — OpenAI- and Anthropic-compatible API with a recurring daily free token quota",
      "limits": "100K free tokens/day; a larger free tier for Flash-Lite (50M tokens/day) is announced and the model is uncapped during rollout",
      "models": [
        {
          "family": "longcat-2.0",
          "released": "2026-06"
        },
        {
          "family": "longcat-flash",
          "released": "2025-09"
        }
      ],
      "api": {
        "base_url": "https://api.longcat.chat/openai/v1",
        "key_url": "https://longcat.chat/platform",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "LongCat-2.0"
        ],
        "note": "Anthropic-compatible sibling at /anthropic/v1/messages; docs include a Claude Code setup guide (cc-switch)"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://longcat.chat/platform/docs/api-docs",
        "keywords": [
          "/openai/v1/chat/completions",
          "LongCat-2.0"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-22",
      "last_verified": "2026-08-13",
      "delisted": {
        "on": "2026-08-14",
        "reason": "the daily free quota was gone before the row was listed — the change log retired the Flash line on 2026-05-29 and switched billing on for LongCat-2.0 on 2026-06-30, and no LongCat page still published the 100K tokens a day"
      },
      "probe_failures": 0,
      "provisional": false,
      "rank": 55,
      "archived": true,
      "archived_because": "delisted on 2026-08-14: the daily free quota was gone before the row was listed — the change log retired the Flash line on 2026-05-29 and switched billing on for LongCat-2.0 on 2026-06-30, and no LongCat page still published the 100K tokens a day",
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/longcat/"
    },
    {
      "id": "cerebras-free",
      "name": "Cerebras Inference",
      "category": "trial",
      "url": "https://www.cerebras.ai",
      "source_urls": [
        "https://inference-docs.cerebras.ai/support/rate-limits",
        "https://www.cerebras.ai/pricing",
        "https://inference-docs.cerebras.ai/models"
      ],
      "card_required": true,
      "offering": "Very fast inference; $5 in trial credits that expire in 30 days, card required before the API answers at all",
      "limits": "Cerebras' own docs: \"New accounts receive $5 in free credits after adding a verified payment method\", credits \"expire 30 days after they're granted\", and \"If you skip adding a payment method at sign-up, Playground and API access remain inactive until you do\". Asked \"Is there a permanently free tier?\" the same page answers \"No\". Free Trial rate limits are per model and the same on both the public catalog now lists — 5 RPM, 30K uncached TPM, 90K total TPM, 1M TPH, 1M TPD each (read 2026-09-03), the two TPM figures being the dual bucket the page describes. That catalog has turned over twice: GLM 4.7 was deprecated on 2026-08-17 exactly as it announced, and Gemma 4 31B left between the 09:55 UTC probe on 2026-09-03, which still found it named, and a re-read eleven hours later — replaced by Qwen 3.8 27B, the one model here that reads images, 2 per request on this tier. The marketing pricing page still promises the credits \"after making an account\" and mentions no card — that was the old API tier, which accounts opened before the change kept until 2026-08-17 and which is now gone",
      "models": [
        {
          "family": "gpt-oss",
          "released": "2025-08"
        },
        {
          "family": "qwen3.8",
          "released": ""
        }
      ],
      "api": {
        "base_url": "https://api.cerebras.ai/v1",
        "key_url": "https://cloud.cerebras.ai",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [
          "gpt-oss-120b",
          "qwen-3.8-27b"
        ],
        "note": "the Free Trial tier reaches every model in the public catalog, which is these two: \"Every model on the public Model Catalog is available on the Free Trial tier, subject to the per-model Free Trial rate limits\". The pair turns over: gemma-4-31b was in it on the morning of 2026-09-03 and gone by that evening, with qwen-3.8-27b in its place"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://inference-docs.cerebras.ai/support/rate-limits",
        "keywords": [
          "after adding a verified payment method",
          "credits expire 30 days after"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-19",
      "last_verified": "2026-09-14",
      "delisted": {
        "on": "2026-09-16",
        "reason": "its only free offer was $5 of credit granted after a verified payment method is added, expiring in 30 days — a one-off credit behind a card, which CONTRIBUTING does not admit"
      },
      "probe_failures": 0,
      "provisional": false,
      "rank": 35,
      "archived": true,
      "archived_because": "delisted on 2026-09-16: its only free offer was $5 of credit granted after a verified payment method is added, expiring in 30 days — a one-off credit behind a card, which CONTRIBUTING does not admit",
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/cerebras-free/"
    },
    {
      "id": "infomaniak-ai",
      "name": "Infomaniak AI Services",
      "category": "trial",
      "url": "https://www.infomaniak.com/en/hosting/ai-services",
      "source_urls": [
        "https://www.infomaniak.com/en/support/faq/2845/getting-started-guide-ai-services-sovereign-ai-services",
        "https://www.infomaniak.com/en/hosting/ai-services/prices"
      ],
      "card_required": true,
      "offering": "Swiss sovereign-cloud API over open-weight models with a one-month trial wallet of one million credits, one credit per LLM token",
      "limits": "\"One million free credits allow you to test the service without commitment for one month\" and \"The API is billed on a credit basis. Each request consumes one credit or LLM token\" (support guide 2845, read 2026-09-02). The card is the gate: \"A credit card is required to start using the API. An unpaid invoice will result in service suspension\", and the sales FAQ adds that at account creation \"we'll ask you to confirm your identity by registering a valid payment card\". After the wallet, list rates in CHF per 1M tokens — Gemma 4 31B at CHF 0.20/0.40, Kimi K2.6 at CHF 0.60/3.00, Qwen3.5-122B at CHF 0.40/3.20 — billed at the end of the month, with a spending limit settable in the Manager. Models are hosted in Switzerland, and \"We don't currently offer the option of training our AI Services using custom data\"",
      "models": [],
      "api": {
        "base_url": "https://api.infomaniak.com/2/ai/{product_id}/openai/v1",
        "key_url": "https://manager.infomaniak.com",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [],
        "note": "{product_id} is the AI Services product id shown in the Infomaniak Manager, where the API token is created too; the million credits are a one-month trial rather than a standing lane, which is why the Free models column stays empty"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://www.infomaniak.com/en/support/faq/2845/getting-started-guide-ai-services-sovereign-ai-services",
        "keywords": [
          "One million free credits",
          "A credit card is required to start using the API"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-09-02",
      "last_verified": "2026-09-14",
      "delisted": {
        "on": "2026-09-16",
        "reason": "a one-month wallet of a million credits, and \"A credit card is required to start using the API\" — a one-off credit behind a card, which CONTRIBUTING does not admit"
      },
      "probe_failures": 0,
      "provisional": true,
      "rank": 85,
      "archived": true,
      "archived_because": "delisted on 2026-09-16: a one-month wallet of a million credits, and \"A credit card is required to start using the API\" — a one-off credit behind a card, which CONTRIBUTING does not admit",
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/infomaniak-ai/"
    },
    {
      "id": "kenari",
      "name": "Kenari",
      "category": "aggregator",
      "url": "https://kenari.id",
      "source_urls": [
        "https://kenari.id/en/docs/billing",
        "https://kenari.id/api/public/pricing",
        "https://kenari.id/v1/models",
        "https://kenari.id/docs/messages"
      ],
      "card_required": false,
      "offering": "Indonesian OpenAI- and Anthropic-compatible gateway whose :free ids are billed Rp 0 behind a per-minute and a daily cap — sixteen on 2026-09-16, GLM-4.7-Flash, Nemotron 3 Ultra, Hy3 and Mistral Medium 3.5 among them",
      "limits": "\"Models with the :free suffix, for example step-3-7-flash:free, are billed at Rp 0. In exchange, there is a per-account request limit per minute\", and \"Besides the per-minute limit, :free models also carry a daily request allowance with three tiers, based on account status\". The figures live in the public pricing endpoint the docs point at, kenari.id/api/public/pricing (re-read 2026-09-03, unchanged): a new account gets 50 requests a day at 5 per minute, an account whose top-ups pass Rp 10,000 gets 1,000 a day at 10 per minute, and a subscription lifts the per-minute cap to 15. \"Running out of daily quota returns HTTP 429 with a Retry-After header and reason free_quota_daily\", and \"The free lane is best-effort: capacity is kept lean, with no guarantee of the same speed or availability as paid models\". Sign-up asks for no card — top-ups are QRIS, \"tanpa kartu kredit internasional\", without an international credit card — and the privacy policy says \"Kami tidak menyimpan isi prompt maupun isi respons\", prompt and response content are not stored; the terms forbid reselling access. Docs are Indonesian with a full English mirror under /en/docs",
      "models": [
        {
          "family": "nemotron-3-ultra",
          "released": "2026-03",
          "aa_model": "nvidia-nemotron-3-ultra-550b-a55b"
        },
        {
          "family": "nemotron-3-super",
          "released": "2026-03",
          "aa_model": "nvidia-nemotron-3-super-120b-a12b"
        },
        {
          "family": "step-3.7-flash",
          "released": "2026-07",
          "aa_model": "step-3-7-flash"
        },
        {
          "family": "laguna-s-2.1",
          "released": "2026-07"
        }
      ],
      "probe": {
        "type": "api-models",
        "endpoint": "https://kenari.id/v1/models",
        "keywords": [],
        "free_marker": ":free",
        "dead_markers": [],
        "require_zero_price": true,
        "machinery_keywords": []
      },
      "first_seen": "2026-09-02",
      "last_verified": "2026-09-14",
      "delisted": {
        "on": "2026-09-16",
        "reason": "rejected for cause — the operator's own JavaScript bundle showed its capacity coming from pooled ChatGPT and Codex OAuth credentials, captcha solvers and a proxy pool that multiplies per-IP free quotas"
      },
      "probe_failures": 0,
      "provisional": true,
      "rank": 55,
      "archived": true,
      "archived_because": "delisted on 2026-09-16: rejected for cause — the operator's own JavaScript bundle showed its capacity coming from pooled ChatGPT and Codex OAuth credentials, captcha solvers and a proxy pool that multiplies per-IP free quotas",
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/kenari/"
    },
    {
      "id": "scaleway-generative",
      "name": "Scaleway Generative APIs",
      "category": "api-free-tier",
      "url": "https://www.scaleway.com/en/generative-apis/",
      "source_urls": [
        "https://www.scaleway.com/en/docs/generative-apis/faq/"
      ],
      "card_required": true,
      "offering": "EU-made serverless LLM API (OpenAI-compatible); 1M free tokens for every new customer",
      "limits": "1,000,000 free tokens then pay-per-token; a valid payment method is required. The allowance is not a model lane — \"The Free Tier is applied to the most expensive tokens first\", across the whole serverless catalog, which on 2026-08-14 read glm-5.2, deepseek-v4-flash-0731, gpt-oss-120b/20b, qwen3.5-397b-a17b, qwen3-235b, llama-3.3-70b and the Mistral line",
      "models": [],
      "api": {
        "base_url": "https://api.scaleway.ai/v1",
        "key_url": "https://console.scaleway.com",
        "auth": "api-key",
        "openai_compatible": true,
        "model_ids": [],
        "note": "non-default project: https://api.scaleway.ai/{project_id}/v1"
      },
      "probe": {
        "type": "page-keywords",
        "endpoint": "https://www.scaleway.com/en/docs/generative-apis/faq/",
        "keywords": [
          "1,000,000 tokens",
          "free tier"
        ],
        "free_marker": "",
        "dead_markers": [],
        "require_zero_price": false,
        "machinery_keywords": []
      },
      "first_seen": "2026-07-20",
      "last_verified": "2026-09-14",
      "delisted": {
        "on": "2026-09-16",
        "reason": "1,000,000 free tokens once per customer, and \"Ordering Scaleway resources requires a valid credit card\" — a one-off credit behind a card, which CONTRIBUTING does not admit"
      },
      "probe_failures": 0,
      "provisional": false,
      "rank": 98,
      "archived": true,
      "archived_because": "delisted on 2026-09-16: 1,000,000 free tokens once per customer, and \"Ordering Scaleway resources requires a valid credit card\" — a one-off credit behind a card, which CONTRIBUTING does not admit",
      "page": "https://mvalentsev.github.io/awesome-free-ai-coding/providers/scaleway-generative/"
    }
  ],
  "watchlist": [
    {
      "domains": [
        "modelscope.cn",
        "modelscope.ai"
      ],
      "name": "ModelScope (Alibaba)",
      "checked_on": "2026-09-17",
      "reason": "The API-Inference free quota is real and readable now, in the markdown the docs load from resouces.modelscope.cn: calls are paid in 魔粒 — \"轻量模型（0.5 魔粒/次），主流模型（1 魔粒/次），旗舰模型（2 魔粒/次）\" (0.5, 1 or 2 per call by model size) — and an account gets \"200 魔粒/日\" for signing in and 50 more a day for binding an Alibaba Cloud account, both marked 短期 (short-term). The grant comes with each day's login (每日登录即可获取，当日有效), and spending 魔粒 first needs a verified personal email (魔粒使用前置要求：完善个人信息，包括提供验证通过的个人邮箱). The keyless catalog at api-inference.modelscope.cn/v1/models lists 35 ids (2026-09-17). API-Inference needs that Alibaba Cloud account to have passed real-name verification (\"对应云账号需已通过实名认证后，才可正常使用API-Inference\"), which CONTRIBUTING counts against a row's rank rather than its place on the list. What keeps it off is the probe: the docs sit under a dated release path (2026-9-10_15-4-CN) that the site replaces, while old paths keep answering, so a keyword read there would outlive the offer.",
      "reopen_if": "A stable URL carries the 魔粒 quota, or the probe learns to follow the current path from www.modelscope.cn/api/v1/document/main_doc_CN_prod.",
      "current": true
    },
    {
      "domains": [
        "siliconflow.com",
        "siliconflow.cn"
      ],
      "name": "SiliconFlow",
      "checked_on": "2026-09-16",
      "reason": "siliconflow.com/pricing states the offer as \"postpaid billing—plus $1 in free credits to get you started!\", a one-off grant, and siliconflow.cn/pricing marks only non-coding rows 免费 (free), Hunyuan-MT-7B translation among them. A one-off dollar is listed here when it asks for no card, as RouterPlex's does, so the open question is the card: no page read says whether the credit can be spent before a payment method is added (2026-09-16).",
      "reopen_if": "A page says the $1 needs no payment method, or a zero-priced coding model appears.",
      "current": true
    },
    {
      "domains": [
        "nebius.com",
        "nebius.ai"
      ],
      "name": "Nebius Token Factory",
      "checked_on": "2026-08-14",
      "reason": "Rebranded from Nebius AI Studio — studio.nebius.com now redirects to tokenfactory.nebius.com. Its served pages carry no free tier at all: the pricing page prices storage and GPU-hours, the product page offers a \"Start free\" button and a sales contact, and the docs quickstart carries no grant, quota or trial. The catalog answers 401 without a key. Nothing here is a free offer a developer can name, so there is nothing to list.",
      "reopen_if": "Token Factory publishes a signup grant or a free model lane on a served page.",
      "current": true
    },
    {
      "domains": [
        "nscale.com"
      ],
      "name": "Nscale",
      "checked_on": "2026-09-16",
      "reason": "Paid from the first call: docs.nscale.com, readable again on 2026-09-16, opens with \"Add credit to your account From the dashboard, add a minimum of $5 of credit to start using our service\", and no page names a free grant.",
      "reopen_if": "Nscale publishes free credits or a free serverless allowance.",
      "current": true
    },
    {
      "domains": [
        "glhf.chat"
      ],
      "name": "glhf.chat",
      "checked_on": "2026-08-14",
      "reason": "The service does not answer. Both the site and its OpenAI-compatible endpoint return Cloudflare 522 \"Connection timed out\" — the origin is down, not the edge. An offer that cannot be reached cannot be verified, and a dead host is not evidence of a withdrawn tier either, which is why this is a watch and not a block.",
      "reopen_if": "The origin answers again and its free lane is still there.",
      "current": true
    },
    {
      "domains": [
        "x.ai"
      ],
      "name": "xAI (Grok API)",
      "checked_on": "2026-08-14",
      "reason": "docs.x.ai prices every surface — text, Agent, TTS, STT, Imagine — and names no free tier or signup grant. x.ai/api answers HTTP 403 to every non-browser client, so even a stated offer could not be probed from here. The free API credits xAI ran in exchange for data sharing are not on any current page.",
      "reopen_if": "A free tier or signup grant appears on a page that answers a plain HTTP client.",
      "current": true
    },
    {
      "domains": [
        "deepseek.com"
      ],
      "name": "DeepSeek",
      "checked_on": "2026-08-14",
      "reason": "Re-checked against api-docs.deepseek.com/quick_start/pricing, which is server-rendered and prices every model — $0.14 in / $0.28 out per 1M for the cache-miss tier, no zero row anywhere. This confirms the 2026-07-27 removal: the 5M-token signup grant that used to be cited for DeepSeek was only ever reported by third parties and appears on no official page.",
      "reopen_if": "An official DeepSeek page states a free grant or a zero-priced model.",
      "current": true
    },
    {
      "domains": [
        "iflow.cn"
      ],
      "name": "iFlow",
      "checked_on": "2026-09-16",
      "reason": "iFlow stopped its developer service on 2026-04-17. Its own forum announcement that day reads \"今日11点 iFlow CLI 将停止各项服务，除仅支持使用自定义模型外相关的模型调用、搜索服务都不可用\" (from 11:00 today iFlow CLI stops its services; model calls and search are unavailable, only custom models remain). This record used to call a rival list's report of that shutdown wrong; the report was right.",
      "reopen_if": "iFlow reopens model calls with a free quota.",
      "current": true
    },
    {
      "domains": [
        "supermaven.com"
      ],
      "name": "Supermaven",
      "checked_on": "2026-09-16",
      "reason": "Being wound down. \"Sunsetting Supermaven\" (supermaven.com/blog, Nov 21, 2025): \"We will provide free autocomplete inference for existing customers for the foreseeable future.\" The pricing page still shows \"Free Tier $0 /month\", but the free promise covers existing customers, and it was completions only — no chat, agent use or API.",
      "reopen_if": "Supermaven takes new users again with a free plan that includes chat, agent use or an API.",
      "current": true
    },
    {
      "domains": [
        "novita.ai"
      ],
      "name": "Novita AI",
      "checked_on": "2026-08-14",
      "reason": "Listed here from 2026-07-19 until 2026-08-14, when a hand check found the free lane gone with no announcement anywhere. novita.ai/pricing carries 102 published prices and not one of them is zero; the two models this entry named as free are now billed — inclusionai/ling-3.0-flash at $0.06/$0.18 per Mt and mindai/macaron-v1-venti at 15000/45000 micro-units — and novita.ai/models marks every one of its 102 rows \"isFree\": false in its own page data. The keyless catalog does carry eleven rows at input_token_price_per_m 0, but they publish no pricing object, four are plainly internal (ai_infer_test_1/2/3, bunny) and the rest 404 on their own model pages, so that is an unpriced shelf and not an offer. What is left is the ~$0.5 signup credit, and a trial is not a tier. The old probe passed through all of this because it anchored on the id \"ling-3.0-flash\" plus the word \"free\" — both still on the page — instead of on the price beside the id.",
      "reopen_if": "novita.ai/pricing shows a zero price, or a model on novita.ai/models carries \"isFree\": true.",
      "current": true
    },
    {
      "domains": [
        "aionlabs.ai"
      ],
      "name": "Aion Labs",
      "checked_on": "2026-08-14",
      "reason": "Re-checked 2026-08-14, and the first reason recorded here was wrong: this is an LLM API vendor, not the email-agent company of the same name. The site sells \"Powerful AI Models & Agents\" with \"access via an OpenAI-compatible API\"; api.aionlabs.ai/v1/models answers keyless with four models — aion-2.0, aion-3.0, aion-3.0-mini and aion-rp-llama-3.1-8b, roleplay and storytelling variants of DeepSeek and GLM. The verdict is unchanged for a different reason: every one of the four publishes a price and none of them is zero, the cheapest being aion-3.0-mini at $0.0000007 per prompt token. Note the catalog answers {\"models\": [...]} rather than the OpenAI {\"data\": [...]} shape, so an api-models probe here would need that read first.",
      "reopen_if": "A zero-priced row appears in the api.aionlabs.ai catalog.",
      "current": true
    },
    {
      "domains": [
        "tokenrouter.io"
      ],
      "name": "TokenRouter.io",
      "checked_on": "2026-08-05",
      "reason": "Legitimate commercial routing layer, and the third unrelated service to carry the TokenRouter name — check the TLD before acting on any lead here, because .com is the listed PaleBlueDot gateway and .me is blocklisted. Its quickstart says \"You need at least one AI provider key to route requests\" and sends you to platform.openai.com, i.e. BYOK-only with no bundled model usage, and its \"Free tier available\" covers the routing plan, not tokens — the pricing page's own words are \"Pay only for routing and insights\". Not blocklisted precisely because nothing is wrong with it.",
      "reopen_if": "TokenRouter.io starts bundling model usage rather than routing only.",
      "current": true
    },
    {
      "domains": [
        "morphllm.com"
      ],
      "name": "Morph (fast-apply)",
      "checked_on": "2026-09-16",
      "reason": "A free tier of roughly 200 requests a month on the fast-apply model is reported by third parties, and nothing readable confirms it: morphllm.com/pricing answers HTTP 429 with a Vercel Security Checkpoint, and docs.morphllm.com/llms.txt carries no prices and no free tier (2026-09-16).",
      "reopen_if": "Morph states its free quota on a page an ordinary client can read.",
      "current": true
    },
    {
      "domains": [
        "arcee.ai"
      ],
      "name": "Arcee (Trinity)",
      "checked_on": "2026-07-22",
      "reason": "Direct API grants are application-gated, and an application with a selection step is not an offer a developer can simply use — the same bar that keeps TokenRouter's builder programme out of its entry. The :free Trinity variants that are open live on OpenRouter, which this list already covers.",
      "reopen_if": "Arcee opens direct API credits without an application.",
      "current": true
    },
    {
      "domains": [
        "ofox.ai"
      ],
      "name": "OfoxAI",
      "checked_on": "2026-08-14",
      "reason": "An OpenAI-compatible gateway with a keyless catalog — api.ofox.ai/v1/models answers 130 rows unauthenticated — and every text model in it is priced. Its eight GLM rows start at glm-4.7-flashx for $0.072 per M input, and there is no glm-4.7-flash in the catalog at all, so the third-party claim that it serves GLM-4.7-Flash at $0 per M is about a model it does not carry. The fourteen rows that do read prompt 0 and completion 0 are video, image and transcription models whose real price sits in a per-second or per-image field beside them.",
      "reopen_if": "A text model in api.ofox.ai/v1/models prices both prompt and completion at zero.",
      "current": true
    },
    {
      "domains": [
        "warp.dev"
      ],
      "name": "Warp",
      "checked_on": "2026-08-14",
      "reason": "The Free plan is real and costs nothing, but it bundles no model usage: warp.dev/pricing lists it as \"Reload credits at pay-as-you-go rates\" and \"Bring your own AI inference\", while the 1,500 included credits begin on the $20 Build plan. Third-party lists still credit the free plan with 150 then 75 AI credits a month; that allowance is no longer on the vendor's own page. A terminal that asks for your own key is the aider case, not the opencode one.",
      "reopen_if": "The Free plan on warp.dev/pricing lists an included monthly credit or token allowance instead of pay-as-you-go reloads.",
      "current": true
    },
    {
      "domains": [
        "platform.xiaomimimo.com",
        "mimo.mi.com"
      ],
      "name": "Xiaomi MiMo (API platform)",
      "checked_on": "2026-08-14",
      "reason": "A separate surface from the archived MiMo Code entry, and also paid. The keyless platform.xiaomimimo.com/api/v1/models publishes five models and prices all of them, the cheapest being mimo-v2.5 at $0.14 in / $0.28 out per M. The Token Plan is a paid subscription — the site advertises MiMo Claw at 14.9 yuan a month as \"stackable with Token Plan\" — and both mimo.mi.com/pricing and platform.xiaomimimo.com/pricing are client- rendered shells serving 29 characters of text, so no probe could read an offer there even if one appeared.",
      "reopen_if": "The keyless catalog carries a zero-priced row, or a free tier appears in server-rendered HTML.",
      "current": true
    },
    {
      "domains": [
        "atlassian.com"
      ],
      "name": "Atlassian Rovo Dev",
      "checked_on": "2026-09-16",
      "reason": "Its own FAQ answers the question: \"There is no free tier for Rovo Dev\", and \"Rovo Dev Standard is available with a free 30-day trial\" (atlassian.com/software/rovo-dev/pricing, 2026-09-16). The limited monthly credits Atlassian extends to Jira Cloud customers ride on a paid subscription, and neither page says whether the trial takes a card.",
      "reopen_if": "Rovo Dev gains an allowance reachable without a paid plan, or a trial page states it needs no card.",
      "current": true
    },
    {
      "domains": [
        "forgecode.dev"
      ],
      "name": "ForgeCode",
      "checked_on": "2026-08-14",
      "reason": "A coding harness that brings no model usage of its own. Its installation docs say ForgeCode \"needs access to at least one AI model\", walk you through entering an API key, and recommend reusing a ChatGPT Plus or Claude subscription you already pay for; forgecode.dev/pricing is a 404. The \"10K tokens a day via OpenRouter\" credited to it elsewhere is OpenRouter's own free tier reached with the reader's key, and OpenRouter is already an entry here.",
      "reopen_if": "ForgeCode Services bundles model usage on a plan that costs nothing.",
      "current": true
    },
    {
      "domains": [
        "deepinfra.com"
      ],
      "name": "DeepInfra",
      "checked_on": "2026-08-14",
      "reason": "deepinfra.com/pricing serves 17,500 characters of text and not one of them is \"free\" or \"credit\" — the whole page is per-token rates for language models and per-execution-time rates for everything else. The signup credit it is still credited with elsewhere is not on the vendor's own page.",
      "reopen_if": "DeepInfra publishes a signup credit or a free model on its pricing page.",
      "current": true
    },
    {
      "domains": [
        "baseten.co"
      ],
      "name": "Baseten",
      "checked_on": "2026-08-14",
      "reason": "Its pricing FAQ says only that \"new Baseten accounts come with credits so you can get to know the UI and experiment with deployments for free\" — no figure, anywhere on the page. There is nothing a probe could anchor on, and a sentence with no number in it reads the same the day the credit stops being granted.",
      "reopen_if": "Baseten publishes the size of the signup credit.",
      "current": true
    },
    {
      "domains": [
        "hyperbolic.ai",
        "hyperbolic.xyz"
      ],
      "name": "Hyperbolic",
      "checked_on": "2026-08-14",
      "reason": "The business is GPU rental now, not a free inference lane — hyperbolic.ai/pricing is a 404 and the home page sells on-demand GPUs \"billed by the hour\" and reserved capacity at discounted rates. The $1 inference credit third-party lists still quote is not on any page it serves. Both domains are recorded because the lists still point at the older one: hyperbolic.xyz/pricing and app.hyperbolic.xyz redirect to the .ai host (measured 2026-08-14), so a verdict filed under one name would have left the other free to be re-proposed.",
      "reopen_if": "Hyperbolic publishes an inference free tier or signup credit again.",
      "current": true
    },
    {
      "domains": [
        "inference.net"
      ],
      "name": "Inference.net",
      "checked_on": "2026-08-14",
      "reason": "The $0 plan is a gateway and observability tier, not free inference: it lists \"1M included Gateway requests, 1M tracing spans, 14-day data retention, 1 seat, 30 req/min\" and is priced \"$0 + usage\", so the tokens themselves are still bought. The only opening credit on the page, $50, is attached to the $250-a-month Growth plan.",
      "reopen_if": "The $0 plan includes inference credits or a zero-priced model rather than routing quota.",
      "current": true
    },
    {
      "domains": [
        "chutes.ai"
      ],
      "name": "Chutes",
      "checked_on": "2026-08-14",
      "reason": "Re-confirms the 2026-08-06 reading, which was never written down. Its pricing page states the model outright — \"Pay per token. No subscription, no minimum, no markup\" — and the cheapest thing on it is a $10-a-month Plus plan bundling a daily request quota. The free-trial FAQ entry is a collapsed client-rendered answer with nothing behind it in the HTML.",
      "reopen_if": "Chutes publishes a zero-priced model or a no-card trial quota.",
      "current": true
    },
    {
      "domains": [
        "tabnine.com"
      ],
      "name": "Tabnine",
      "checked_on": "2026-09-16",
      "reason": "No free plan to read any more: \"Tabnine has been acquired by Tricentis\" (tabnine.com/pricing), and the subscription docs list only \"Enterprise (SaaS)\" and \"Enterprise (private installation)\" (2026-09-16).",
      "reopen_if": "A free or individual plan returns.",
      "current": true
    },
    {
      "domains": [
        "bolt.new"
      ],
      "name": "Bolt.new",
      "checked_on": "2026-08-14",
      "reason": "A real bundled free tier — bolt.new/pricing gives the $0 plan \"300K tokens daily limit, 1M tokens per month\" — spent inside a hosted app builder. It buys generations in Bolt's own workspace, not model access a developer can point at a repository they already have, and there is no client to install and no endpoint to call. That is the line this list draws: an entry has to hand you model access you can aim at your own code.",
      "reopen_if": "Bolt ships a CLI or an API whose free plan includes the model usage.",
      "current": true
    },
    {
      "domains": [
        "lovable.dev"
      ],
      "name": "Lovable",
      "checked_on": "2026-08-14",
      "reason": "Same hosted-builder shape as Bolt, and thinner: its own FAQ says \"Paid plans have access to a credit balance\" and describes the free plan only as having \"grants included in the free plan\", with no figure in the served HTML.",
      "reopen_if": "Lovable publishes a free-plan allowance in server-rendered HTML and a way to spend it outside its own workspace.",
      "current": true
    },
    {
      "domains": [
        "v0.dev",
        "v0.app"
      ],
      "name": "v0 (Vercel)",
      "checked_on": "2026-09-17",
      "reason": "The closest of the three to qualifying and still out. Its free plan is \"$5 of included monthly credits\" with a \"7 message/day limit\", and it does have an API — api.v0.dev/v1, keyed by V0_API_KEY — but that API is /chats/:id/messages, a product endpoint for driving v0's own builder, not a model endpoint. The credit buys v0 messages, not tokens you can spend on your own codebase. Vercel's model credits that can be spent that way are already listed here as Vercel AI Gateway. Re-read 2026-09-17: a keyless POST to api.v0.dev/v1/chat/completions answers 404, while /v1/chats answers 401.",
      "reopen_if": "The v0 free plan's credits become spendable through an OpenAI-compatible or otherwise general model endpoint.",
      "current": true
    },
    {
      "domains": [
        "longcat.chat"
      ],
      "name": "LongCat API Platform (Meituan)",
      "checked_on": "2026-08-14",
      "reason": "Listed here from 2026-07-22 for a recurring 100K free tokens a day, and delisted because that quota is published nowhere on Meituan's own site today. Two dated entries in its change log explain what happened. \"Version: 2026-05-29 — LongCat Model Service Sunset\" retired the whole Flash line the free quota applied to: \"Effective May 29, 2026, the platform will retire the following 6 models: LongCat-Flash-Chat, LongCat-Flash-Thinking, LongCat-Flash-Thinking-2601, LongCat-Flash-Lite, LongCat-Flash-Omni-2603, LongCat-Flash-Chat-2602-Exp\". Then \"Version: 2026-06-30 — LongCat-2.0 Release & Billing Now Available\" turned on Token Packs and pay-as-you-go. The API is alive and good, but it is now priced: \"Pay-As-You-Go currently supports LongCat-2.0\" at $0.75 uncached input and $2.95 output per 1M tokens, and its prerequisites end with \"Top up your balance at Billing → Recharge\". The words \"free\" and 免费 appear nowhere in Quick Start, Token Pack, API Pay-As-You-Go, the FAQ, the API overview or the pricing page — the one \"free\" in the change log is about chatting on the consumer LongCat Chat app, not the API. The platform page itself is a 21-character client-rendered shell. Complimentary credits exist as a concept (\"If you also have complimentary credits, those are consumed before your paid balance\") but nothing states that a new account is granted any, how many, or how often. Our probe never noticed, because it anchored on the endpoint path and the model name rather than on the offer — novita's failure, again. Where our figure came from, for whoever is tempted to re-add it: free daily quotas at LongCat belong to the era before GA. The Chinese change log grants one on 2026-04-20, to the PREVIEW model — \"初始额度5,000,000 Tokens/天 ... 每日最多可获得120,000,000 Tokens\" — and 赠送 appears nowhere in that log at all. The reference response for GET /openai/v1/models in the docs now lists exactly one entry, \"id\": \"LongCat-2.0\", \"owned_by\": \"LongCat\".",
      "reopen_if": "LongCat publishes a free daily token quota, or a stated signup grant, on a server-rendered page of its own.",
      "current": true
    },
    {
      "domains": [
        "anyapi.ai"
      ],
      "name": "AnyAPI",
      "checked_on": "2026-08-14",
      "reason": "The free plan is real, published and server-rendered: anyapi.ai/pricing reads \"Free / Getting started / $0 / mo\", \"ANY Tokens: 100K / day\", \"Core features: All free and basic models\", \"No credit card required\", and docs.anyapi.ai repeats it — \"$0/month 100 000 ₳nyTokens per day for free / Basic and free models access\" and \"Free: Your 100K daily ₳nytokens reset every 24 hours\". What stops it is that nothing says what the quota buys. The plan cards count ₳nyTokens; the FAQ on the same pricing page defines a different unit and never reconciles them — \"A credit is our universal currency for API usage across all 400+ models. One credit equals roughly 1,000 tokens for most models, but premium models like GPT-4 or Claude 3 Opus consume more credits per token\". At 1,000 tokens a unit the free plan would be 100M model tokens a day, and the $19.90 plan 100 billion a month, which cannot be what is meant. Which models count as \"free and basic\" is published nowhere, api.anyapi.ai/v1/models answers 401, and there is no per-model price page — so there is nothing to probe that ties a model to the tier, and no arithmetic to tell a real gateway from a resold pool. The pricing copy still headlines GPT-4 and Claude 3 Opus in 2026, which is its own answer about how current it is.",
      "reopen_if": "AnyAPI publishes which models the free plan serves, or a keyless catalog, or defines its token unit against real model tokens.",
      "current": true
    },
    {
      "domains": [
        "ainative.studio"
      ],
      "name": "AINative Studio",
      "checked_on": "2026-08-14",
      "reason": "Carried elsewhere as \"a recurring ~10M tokens/month free allocation (no card)\". Its own pricing page says otherwise, twice on one screen: the heading \"Hobbyist (free)\" is followed by \"Just getting started? Start the Hobbyist plan — 3-day free trial, then $5/mo\", and the model table under it is titled \"Hobbyist $5/mo and up ... Token usage billed per rates below\" with a real price on every row (Qwen3 Coder 30B $0.04/$0.04, GPT OSS 120B $0.42/$0.90, Gemma 4 31B $0.99/$1.49, GLM-4.7 Preview $1.25/$2.75). So the free part is a three-day trial on a paid plan that also meters tokens, and the words \"free tier\", \"10M\" and \"no credit card\" appear nowhere on the page. Its keyless api.ainative.studio/api/v1/models does answer 200 with 84 rows, but they carry no prices and include other vendors' catalogs (claude-3-sonnet owned_by anthropic, arcee-trinity owned_by digitalocean) tagged source \"playground\".",
      "reopen_if": "AINative publishes a recurring no-card allowance on a served page, with the models it covers.",
      "current": true
    },
    {
      "domains": [
        "aihorde.net"
      ],
      "name": "AI Horde",
      "checked_on": "2026-09-17",
      "reason": "Genuinely free and legitimate — \"A free, community-powered generation service: volunteers share spare computer power so anyone can generate images and text\" — and OpenAI-shaped at oai.aihorde.net, where anyone may \"use the anonymous API key 0000000000 at the lowest priority\" (a call with no key at all answers 401). It cannot drive a coding agent: the route's ChatCompletionRequest schema has no tools field, and what it serves is a live census of whichever volunteers are online, mostly small roleplay fine-tunes, with no model an agent can count on being there tomorrow. The route calls itself \"a pilot and might be restricted or expanded in the future\" (2026-09-17).",
      "reopen_if": "AI Horde's OpenAI route accepts tool definitions, or it publishes a set of models it keeps available.",
      "current": true
    },
    {
      "domains": [
        "together.ai",
        "together.xyz"
      ],
      "name": "Together AI",
      "checked_on": "2026-08-14",
      "reason": "Serverless inference priced per token with no free lane on its own pages. together.ai/pricing is a per-1M-token table whose cheapest row is still paid, and the word \"free\" does not occur once in the served text of that page, of docs.together.ai/docs/serverless/rate-limits, or of the quickstart; no model id ending in -Free is served on any of the three. The rate-limit page talks about bursts and real-time capacity and never about a tier.",
      "reopen_if": "Together publishes a free tier or a zero-priced model row, or a model id ending in -Free returns to its catalog.",
      "current": true
    },
    {
      "domains": [
        "perplexity.ai"
      ],
      "name": "Perplexity (Sonar API)",
      "checked_on": "2026-08-14",
      "reason": "Pay-per-use with no free allowance of its own. The word \"free\" does not occur in the served text of docs.perplexity.ai/getting-started/pricing, which prices Sonar at $1 in and $1 out per 1M tokens, search requests at $5 per 1000 and each tool per invocation; the page's only credit language is \"Purchase API credits through AWS Marketplace\". Credits bundled with a paid subscription, if any, would be a wallet behind a paywall rather than a free tier.",
      "reopen_if": "Perplexity publishes an API allowance reachable without a paid subscription or a credit purchase.",
      "current": true
    },
    {
      "domains": [
        "replicate.com"
      ],
      "name": "Replicate",
      "checked_on": "2026-08-14",
      "reason": "replicate.com/pricing says \"You only pay for what you use on Replicate\" and prices every model by hardware-second or by token. The only \"free\" in the served text is the \"Try for free\" sign-in button in the header — no signup grant, no recurring allowance, no zero-priced model.",
      "reopen_if": "Replicate publishes a signup grant or a recurring allowance rather than pay-as-you-go only.",
      "current": true
    },
    {
      "domains": [
        "modal.com"
      ],
      "name": "Modal",
      "checked_on": "2026-08-14",
      "reason": "Recurring and real — modal.com/pricing gives the $0/month Starter plan \"$30 / month free credits\" — but the credits buy compute, not inference. They are spent on containers and GPU-seconds running a model the developer deploys themselves, so there is no vendor in the transaction, nothing to probe behind an OpenAI-compatible URL and nothing to put in a Models column. It fails this list's bar on shape, the way a free Colab GPU does.",
      "reopen_if": "Modal serves models of its own behind an OpenAI-compatible endpoint on a free allowance.",
      "current": true
    },
    {
      "domains": [
        "zenmux.ai"
      ],
      "name": "ZenMux",
      "checked_on": "2026-08-14",
      "reason": "The scout proposed this on 2026-08-14 and the probe passed, because zenmux.ai/api/v1/models prices six of its 156 rows at 0 — z-ai/glm-4.6v-flash-free, z-ai/glm-4.7-flash-free, deepseek/deepseek-v4-flash-free, inclusionai/ling-3.0-tiny and the two sapiens-ai/agnes-*-flash. A zero in a price column is not a lane you can reach: ZenMux's own subscription guide says of its $0 Free tier \"The Free plan can only be used in Studio Chat on the web (roughly 5 conversations per 5 hours) and provides no API Request access\", and the other billing system, Pay As You Go, is documented as \"prepaid balance + pay-as-you-consume\" with a $5 minimum top-up. Neither published path hands a developer an API key that calls those six ids without paying, so the free price is a discount inside a paid plan rather than a free tier.",
      "reopen_if": "ZenMux documents that a zero-balance Pay As You Go key may call the -free ids, or the Free Builder tier gains API access.",
      "current": true
    },
    {
      "domains": [
        "xfyun.cn",
        "xf-yun.com",
        "xinghuo.xfyun.cn"
      ],
      "name": "iFlytek Spark (讯飞星火)",
      "checked_on": "2026-08-14",
      "reason": "The free model is real and the vendor says so on its own page: the HTTP docs describe Lite as \"轻量级大语言模型 ... 具有更高的响应速度，支持免费使用\" (a lightweight model, faster to respond, free to use), give the model id as `lite` and publish an OpenAI-compatible base url, https://spark-api-open.xf-yun.com/v1/. An anchor exists too, contrary to an earlier note here: 「具有更高的响应速度,支持免费使用」 sits in the Lite column of that page's version table in served HTML, glued to the id by 「lite指向Lite版本」 beside it. What blocks the listing is reachability. No served page states a quota, a QPS or a duration for the Lite lane; the figures that exist — the 0元/百万tokens cell and the 200,000-token free package — appear only after JavaScript runs on xinghuo.xfyun.cn/sparkapi, and that same table conditions the package on 个人认证 or 企业认证, real-name verification. Whether `lite` itself is reachable without it is stated nowhere, and console.xfyun.cn renders 「加载中……」 and nothing else. That is the ModelScope case: a real free model this list cannot yet tell a developer how to reach.",
      "reopen_if": "iFlytek states, on a served page, what the Lite lane costs and whether it needs 实名认证 — or the registration gate turns out not to need a mainland-China identity.",
      "current": true
    },
    {
      "domains": [
        "intern-ai.org.cn"
      ],
      "name": "Intern AI (书生 / InternLM, Shanghai AI Lab)",
      "checked_on": "2026-08-14",
      "reason": "The docs are readable after all, at internlm.intern-ai.org.cn/doc/docs/ — and the trailing slash is load-bearing, since the same path without it answers a 168-byte stub, which is what an earlier check here mistook for an empty domain. 197KB of served HTML confirms the base url chat.intern-ai.org.cn/api/v1, the four model ids, an Anthropic-format endpoint with a Claude Code guide, and a quota: 「API 流控限制：默认每用户 每分钟限制30次」, thirty requests a minute rather than the ten a feed credits it with. What is missing is the offer itself. Across all nine doc pages the words 免费, 收费, 付费, 计费 and 价格 do not occur once: the service states no price, free or otherwise, so there is nothing to verify and nothing an anchor could hang on — 每分钟限制30次 is a rate limit that would read exactly the same the day it started billing.",
      "reopen_if": "Intern AI states a price, or states that the API is free, on a served page.",
      "current": true
    },
    {
      "domains": [
        "dxnt.com"
      ],
      "name": "DX TOKEN",
      "checked_on": "2026-08-14",
      "reason": "Blocklisted earlier the same day on a reason that turned out to be wrong, and moved here rather than left standing. The claim was that its model ids anonymise the upstream they route to; dxnt.com/byok refutes it in its own words — \"在控制台添加自有端点，用 {身份码}/{模型名} 调用。请求直接转发到你的供应商\" — so the opaque four-character prefixes (ot5k/, its0/, ry5b/) are per-user identity codes for a customer's OWN endpoint, not a hidden supplier, and dxnt's own catalog names its models plainly as dxnt/qwen3.5-397b-a17b and the like. Its free route is four models at multiplier 0, mostly open-weight (nemotron-3-nano, llama-3.2-90b-vision, step-3.7-flash, sensenova-6.7-flash-lite), which is capacity anyone may host. What is left is not enough to block and not enough to list: the service calls itself a 中转网关, a relay gateway, discloses no sourcing for the proprietary Chinese models it relays, and its footer links 服务条款 and 隐私政策 both resolve to a page containing neither, so there are no terms and no legal entity behind any of it.",
      "reopen_if": "DX TOKEN publishes terms of service and a legal entity, or states where the models on its own dxnt/ prefix are licensed from.",
      "current": true
    },
    {
      "domains": [
        "giga.chat",
        "gigachat.devices.sberbank.ru",
        "developers.sber.ru"
      ],
      "name": "GigaChat API (Sber)",
      "checked_on": "2026-08-14",
      "reason": "The largest free grant this repository has ever verified, and it still cannot be listed. Sber's own tariff page, updated 22 July 2026, says \"В рамках Freemium-режима пользователи получают 365 000 000 бесплатных токенов для генерации текста\" and breaks it down in a served table that glues each figure to the ids it applies to — 250 000 000 for Lite (GigaChat, GigaChat-2), 40 000 000 for Pro, 25 000 000 for Max, 50 000 000 for GigaChat-3-Ultra — each valid 12 months, \"Генерация текста выполняется в одном потоке\", one stream at a time. Every new account gets the Freemium tariff by default and no card is asked for; only the paid packages take one. The endpoint is OpenAI-shaped and printed in the docs: base_url \"https://api.giga.chat/v1\", model \"GigaChat\". What blocks it is the transport. Both api.giga.chat and gigachat.devices.sberbank.ru serve certificates issued by \"C = RU, O = The Ministry of Digital Development and Communications, CN = Russian Trusted Sub CA\", chaining to a Russian Trusted Root CA that is in no mainstream trust store — measured here, not inferred: httpx fails both with CERTIFICATE_VERIFY_FAILED, and Sber documents the fix as installing the НУЦ Минцифры certificates at application or OS level. That is a change to the reader's machine, and to what their machine trusts for every other TLS connection, which is not a thing a row in a table can ask for in a footnote. Registration is a second gate on top: the console takes a Сбер ID and issues scope GIGACHAT_API_PERS.",
      "reopen_if": "api.giga.chat serves a certificate from a publicly trusted CA, or Sber documents an endpoint that does. At that point only the Сбер ID gate is left, which is the SenseNova case and lives inside an entry, and the anchor is already measured: the 365 000 000 sentence and the per-tier table sit in served HTML with ordinary spaces.",
      "current": true
    },
    {
      "domains": [
        "you.com"
      ],
      "name": "You.com API",
      "checked_on": "2026-08-14",
      "reason": "A genuinely free, genuinely keyless lane that is the wrong kind of thing. you.com/docs offers \"Try it free — no API key required\": point any MCP-enabled tool at https://api.you.com/mcp?profile=free and \"use you-search with no signup or credentials\", capped at 100 queries a day, with new accounts getting $100 in credits for the rest. It names Claude Code, Cursor, VS Code and JetBrains by name, so it is aimed squarely at the readers of this list — but what it hands them is web search, not model access, and CONTRIBUTING asks an entry for a lane you can point a coding agent's model at.",
      "reopen_if": "You.com opens a free lane on an inference endpoint rather than on search and retrieval — or this list decides that free agent tooling belongs in a section of its own, in which case this is the first row in it.",
      "current": true
    },
    {
      "domains": [
        "blackbox.ai"
      ],
      "name": "Blackbox AI",
      "checked_on": "2026-08-14",
      "reason": "Two tiers on its own pricing page and neither is free: \"PAY AS YOU GO\", metered per token against prepaid credits, and \"ENTERPRISE\", \"Your model, your keys, your contract\". The $0 in the first column is the monthly commitment — \"$0 / MO COMMIT ... Committed spend None — pay for what you use\" — not a token allowance, which is the same shape this repository rejected for AIHubMix's neighbours and for ZenMux. The 300+ model table below prices every row.",
      "reopen_if": "Blackbox publishes a free tier with a token or request allowance, on the pricing page rather than in an extension listing.",
      "current": true
    },
    {
      "domains": [
        "orcarouter.ai"
      ],
      "name": "OrcaRouter",
      "checked_on": "2026-08-14",
      "reason": "A router whose free plan is free routing, not free tokens: \"Hacker Free Forever. Zero markup on all tokens ... 3 API keys · 0% token markup\", and in its own words \"You pay each provider's published rate; OrcaRouter adds $0 per token\". Its structured pricing data agrees — an Offer named \"Free\" at price 0 with the description \"Pay provider cost only\". That is the standing rule here that a zero in a price column is not a lane you can reach: nothing is granted, the $0 is the fee for the routing.",
      "reopen_if": "OrcaRouter grants credits or a free model lane of its own, rather than charging nothing to pass a paid one through.",
      "current": true
    },
    {
      "domains": [
        "aibadgr.com"
      ],
      "name": "Badgr",
      "checked_on": "2026-08-14",
      "reason": "Not an inference free tier — GPU capacity by the hour, advertised as \"Available now Badgr 4090\". The pricing page's $0 is a subscription that does not exist: \"Pay as you go $0 /month + usage: every account gets the same features\", \"no setup fee, no monthly minimum\". A wallet, and not even a wallet with anything in it.",
      "reopen_if": "Badgr starts granting inference credits, or serves models rather than renting the cards they run on.",
      "current": true
    },
    {
      "domains": [
        "whiterabbitneo.com",
        "deephat.ai"
      ],
      "name": "Deep Hat (formerly WhiteRabbitNeo, Kindo)",
      "checked_on": "2026-08-14",
      "reason": "Renamed since gpt4free wrote its adapter — whiterabbitneo.com now redirects to deephat.ai, \"Deep Hat, formerly Whiterabbitneo, is Kindo's uncensored cybersecurity model\". The four \"Use it for free\" and \"Try it for free\" buttons on that page all lead to the hosted app; the API route on the same page is \"Get a demo\". The weights are on Hugging Face, which is a licence rather than a free tier, and is not an endpoint anyone can point an agent at without hosting it themselves.",
      "reopen_if": "Deep Hat publishes an API with a free lane, rather than a hosted app and open weights.",
      "current": true
    },
    {
      "domains": [
        "phind.com"
      ],
      "name": "Phind",
      "checked_on": "2026-08-14",
      "reason": "Nothing could be verified, and that is the finding. www.phind.com and www.phind.com/plans both answer HTTP 403 to every client tried here, including one sending a full browser header set — so no probe on this domain can read an offer, and this list would be repeating a claim rather than checking one. Worth the record because the name is otherwise a plausible candidate: a developer-facing answer engine with an editor extension is exactly the shape CONTRIBUTING admits when the free usage is bundled. Note also that gpt4free does not call phind.com at all — its adapter points at phindai.org, an unrelated clone, now on the blocklist.",
      "reopen_if": "Phind serves its plans page to a non-browser client, or publishes free terms anywhere a probe can reach.",
      "current": true
    },
    {
      "domains": [
        "yupp.ai"
      ],
      "name": "Yupp",
      "checked_on": "2026-08-14",
      "reason": "Unreadable rather than absent: yupp.ai answers HTTP 429 to every request made here, browser headers included, and the docs.yupp.ai its adapter implies does not resolve at all. gpt4free's own class for it carries working = False and needs cloudscraper, which is the same verdict from the other side. Nothing states an offer, so there is nothing to verify.",
      "reopen_if": "Yupp serves a plan or docs page to an ordinary HTTP client, and that page describes an API rather than a chat product.",
      "current": true
    },
    {
      "domains": [
        "venice.ai"
      ],
      "name": "Venice.ai",
      "checked_on": "2026-08-14",
      "reason": "The Free plan does carry an \"API Access\" checkmark, and the docs say what it is worth: \"You can create a key before funding the account, but model requests will not succeed until the account can consume DIEM, bundled credits, or USD\". DIEM comes from staking VVV and bundled credits from a subscription, which venice.ai/pricing states from the other side — \"Pro subscribers get free-tier API access\". So the free lane is a key that cannot call anything, and every row of the docs price table is quoted in dollars per million tokens.",
      "reopen_if": "An unfunded Venice account gets a callable allowance, or a model appears priced at zero for the Free plan.",
      "current": true
    },
    {
      "domains": [
        "friendli.ai"
      ],
      "name": "FriendliAI",
      "checked_on": "2026-08-14",
      "reason": "friendli.ai/pricing prices everything it serves: per-token rates for the Model APIs — GLM-5.2 at $1.4 in / $4.4 out per 1M, gemma-4-31B-it at $0.14 / $0.4 — and per-second GPU time for dedicated endpoints, $2.9 an hour on an A100 up to $12.0 on a B300. The word \"free\" does not occur in the served text of that page at all, and its own \"How do I get started?\" answer is sign up, generate a key, make a request, with no grant in between. The $10 signup credit third-party lists quote is on none of it.",
      "reopen_if": "FriendliAI states a signup grant or a zero-priced model on a page it serves.",
      "current": true
    },
    {
      "domains": [
        "cerebrium.ai"
      ],
      "name": "Cerebrium",
      "checked_on": "2026-08-14",
      "reason": "The wrong shape twice over. It is a serverless platform you deploy your own container to rather than a model endpoint you can aim an agent at, which is the BYOK case CONTRIBUTING excludes; and the free thing on cerebrium.ai/pricing is the Hobby plan's allowance of seats and slots — \"Up to 3 deployed apps\", 3 seats, 1 day of log retention — while the compute underneath is billed throughout, the page's own worked example putting 500,000 requests at \"roughly $309\" a month. No $30 credit appears anywhere on it.",
      "reopen_if": "Cerebrium starts serving hosted models on a free allowance rather than hosting yours.",
      "current": true
    },
    {
      "domains": [
        "coze.com"
      ],
      "name": "Coze",
      "checked_on": "2026-08-14",
      "reason": "Nothing here can be read, so nothing can be verified: www.coze.com answers every path tried with the same 43,754-byte SPA shell — the API overview, the pricing guide, /robots.txt and /sitemap.xml alike — and the document API behind that shell replies {\"code\":700012006,\"msg\":\"Login verification is invalid\"}. No quota, model list or terms are served anywhere a probe could anchor. The shape is doubtful as well — its own og:title calls it an \"AI Agent Intelligent Office Platform\" and its API is /v3/chat against bots built inside its workspace, which is the hosted-app-builder case CONTRIBUTING excludes — but the verification rule alone settles it, the way it settled Morph LLM.",
      "reopen_if": "Coze serves its developer docs or pricing to an ordinary HTTP client, and that page describes model access rather than bot invocations.",
      "current": true
    },
    {
      "domains": [
        "publicai.co"
      ],
      "name": "Public AI Inference Utility",
      "checked_on": "2026-09-02",
      "reason": "The word \"Free\" here names a rate-limit tier, not free inference. platform.publicai.co/plans puts four tiers side by side and the Free one buys \"100 requests/minute — default when you create an API key\"; the same page keeps the money in a separate paragraph — \"Rate limits and token usage billing are separate ... Token usage is billed against wallet credits\", with \"New accounts receive starter credits when they first use billing features\" and no figure attached to those credits anywhere on the portal. The catalog agrees: every one of the eleven models on platform.publicai.co/models carries a price (swiss-ai/apertus-v1.5-8b at $0.10/$0.20 per 1M, up to $0.82/$2.92 for the 70b), and none is listed at zero. An unnamed starter credit is the SiliconFlow reasoning again: a sign-up courtesy is not a free tier. The nonprofit itself is exactly what it says — a public-AI gateway fronting Apertus, SEA-LION, Olmo, Bielik and EuroLLM, and this list already carries SEA-LION from its own vendor. Re-read 2026-09-02: the plans page still says \"every new API key starts on the free tier\" and \"new accounts receive starter credits when they first use billing features\" with no figure attached, the models page still prices every row ($0.10 to $2.92 per 1M), and api.publicai.co/v1/models answers 401 to a keyless GET, so the catalog itself cannot be read without an account.",
      "reopen_if": "The portal names the starter credit, or platform.publicai.co/models lists a model at zero.",
      "current": true
    },
    {
      "domains": [
        "crof.ai",
        "nahcrof.com"
      ],
      "name": "CrofAI",
      "checked_on": "2026-09-02",
      "reason": "A free account is not a free tier. crof.ai/home sells the on-ramp — \"Get an API key — free account, no credit card required\" — and crof.ai/pricing states the offer in one line: \"Pay for what you use. Per-token pricing across every model we serve. No subscriptions, no minimums — only the tokens you actually burn.\" The catalog behind it, ai.nahcrof.com/v1/models, is public and prices all 23 models; not one is at zero (the cheapest row read on 2026-08-30 was $0.35 in / $0.80 out per 1M). Reached from OmniRoute's provider table, where it is filed under paid. Re-read 2026-09-02: still 23 rows and none at zero, the cheapest still $0.35 in / $0.80 out per 1M, and the only \"free\" on the pricing page is a JavaScript comment about the billing portal.",
      "reopen_if": "A model priced at 0 appears in ai.nahcrof.com/v1/models, or the pricing page starts naming a recurring free allowance.",
      "current": true
    },
    {
      "domains": [
        "bluesminds.com"
      ],
      "name": "BluesMinds",
      "checked_on": "2026-08-30",
      "reason": "OmniRoute credits it with 22 free models and ~7M tokens a month; the vendor publishes nothing of the kind. www.bluesminds.com is an enterprise page whose only two calls to action are \"Sign in\" and \"Request access\", /pricing 404s, and there is no docs host to read. The one thing its API does say is what it runs on: api.bluesminds.com/v1/models answers {\"error\":{\"message\":\"Invalid token ...\",\"type\":\"new_api_error\"}}, the error shape of the New API resale panel, which is the software a key-pooling gateway is usually built from. Nothing here is verifiable and the free claim is a third party's.",
      "reopen_if": "BluesMinds publishes a pricing or docs page an ordinary HTTP client can read, and that page names a free allowance of its own.",
      "current": true
    },
    {
      "domains": [
        "bynara.id"
      ],
      "name": "Nara / NaraRouter",
      "checked_on": "2026-09-14",
      "reason": "The free plan is real now and published, and what it serves is the reason it stays here. The keyless router.bynara.id/api/plans reads \"Free tier with a daily token quota. No card required\", token_cap_daily 7,000,000 at 15 requests a minute, over four models — agnes-2.5-flash, laguna-s-2.1, stepfun-3.7-flash and tencent-hy3-free — which are other vendors' free lanes: Agnes prices its Flash at zero itself, Laguna S 2.1 is free on OpenRouter and Kilo, and Step 3.7 Flash on Kilo. The paid day passes beside it (Freemium at Rp 5,000 a day, FreeMium Max, FreeMium Ultra) sell glm-5.3-free, mimo-v2.5-free, qwen3.8-flash-free, deepseek-v4.1-flash-free and muse-spark-1.3-contributor-free — ids named for free lanes, sold by the day. OmniRoute also reports that a key requires linking Telegram. The 2026-08-30 reading here found no pricing and a 401 catalog; this one was prompted by OmniRoute citing the plans endpoint.",
      "reopen_if": "Nara's free plan serves a model it hosts or licenses itself, rather than another gateway's free lane.",
      "current": true
    },
    {
      "domains": [
        "liquid.ai"
      ],
      "name": "Liquid AI (LFM / LEAP)",
      "checked_on": "2026-08-30",
      "reason": "The wrong shape rather than the wrong price. Liquid's product is the LEAP edge platform — \"Discover, specialize, and deploy models on any device\" — whose models run on the phone or laptop you ship them to, not behind a hosted endpoint an agent can call: api.liquid.ai/v1/models does not exist (404 from the marketing app) and labs.liquid.ai serves no catalog either. A local runtime is out of scope here for the same reason Ollama's desktop build is, and the \"keyless\" row OmniRoute files for it names no endpoint.",
      "reopen_if": "Liquid opens a hosted LFM API with a free lane a developer can call from outside its own SDK.",
      "current": true
    },
    {
      "domains": [
        "xkiro.com"
      ],
      "name": "xKiro",
      "checked_on": "2026-09-16",
      "reason": "api.xkiro.com/v1/models now marks 42 rows access_tier free at 0/0, no longer only Qwen: openai/gpt-5.3-codex-spark, mistralai/mistral-large-2512 and mistralai/codestral-2508 are among them, and the site's own JSON-LD featureList includes \"Claude and GPT proxy\". Free closed models prove nothing about where the capacity comes from, and no page states it either — no upstream provider is named anywhere read — so it stays unlisted until that is known (2026-09-16).",
      "reopen_if": "xKiro names where its free models are served from, or a provider confirms the arrangement.",
      "current": true
    },
    {
      "domains": [
        "unorouter.com"
      ],
      "name": "UnoRouter",
      "checked_on": "2026-08-30",
      "reason": "Blocked on 2026-08-30 and un-blocked the same day for the same error as xKiro: the frontier ids that triggered it are the paid catalog, not the free lane. Of 227 `:free` ids only nine are frontier-named, and all nine are Google's cheap tier (gemini-flash-lite, gemini-3.5/3.6-flash-lite, embeddings, robotics previews) — no Claude, no GPT. What keeps it off the list is what cannot be read rather than what was found: its catalog publishes no prices at all, so no probe here can tell a free id from a metered one; its 338 rows are `owned_by: \"custom\"` on 318 of them; and 17 Claude ids are spelled in a vocabulary no public catalog uses — claude-opus-5[1m], claude-sonnet-5-thinking[1m] — which a router may well have invented for a context-and-reasoning preset, but which nothing on the site explains. Its paid plans sell $50 of credit for $25, permanently.",
      "reopen_if": "Its catalog starts publishing per-model prices, or a page states what the free lane grants and where the `[1m]` ids come from.",
      "current": true
    },
    {
      "domains": [
        "reka.ai"
      ],
      "name": "Reka AI",
      "checked_on": "2026-08-30",
      "reason": "Moved off the blocklist, where it sat since 2026-08-11 with a reason that ended \"delete this line if an account shows otherwise\" — a verdict written to expire, filed where nothing expires. The finding itself still holds and is a watchlist finding: the entry once claimed \"$10 free credits at the start of every month\" on the strength of one dated announcement post, and no live vendor page corroborates a recurring grant. platform.reka.ai/pricing today sells Pay as you go at $0/mo with \"Credits — Top up anytime\", and the only free thing it names is in the past tense, a banner reading \"Free credits used\". A legitimate vendor with no free tier a developer can reach is the definition of this file, not of the blocklist.",
      "reopen_if": "A Reka page states a recurring free grant, or the signup credit is named with a figure.",
      "current": true
    },
    {
      "domains": [
        "api.navy",
        "navyai.dev"
      ],
      "name": "NavyAI",
      "checked_on": "2026-08-30",
      "reason": "Moved off the blocklist because the fact it rested on is not what the catalog says. The reason read \"163 models, 77 of them paid frontier ids — claude-opus-5, claude-opus-4.8, the gpt-5.6 line, o3 — offered on a free plan of 150K tokens/day\", and api.navy/v1/models carries a `premium` flag per row: 50 rows are premium and they are precisely that frontier line (gpt-5.6-sol/terra/luna, 5.5, 5.4, 5.3-codex), while the frontier-named rows that are NOT premium are the mini, nano and lite tiers. There is also a `token_multiplier` per row — 20 for claude-opus-5, 16 for gpt-5.6-sol, 1 for the ordinary rows — so the quota is spent at a rate that matches the model's cost. That is the shape of a metered plan, not of capacity given away. Not listed because nothing here can be read: api.navy and its docs answer a Cloudflare challenge to every non-browser client, so the free plan's terms cannot be verified from outside a browser.",
      "reopen_if": "NavyAI serves a pricing or docs page to an ordinary HTTP client, and that page states what the free plan grants and which models it covers.",
      "current": true
    },
    {
      "domains": [
        "cto.new"
      ],
      "name": "cto.new",
      "checked_on": "2026-09-16",
      "reason": "cto.new has a coding surface now: its changelog reads \"Launched the first version of the CTO CLI\" (June 5th 2026), and the free tier stands in the fair-use doc: \"Use cto completely free. Access to the best value models with generous usage limits that reset every day\". No page read says whether the CLI runs on that free tier, and cto.new itself answers ordinary clients with a Vercel Security Checkpoint, so docs.cto.new is the readable surface. It is Engine Labs' product (every docs asset is served from mintcdn.com/enginelabs/).",
      "reopen_if": "A cto.new page says the CLI works on the free tier.",
      "current": true
    },
    {
      "domains": [
        "gitlab.com"
      ],
      "name": "GitLab Duo Agent Platform",
      "checked_on": "2026-09-02",
      "reason": "Reached through the models.dev digest, which lists 23 duo-chat rows at cost 0 because the price is not on the row. The product page, docs.gitlab.com/user/duo_agent_platform/, files the platform under \"Tier: Premium, Ultimate\" and says of the one place a free account appears, \"Features available on the Free tier require the purchase of GitLab Credits\" — the generally available features \"consume GitLab Credits when used\". A credit you must buy is not a free tier.",
      "reopen_if": "The docs state a credit allowance included with the Free tier at no charge, with a figure.",
      "current": true
    },
    {
      "domains": [
        "pendra.ai"
      ],
      "name": "Pendra",
      "checked_on": "2026-09-02",
      "reason": "Reached through the models.dev digest (6/6 rows at cost 0). The free plan is your own hardware: pendra.ai/pricing offers \"Free £0 /month — For personal use — sovereign inference on your hardware. 1 self-hosted Pendra Worker\", the home page says \"Bring your own GPUs with a free account, or let us manage everything\", and the paid Pro tier at £99 a month is what carries \"£99 of credit to spend on on-demand GPUs\". api.pendra.ai/api/v1/models answers 401 to a keyless GET. A gateway to a GPU you supply is not free inference.",
      "reopen_if": "A hosted model callable on the free plan without supplying a worker, with a quota on the pricing page.",
      "current": true
    },
    {
      "domains": [
        "llmgateway.io"
      ],
      "name": "LLM Gateway",
      "checked_on": "2026-09-02",
      "reason": "Reached through the models.dev digest (2/182 rows at cost 0). The word \"Free\" names the platform plan, not inference: the pricing page's own JSON-LD offer reads \"Free … Access all 200+ models with a flat 5% platform fee on credit purchases, or bring your own provider keys for free\", the page says \"Start free with no credit card. Pay only for what you use\", and the docs put it as \"Pay per-token with prepaid credits at provider list rates, or bring your own provider keys (BYOK) for free\". The keyless catalog at api.llmgateway.io/v1/models prices 42 of 252 rows at 0 and every one of them is a router (custom, auto) or a media model billed by another unit — TTS, image, video. No text model is priced 0 and no sign-up credit is named. Open source under AGPLv3, which is a reason to self-host, not a free lane.",
      "reopen_if": "A text model priced 0 in the catalog, or a sign-up credit named on the pricing page.",
      "current": true
    },
    {
      "domains": [
        "nova.amazon.com"
      ],
      "name": "Amazon Nova developer API",
      "checked_on": "2026-09-02",
      "reason": "Reached through the models.dev digest, which lists api.nova.amazon.com with 2/2 rows at cost 0. Nothing here can be read: nova.amazon.com/dev, /dev/documentation, /dev/pricing and even /llms.txt all serve the same 3.8-kilobyte JavaScript shell with 13 characters of visible text, and api.nova.amazon.com/v1/models answers 500 to a keyless GET. Whatever the developer portal grants, no page states it to an ordinary HTTP client — the ModelScope bar, on the other side of the world.",
      "reopen_if": "A server-rendered page states a free quota for the Nova API, or /v1/models answers.",
      "current": true
    },
    {
      "domains": [
        "llama.developer.meta.com",
        "api.llama.com"
      ],
      "name": "Meta Llama API",
      "checked_on": "2026-09-16",
      "reason": "llama.developer.meta.com now redirects to ai.developer.meta.com, which renders nine characters of text to an ordinary client, and api.llama.com/compat/v1/models answered 401 to a keyless GET (2026-09-02). Meta may serve these models at no charge; nothing it publishes to an ordinary client says so.",
      "reopen_if": "A readable pricing or rate-limits page for the Llama API states the free allowance.",
      "current": true
    },
    {
      "domains": [
        "inferx.net"
      ],
      "name": "InferX",
      "checked_on": "2026-09-02",
      "reason": "Reached through the models.dev digest (12/12 rows at cost 0). The doc link the catalog carries, model.inferx.net/endpoints, answers 404, and the api url beside it answers 401 with \"service failure: no tenant context: set a default tenant\" to a keyless /v1/models. Nothing here names an offer, a price or a quota.",
      "reopen_if": "A readable page states what a new account may call for free, and the catalog answers.",
      "current": true
    },
    {
      "domains": [
        "kimi.com"
      ],
      "name": "Kimi For Coding (Moonshot)",
      "checked_on": "2026-09-02",
      "reason": "Reached through the models.dev digest, which lists api.kimi.com/coding with 4/4 rows at cost 0 — the price is the membership, not the row. The product docs say \"Subscribers can also obtain an API Key\" and give the billing as \"Membership subscription, monthly/annual payment, with rate limiting\" or \"Pay-as-you-go, top up and use\". The doc url the catalog carries answers 404. No free membership is named anywhere read.",
      "reopen_if": "A free membership tier with API access, with its quota stated.",
      "current": true
    },
    {
      "domains": [
        "empiriolabs.ai"
      ],
      "name": "EmpirioLabs",
      "checked_on": "2026-09-02",
      "reason": "Reached through the models.dev digest (3/56 rows at cost 0). The keyless catalog at api.empiriolabs.ai/v1/models prices 78 of 177 rows at 0 per token, and almost all of them charge by another unit — video, music, image, speech, search — while two chat rows, gemma-3-27b and mistral-small-3-1, print \"$0.0040 Per Message\" beside their zero token price. Three GLM Flash rows (glm-4-7-flash, glm-4-5-flash, glm-4-6v-flash) are the only ones whose pricing rows read \"Input Free / Output Free\", with the note \"Base token use is free\" — the same models Z.ai serves free from its own gateway, which this list already carries. Getting Started lists \"prepaid credits on your account (top up via the dashboard Billing page)\" among the prerequisites, Billing says \"EmpirioLabs AI uses a prepaid balance system\", and nothing read says a zero-balance account can call the Free rows. Limits are 50 RPM and 2M TPM per account.",
      "reopen_if": "The docs say the Free rows run on an account with no top-up, or a sign-up credit is named.",
      "current": true
    },
    {
      "domains": [
        "augmentcode.com"
      ],
      "name": "Augment Code",
      "checked_on": "2026-09-02",
      "reason": "Reached through the codertesla/ai-coding-deals list, which credits it with an unquantified Community tier. The vendor's pricing page carries two plans and neither is it: \"BUSINESS $100 /month flat — no per-seat charge\" with \"$100/mo of usage included\" for \"up to 50 seats\", and \"ENTERPRISE Custom\". The only trial on the page is a line in the SLA FAQ — \"Trials and beta use: Community support only; our SLA does not apply to trials or beta usage\" — with no terms, quota or sign-up path beside it, and the docs' token-based pricing page prices every model at public API list price plus a 40% service fee from the first token. The home page names nothing free either. Should a Community plan return, its terms are still published (v1.9, 2026-01-14): \"you grant us the right to use your Customer Code, Output, and Usage Data to train the artificial intelligence models\", against the paid page's \"No AI training allowed\".",
      "reopen_if": "A free or community plan with a stated quota appears on the pricing page.",
      "current": true
    },
    {
      "domains": [
        "app.ai21.com"
      ],
      "name": "AI21 Gateway (Tokenwise)",
      "checked_on": "2026-09-05",
      "reason": "A separate surface from the archived AI21 Labs (Jamba) entry. The 410 that retired AI21 Studio's catalog route points here — \"The AI21 Gateway is available at https://app.ai21.com\" — and what is here is a bring-your-own-key gateway, not a model API: the app's own env file names it ai21-intelligent-gateway-webapp with a base of api.ai21.com/gateway, its code snippets pass \"your own OpenAI key\" or \"your own Anthropic key\" upstream, and the only \"Free trial\" in it is a Stigg-billed \"Tokenwise\" plan trial counted in days. api.ai21.com/gateway/v1/chat/completions answers 400 \"bad or missing authentication\" keyless, so the route exists; no page, docs entry or llms.txt line describes it, and the docs index still lists only the Jamba, Maestro and Studio pages. Studio itself — where the $10 no-card trial lived — redirects every route to the www.ai21.com homepage.",
      "reopen_if": "AI21 documents the Gateway with a model AI21 hosts itself and a free quota or credit on it that needs no card.",
      "current": true
    },
    {
      "domains": [
        "poe.com"
      ],
      "name": "Poe (OpenAI-compatible API)",
      "checked_on": "2026-09-05",
      "reason": "Reached through the models.dev digest (3/137 rows at cost 0). The vendor's own catalog at api.poe.com/v1/models is keyless and carries 347 rows, 146 of them with a pricing block and none at 0 — the three the digest counts as free, gemma-4-31b, kimi-k2.5-fw and gpt-5.3-codex-spark, are rows the catalog publishes no price for at all. creator.poe.com's API page says who pays: \"All Poe subscribers can use their existing subscription points with the API at no additional cost\", a 402 insufficient_credits comes back at \"balance ≤ 0\", and the rate limit is 500 requests per minute. Whether the daily points a free Poe account gets in the app reach the API is stated nowhere the docs reach, and poe.com/pricing is a 342-character client-rendered shell.",
      "reopen_if": "Poe's docs say API calls draw on a free account's daily points, with the figure, or its catalog prices a chat row at 0.",
      "current": true
    },
    {
      "domains": [
        "cortecs.ai"
      ],
      "name": "Cortecs",
      "checked_on": "2026-09-05",
      "reason": "Reached through the models.dev digest (2/109 rows at cost 0). The keyless catalog at api.cortecs.ai/v1/models prices every row in EUR and the only two at 0.0 are qwen3guard-gen-0.6b and qwen3guard-gen-8b, safety-moderation classifiers served through OVH — the same shape as OVHcloud's zero-priced guard rows, and not a chat model. cortecs.ai/pricing is a prepaid balance with a \"5% flat service fee\", paid \"via credit card or by invoice\" behind an Auto Top-up threshold; no signup credit is named anywhere on it.",
      "reopen_if": "A chat model priced 0 in api.cortecs.ai/v1/models, or a signup credit with a figure on cortecs.ai/pricing.",
      "current": true
    },
    {
      "domains": [
        "bothub.ru"
      ],
      "name": "BotHub",
      "checked_on": "2026-09-05",
      "reason": "Reached through the models.dev digest (2/2 rows at cost 0, nemotron-3-ultra-550b-a55b:free and gemma-4-31b-it:free). bothub.ru/models lists nine :free ids with no price where every other row carries rubles per 1M tokens, and its FAQ says where they are free: \"Есть бесплатные модели с постфиксом ':free' и '-exp', которые можно использовать бесплатно через мини-окно на главной странице, а также странице модели\" — through the mini-window on the home page and the model page, which is the web chat. The API documentation at bothub.ru/api/documentation/ru says \"вы оплачиваете только фактическое использование API и моделей\" and names no free tier, the model pages count a CAPS balance, and the catalog at openai.bothub.ru/v1/models answers 401 keyless.",
      "reopen_if": "BotHub's API docs say the :free ids cost 0 CAPS through the API, or the catalog opens keyless with those rows priced 0.",
      "current": true
    },
    {
      "domains": [
        "merge.dev"
      ],
      "name": "Merge Gateway",
      "checked_on": "2026-09-05",
      "reason": "Reached through the models.dev digest (1/180 rows at cost 0, nvidia/nemotron-3.5-lightning-30b-a3b). merge.dev/pricing/gateway has a Free plan — \"Test the core functionality before you upgrade\", \"Access all free LLMs\", \"Route requests automatically with built-in fallback\", \"Start without a credit card\" — and a Pro plan at \"Pay LLM cost plus a 5% fee. Get $10 in free credits every month\", card required. Which LLMs are free is written nowhere readable: the docs' Models page is 275 characters of navigation, the catalog at api-gateway.merge.dev answers 401 keyless, and the vendor-access page says organizations created after a vendor's cutoff on Free or Pro get no access to that vendor \"until access is granted\". A plan that names no model and no quota gives a probe nothing to hold, and the one zero-priced id this list knows of came from someone else's key.",
      "reopen_if": "Merge publishes which models the Free plan serves and at what limit, or opens its catalog keyless with prices.",
      "current": true
    },
    {
      "domains": [
        "zeldoc.ai"
      ],
      "name": "Zeldoc.ai",
      "checked_on": "2026-09-05",
      "reason": "Reached through the models.dev digest (1/1 row at cost 0, zdev). docs.zeldoc.ai: \"Get an API key — Request an invitation and generate your key\" — an invitation-only European enterprise platform (\"Private. Governed. Sovereign.\") with ZDev as its own code model and ZRouter over \"40+ models routed\"; zeldoc.ai/pricing answers 404 and no page names a price, a quota or a free plan.",
      "reopen_if": "A public sign-up and a published free tier.",
      "current": true
    },
    {
      "domains": [
        "nano-gpt.com"
      ],
      "name": "NanoGPT",
      "checked_on": "2026-09-05",
      "reason": "Reached through the models.dev digest (4/592 rows at cost 0). The free model is the web chat's: nano-gpt.com/get-started says \"Start chatting with a free model—no account or balance required\", and the API quickstart says \"If you haven't deposited yet, add some funds to your balance. Minimum deposit is just $1, or $0.10 when using crypto\". The keyless catalog at nano-gpt.com/api/v1/models?detailed=true prices 616 rows and only two at 0 per token — nano-gpt-help, the vendor's support assistant, and auto-model, a router billed as whatever it routes to; the two Qwen3.5 Omni rows the digest counts as free carry \"varies_by_modality\" and a non-zero cost estimate. \"API at list prices — no markup\" is the offer, and it is a metered one.",
      "reopen_if": "A chat model priced 0 in the detailed catalog that the docs say answers on a zero balance.",
      "current": true
    },
    {
      "domains": [
        "dashscope.aliyuncs.com",
        "bailian.console.aliyun.com"
      ],
      "name": "Alibaba Cloud Model Studio (China site, 百炼)",
      "checked_on": "2026-09-05",
      "reason": "The China-site twin of the listed Alibaba Cloud Model Studio row, reached through the models.dev digest as alibaba-cn. Its new-user quota is documented in full at help.aliyun.com/zh/model-studio/new-free-quota, which also serves as .md: \"每个模型均有独立的免费额度（通常为 100 万 Token）\" — an independent quota per model, usually one million tokens — for \"90 天\" from activation, in the 华北2（北京）region alone, and \"无需实名认证即可获取和使用免费额度\": no real-name verification is needed to receive and spend it, an unverified account being stopped with a 403 AllocationQuota.FreeTierOnly when it runs out. Two things keep it off the list. The first-API-call guide on the same site says \"如果开通服务时提示'您尚未进行实名认证'，请先进行实名认证\" — activation may ask for the verification the quota page says is not needed — and the account sign-up and activation pages are client-rendered, so which of the two a reader outside mainland China meets cannot be read. The international edition, with its own quota, is the row this list carries.",
      "reopen_if": "A readable vendor page says an aliyun.com account can be opened with a non-mainland phone number and Model Studio activated without real-name verification — the quota itself is documented and large.",
      "current": true
    },
    {
      "domains": [
        "openai.com"
      ],
      "name": "OpenAI API (complimentary tokens for data sharing)",
      "checked_on": "2026-09-05",
      "reason": "Named by every list read on 2026-09-05, usually as \"$50,000 in free credits\". The pricing page (developers.openai.com/api/docs/pricing) prices every model per token, marks one row Free — omni-moderation-latest — and carries no signup credit and no free tier. The one free thing is the help-center article \"Sharing feedback, evaluation and fine-tuning data, and API inputs and outputs with OpenAI\", which answers 403 to this repository's fetches and, as quoted by the developer forum and the third-party guides that cite it, says some organizations may qualify for daily complimentary tokens on traffic shared with OpenAI, that eligibility is shown only inside the organization's data-sharing settings, that the tokens are usable only with a positive account balance, and that the shared prompts and outputs are used for training. An offer decided per account on a page no probe can read, unlocked by a prepaid balance and paid for with the prompts, is not a quota this list can publish.",
      "reopen_if": "OpenAI states the eligibility rule and the daily amounts on a public page, or opens a free tier that needs no balance.",
      "current": true
    },
    {
      "domains": [
        "anthropic.com",
        "claude.com"
      ],
      "name": "Anthropic Claude API",
      "checked_on": "2026-09-05",
      "reason": "claude.com/pricing (read 2026-09-05) prices the API per token from \"$1 / MTok\" on Haiku 4.5 to \"$10 / MTok\" on Fable 5.1 and names no free tier, trial credit or free model; the only free line is operational — code execution has \"50 free hours of usage daily per organization\" — and \"Save 50% with batch processing\" is a discount. Two of the lists read still link console.anthropic.com as a source of trial credits; the page no longer carries one.",
      "reopen_if": "A free tier, free model or signup credit on the pricing page.",
      "current": true
    },
    {
      "domains": [
        "kimi.ai",
        "moonshot.ai",
        "moonshot.cn"
      ],
      "name": "Kimi Open Platform (Moonshot AI)",
      "checked_on": "2026-09-05",
      "reason": "The API platform behind the Kimi models, one row over from the Kimi For Coding membership already here. Its recharge-and-limits page (platform.kimi.ai/docs/pricing/limits, read 2026-09-05) opens with \"you need to recharge at least $1 to start using, and when your cumulative recharge reaches $5, you will receive a\" voucher, and adds that \"Vouchers do not count towards the cumulative recharge total\"; Tier0, the $1 tier, is 1 concurrent request, 3 RPM, 500,000 TPM and 1,500,000 TPD. No free balance, no free model, and the China platform (platform.moonshot.cn) is the same shape in yuan. platform.moonshot.ai now redirects to platform.kimi.ai, so all three apexes are here.",
      "reopen_if": "A signup balance or a free tier with a figure on the pricing page.",
      "current": true
    },
    {
      "domains": [
        "minimax.io",
        "minimaxi.com"
      ],
      "name": "MiniMax Open Platform",
      "checked_on": "2026-09-05",
      "reason": "minimax.io/price and platform.minimax.io/docs (read 2026-09-05) price MiniMax M3, M2.7 and M2.5 per token and sell Token Plans from $10 a month; no free tier or signup grant is on any vendor page read, while the third-party guides that credit new accounts with trial credits also say the amount has shifted across promotions and is only visible on the dashboard after activation. An amount the vendor does not print is not a quota this list can carry. The free music APIs (Music-3.0-free, Music-2.6-free, music-cover-free) were discontinued from 2026-08-20 by the vendor's own notice.",
      "reopen_if": "A signup grant or free lane with a figure on a vendor page.",
      "current": true
    },
    {
      "domains": [
        "relace.ai"
      ],
      "name": "Relace",
      "checked_on": "2026-09-05",
      "reason": "Code-edit models (apply, merge, search, rerank) that a Chinese list carries as a free API. relace.ai/pricing (read 2026-09-05) prices every one per million tokens — $1.00 / $3.00 on Repos, Jacq and relace-search, $0.80 / $1.20 on relace-apply-3, $0.05 in on relace-rank — and names no free tier, credit or plan.",
      "reopen_if": "A free plan or signup credit with a figure on the pricing page.",
      "current": true
    },
    {
      "domains": [
        "ppio.com",
        "ppinfra.com"
      ],
      "name": "PPIO (PPInfra)",
      "checked_on": "2026-09-05",
      "reason": "ppio.com/pricing (read 2026-09-05) is a metered rate card in yuan — DeepSeek V3.2 ¥2 / ¥3 per million tokens, Qwen3.8 Flash ¥0.8 / ¥2.7, GLM 5.3 Flash ¥0.8 / ¥2.8, Kimi K2 ¥4 / ¥16 — with GPU spot discounts and a 50% batch-inference offer; no free quota, signup grant or free model is on it, and the sign-up is a mainland flow.",
      "reopen_if": "A free quota with a figure on a vendor page.",
      "current": true
    },
    {
      "domains": [
        "ncompass.tech"
      ],
      "name": "nCompass",
      "checked_on": "2026-09-05",
      "reason": "A Chinese list carries it as a free LLM API. On 2026-09-05 the site renders as \"nCompass — GPU performance engineering for opencode\" and its pricing page carries no API rate card and no free tier — the inference product the list remembers is not what the site sells now.",
      "reopen_if": "An inference API with a free tier appears on the site.",
      "current": true
    },
    {
      "domains": [
        "streamlake.com"
      ],
      "name": "StreamLake (Kuaishou 万擎)",
      "checked_on": "2026-09-05",
      "reason": "Kuaishou's AI cloud, named by two Chinese lists. The home page (read 2026-09-05) sells KAT-Coder-Pro V2.5 and DeepSeek V4 Flash 0731 behind API/SDK access and offers only a student discount campaign — \"高校师生专属｜模型定制低至5折\", to 2026-09-15, for mainland, Hong Kong, Macau and Taiwan faculty and students — with no free quota anywhere on it; the console is a login page.",
      "reopen_if": "A free quota with a figure on a readable page.",
      "current": true
    },
    {
      "domains": [
        "mancer.tech"
      ],
      "name": "Mancer",
      "checked_on": "2026-09-05",
      "reason": "Honest and OpenAI-compatible by URL swap — its FAQ says \"We offer free models, use them to test before making a purchase\" — and the models page (read 2026-09-05) marks exactly one row FREE: MythoLite, a LLaMA-2 13B roleplay tune with a 2,560-token context and a 150-token output cap. Every coding-tagged row beside it (DeepSeek V4 Flash, GLM 4.7, GPT OSS 120B and 20B) is metered in credits. A free lane that cannot finish a function is not one a coding agent can use.",
      "reopen_if": "A coding-capable model marked FREE on the models page.",
      "current": true
    },
    {
      "domains": [
        "empero.org"
      ],
      "name": "Empero (free.empero.org)",
      "checked_on": "2026-09-05",
      "reason": "\"A free community endpoint\" for GLM 5.3 Flash from an \"Independent AI research lab\" that says it is \"built in Germany\", with weights on Hugging Face under empero-ai. On 2026-09-05 free.empero.org is a maintenance page — \"We are switching the free endpoint to new models\" and \"We are preparing the free endpoint for Qwen3.8-Flash-Next\" — and no terms, rate limit, sign-up or catalog page could be read. Nothing here says how it is hosted or funded.",
      "reopen_if": "The endpoint answers and a page states its limits and terms.",
      "current": true
    },
    {
      "domains": [
        "awanllm.com"
      ],
      "name": "AwanLLM",
      "checked_on": "2026-09-05",
      "reason": "The pricing page (read 2026-09-05) still sells a Lite plan \"Free forever\" — \"20 req/minute\", \"200 req/day\" on small models, \"10 req/day\" on large ones, \"Unlimited Tokens!\" — over a catalog that stopped in 2024 (Llama 3 and 3.1, 8B and 70B). api.awanllm.com timed out on every call that day, catalog and chat alike, at 40 seconds, so the offer cannot be shown to answer, and a plan whose API does not respond is not one this list can verify twice a week.",
      "reopen_if": "api.awanllm.com answers a request.",
      "current": true
    },
    {
      "domains": [
        "kluster.ai"
      ],
      "name": "kluster.ai",
      "checked_on": "2026-09-05",
      "reason": "Still linked by two of the lists read on 2026-09-05. None of kluster.ai, platform.kluster.ai or api.kluster.ai resolves in DNS that day, and the last read of its successor lists recorded the API sunset as 2026-06-09.",
      "reopen_if": "The domain resolves and a page carries a free tier.",
      "current": true
    },
    {
      "domains": [
        "mlvoca.com"
      ],
      "name": "mlvoca",
      "checked_on": "2026-09-17",
      "reason": "The vendor's own repository, github.com/mlvoca/free-llm-api, now names the models and the terms: \"a publicly hosted /api/generate endpoint based on the Ollama API\" serving TinyLlama and DeepSeek R1 (1.5b), which \"currently works without any kind of rate limit or API key\", and \"Commercial use of this api is not allowed\". It names no operator beyond a Proton Mail address, and mlvoca.com still answers 403 to every fetch (2026-09-17). There is nothing here a probe can anchor on that dies with the offer — a README outlives the endpoint it describes — and the endpoint speaks Ollama's generate route rather than chat completions, so the keyless check cannot call it either.",
      "reopen_if": "mlvoca.com serves a readable page about the endpoint, or the service answers an OpenAI-compatible chat completions route.",
      "current": true
    },
    {
      "domains": [
        "b.ai"
      ],
      "name": "B.AI",
      "checked_on": "2026-09-05",
      "reason": "A Chinese list credits it with an anonymous, limited-time free lane at \"0 Credits\" with no end date. The site (b.ai and b.ai/pricing, read 2026-09-05) renders the word BAI and nothing else server-side, 2,841 bytes, so who operates it, what it serves and on what terms cannot be read.",
      "reopen_if": "A server-rendered page with the models, the limits and the operator.",
      "current": true
    },
    {
      "domains": [
        "developer.amd.com.cn"
      ],
      "name": "AMD Token Factory (China developer site)",
      "checked_on": "2026-09-05",
      "reason": "A Chinese list credits it with a daily $10-equivalent quota on AMD-hosted open models, OpenAI-compatible, no card, run with ZZ.ai and limited-time. The page at /radeon/tokenfactory is client-rendered: the readable part (2026-09-05) is a help notice for the \"AMD AI 开发者计划\", the Developer Cloud and a joint ModelScope incentive program, with no quota, model, endpoint or sign-up term in it. The domain is AMD's China developer site.",
      "reopen_if": "A server-rendered page with the quota and the sign-up terms.",
      "current": true
    },
    {
      "domains": [
        "bigmodel.cn"
      ],
      "name": "Zhipu BigModel (China console of Z.ai)",
      "checked_on": "2026-09-05",
      "reason": "The mainland console of the vendor this list carries as Z.ai, named by five of the lists read on 2026-09-05 (one of them: \"永久免费, 仅限速\" — permanently free, rate-limited only — on the GLM Flash models). The same Flash models are the listed row's free lane at api.z.ai, and what the China console adds is a mainland account whose sign-up this list cannot read. Here so the console stops being proposed as a second vendor.",
      "reopen_if": "A readable sign-up page for non-mainland accounts, or a free model the international site does not carry.",
      "current": true
    },
    {
      "domains": [
        "qianfan.baidubce.com",
        "cloud.baidu.com"
      ],
      "name": "Baidu Qianfan (百度千帆)",
      "checked_on": "2026-09-05",
      "reason": "The new-user quota is documented at cloud.baidu.com/doc/qianfan/s/Imi2rpirg (updated 2025-11-17, read 2026-09-05): from 2025-10-24, a user who has \"阅读并同意用户协议\" is granted \"100万\" tokens per model with \"3个月\" validity on 17 models — ERNIE-4.5-Turbo and ERNIE-X1-Turbo, DeepSeek-R1 and V3.1, Kimi-K2-Instruct, Qwen3-Coder-480B-A35B-Instruct among them — for online inference only. A one-off three-month grant is a trial rather than a standing lane, and the page says nothing about who may open the account; Baidu AI Cloud's sign-up is the mainland real-name flow this list cannot read, beside Alibaba's China site for the same reason.",
      "reopen_if": "A readable page saying the console opens without mainland real-name verification, or an international console carrying the grant.",
      "current": true
    },
    {
      "domains": [
        "volcengine.com",
        "volces.com"
      ],
      "name": "Volcengine Ark (火山方舟)",
      "checked_on": "2026-09-05",
      "reason": "Named by two Chinese lists for its 协作奖励计划, the data-collaboration reward. The program page (docs.volcengine.com/docs/82379/1391869, updated 2026-08-31) is client-rendered and came back empty to this repository's fetch on 2026-09-05; what could be read is the vendor's 2025-11-20 notice as quoted by nodeseek and linux.do — the reward for individual users rose \"由原本每日每模型的50万免费tokens奖励提升至200万\", granted as a next-day rebate of what was consumed, for accounts that pass real-name verification and authorize their prompts and outputs for model training — and a 2026-09-01 notice that 38 models left the program. A mainland real-name account and a training authorization are two walls this list does not carry, and the page that would say so is unreadable.",
      "reopen_if": "A server-rendered program page, and a sign-up readable outside the mainland.",
      "current": true
    },
    {
      "domains": [
        "wandb.ai"
      ],
      "name": "W&B Inference (Weights & Biases)",
      "checked_on": "2026-09-05",
      "reason": "A third-party dataset reports \"$100/month of Serverless Inference credits on the Free plan\". The vendor's usage-limits page (read 2026-09-05) says instead that \"Serverless Inference credits come with Free, Pro, and Academic plans for a limited time\" — no amount, no expiry — and lists \"$100/month\" as the Free tier's default spending cap on pay-as-you-go, which a free account must turn on once the credits are gone. The per-model price list (DeepSeek V4 Flash $0.14 / $0.28, Qwen3 Coder 480B $1.00 / $1.50 per million) carries no free row, and the service is \"only available from supported geographic locations\" under CoreWeave's terms.",
      "reopen_if": "A stated credit amount, or a model priced 0.",
      "current": true
    },
    {
      "domains": [
        "pioneer.ai"
      ],
      "name": "Pioneer (Fastino Labs)",
      "checked_on": "2026-09-11",
      "reason": "\"An inference API built by Fastino Labs\", surfaced by the provider table of mnfst/llm-gateway. Every model on the home page is priced per token — Claude Sonnet 5 at $2.00 / $10.00, GPT-5.5 at $5.00 / $30.00, Gemma 4 12B at $0.25 / $0.25, GLiNER2 Large at $0.20 / $0.20 per 1M — and pioneer.ai/pricing sells seats: \"PRO $20/seat/month, $40/seat/month in platform credits included\", Enterprise $50/seat. No signup credit and no free lane on either page as rendered here on 2026-09-11; the only \"trial\" in the page text is the name of its web font.",
      "reopen_if": "pioneer.ai/pricing states a free tier or a signup credit.",
      "current": true
    },
    {
      "domains": [
        "zerolimitai.com"
      ],
      "name": "ZeroLimitAI",
      "checked_on": "2026-09-11",
      "reason": "The product behind ClawLabsAI/free-ai-models, whose README funnels readers to \"one OpenAI-compatible endpoint that auto-routes every request to whichever free model is answering best\". zerolimitai.com/developers does hand out a key — \"OpenAI-compatible · Free tier\", base URL https://www.zerolimitai.com/api/v1, model \"auto\" — but the free key \"expires after 7 days\" and carries no stated quota; the paid tiers are \"Lifetime Core $49 one-time … 2,000 API calls/day\" and \"Lifetime Pro $99 … 10,000 API calls/day\", sold beside \"Unlimited chat\". What the key routes to is \"the best free AI model available — Llama 4 Scout, DeepSeek R1, Qwen3 235B\", the models other vendors serve on their own free lanes, and neither /terms nor /about says where those requests go or under what licence; /docs answers 404. A relay reselling lifetime access to upstream free lanes is the provenance question llm7.io was blocked over, but the models here are open-weight and the operator publishes terms and a named team, so it stays a verdict rather than a block. Read 2026-09-11.",
      "reopen_if": "It publishes the free key's quota and where its \"free models\" are served from.",
      "current": true
    },
    {
      "domains": [
        "allrouter.ai"
      ],
      "name": "AllRouter",
      "checked_on": "2026-09-11",
      "reason": "Named by cuihuan/awesome-ai-gateway's relay watch-list as carrying \"a free GLM/Gemma tier\". allrouter.ai and /pricing are a 2 KB client-rendered shell, /docs is readable (23 KB) and holds no \"free\" wording at all, and api.allrouter.ai does not resolve (2026-09-11). Unreadable rather than absent.",
      "reopen_if": "A page this repository can read states the free tier.",
      "current": true
    },
    {
      "domains": [
        "aimlapi.com"
      ],
      "name": "AIMLAPI",
      "checked_on": "2026-09-16",
      "reason": "\"The Free Tier is currently paused\" (docs.aimlapi.com/faq/free-tier, 2026-09-16), though the marketing pages still offer \"Free credits on signup\".",
      "reopen_if": "The free tier resumes, with its quota stated.",
      "current": true
    },
    {
      "domains": [
        "byteplus.com",
        "bytepluses.com"
      ],
      "name": "BytePlus ModelArk",
      "checked_on": "2026-09-16",
      "reason": "A one-off trial, readable now in the docs' page data: ModelArk has a mode in which \"calls to the inference API consume only the 500k free tokens granted by the platform\", and the campaign terms grant \"500,000 (Five Hundred Thousand) tokens per Model\", \"redeemable only once per BytePlus account\", after \"BytePlus account registration and enterprise information submission\". Sign-up has you \"select one of the options as your payment method\", and no page read says the tokens can be spent before one is added (2026-09-16).",
      "reopen_if": "A page says the free tokens need no payment method, or the grant recurs.",
      "current": true
    },
    {
      "domains": [
        "clarifai.com"
      ],
      "name": "Clarifai",
      "checked_on": "2026-09-12",
      "reason": "The one text-LLM row of pacocartones/free-llm-api-hub left without a verdict here, because nothing under the domain answers. clarifai.com and www.clarifai.com time out on 443 and on 80 alike — from this network on 2026-09-05, 2026-09-11 and 2026-09-12, and from a GitHub runner on 2026-09-12, which is what takes a local block off the table — while api.clarifai.com, docs.clarifai.com, status.clarifai.com and portal.clarifai.com every one answer NXDOMAIN on Google's public resolver. The domain's nameservers are dns1 and dns2 at registrar-servers.com, the registrar's own default pair, and www resolves into static.rcn.com. A platform whose API subdomain does not exist in DNS cannot be verified to offer anything, which is the rule that settled Coze and Morph LLM. It is here and not on the blocklist because none of this is a verdict on the company.",
      "reopen_if": "clarifai.com or api.clarifai.com answers an ordinary HTTP client again, and the page it serves states the free tier.",
      "current": true
    },
    {
      "domains": [
        "aider.chat"
      ],
      "name": "aider",
      "checked_on": "2026-09-14",
      "reason": "Moved here from the blocklist, where it sat as \"BYOK-only, no bundled free model usage\". That is true of aider and it is still a verdict on an offer, not on the tool — Cline sat on the blocklist under the same words for two months while its own provider handed out free models, because nothing on that list ever comes up for a re-check. aider ships no provider of its own: its model docs send readers to other vendors' free tiers — \"Aider works with a number of free API providers: OpenRouter offers free access to many models, with limitations on daily usage\", Gemini beside it — which this list carries directly. The repository was last pushed on 2026-05-22.",
      "reopen_if": "aider ships a hosted provider or a sign-in of its own that includes model usage.",
      "current": true
    },
    {
      "domains": [
        "roomote.dev"
      ],
      "name": "Roomote",
      "checked_on": "2026-09-14",
      "reason": "Moved here from the blocklist for the reason aider was: BYOK-only describes what is offered today, not the company. Roomote is the cloud coding agent the Roo Code team shut Roo Code down to build, and it bundles no inference — \"Every plan includes app hosting and a sandbox provider — you just bring an inference key from any provider we support\". What is free is the hosting: \"a free 7-day trial, no credit card\" on Roomote Cloud, then from $49/mo, and self-hosting that \"is free for up to 10 users\". Neither buys a token.",
      "reopen_if": "A Roomote plan, trial or self-hosted tier includes model usage instead of asking for an inference key.",
      "current": true
    },
    {
      "domains": [
        "puter.com"
      ],
      "name": "Puter",
      "checked_on": "2026-09-14",
      "reason": "Moved here from the blocklist, where it sat as a browser-only SDK with no HTTP endpoint a coding agent could use. That stopped being true: Puter now serves an OpenAI-compatible endpoint at api.puter.com/puterai/openai/v1 and an Anthropic-compatible one at api.puter.com/puterai/anthropic, with its own tutorials for Claude Code, Cline and Kilo Code, and \"every Puter account includes an allowance of storage, database, and AI usage at no charge\". The two do not meet. Its rate-limits page says the compatible endpoints \"additionally require a paid plan — a free account calling them gets 402 subscription_required\", while the free allowance runs through puter.ai.* and /drivers/call, which no coding agent speaks, and the size of that allowance is shown only in the dashboard. The site's \"Free, Unlimited Claude API\" tutorials are the marketing half of the same site, not what its docs describe.",
      "reopen_if": "A free Puter account can call the OpenAI- or Anthropic-compatible endpoint without a paid plan.",
      "current": true
    },
    {
      "domains": [
        "zoocode.dev"
      ],
      "name": "Zoo Code",
      "checked_on": "2026-09-14",
      "reason": "The community fork that carried on when Roo Code shut down, and the one Roo Code's own shutdown notice recommends. Its release notes invite users to take the Zoo Gateway key \"to any OpenAI-compatible client or workflow\", but the gateway is prepaid — the terms read \"Zoo Code credits are prepaid units\" and \"Minimum purchase amount is $5 USD\", non-refundable, and name no company. The public catalog behind zoocode.dev/models serves 251 models at Vercel AI Gateway's own rates plus a ninth (minimax/minimax-m3 at $0.3333/$1.3333 against Vercel's $0.30/$1.20), and the seven it prices at zero are exactly Vercel's seven — the Ling 3.0 Flash Fin, Sante and VL ids and laguna-s-2.1-free — already on this list under Vercel AI Gateway. The v3.82.0 release notes promise \"free access to MiniMax-M3 through Zoo Gateway\" for a limited time while the same catalog prices it, and no page says an account without credits can call anything. Read 2026-09-14.",
      "reopen_if": "Zoo's docs or terms state that an account without purchased credits can call Zoo Gateway models, or MiniMax-M3 appears at zero in its public catalog.",
      "current": true
    },
    {
      "domains": [
        "fastrouter.ai"
      ],
      "name": "FastRouter",
      "checked_on": "2026-09-14",
      "reason": "Operated by AI.tech Ltd under New York law, with a real :free lane in a keyless catalog — openai/gpt-oss-120b:free, openai/gpt-oss-20b:free, google/gemma4-26b:free, nvidia/nemotron-3-nano-30b:free, nvidia/nemotron-3-super:free and sarvam/sarvam-105b:free, all priced 0 — that a new account cannot use. Its own docs set the gate: \"up to 10 requests per org per day, with no payment required for organizations having paid credit balance >$1\", and \"Free models cannot be used when your organization's paid credit balance is <= $1\". The signup grant the site advertises — \"Get Millions Of Tokens To Start. Free Credits On Us\" — carries no figure, and the $0 Starter plan is a gateway plan for your own keys (\"1 BYOK key · 1M requests / month\").",
      "reopen_if": "The :free models answer an account that has never paid, or the signup credit is published as a figure.",
      "current": true
    },
    {
      "domains": [
        "naga.ac"
      ],
      "name": "NagaAI",
      "checked_on": "2026-09-14",
      "reason": "The free tier is published — \"Start free on zero-cost models\", 15+ models at 10 RPM and 100 RPD — and what it serves is other gateways' free lanes: the :free ids in its keyless catalog are ling-3.0-flash-vl:free, ling-3.0-flash-sante:free, ling-3.0-flash-fin:free, nex-n2.5-pro:free, nex-n2.5-mini:free, dots-3-note-preview:free, lfm-2.5-2.6b:free and nemotron-3.5-lightning:free, the lane OpenRouter and Kilo already carry here. The paid catalog prices frontier models well under their makers' rates — gpt-5.6-sol at $1/$5 per 1M against OpenAI's $4/$20, claude-sonnet-5 at $1/$5 — with no statement of where they are served from.",
      "reopen_if": "NagaAI's free lane carries a model it serves itself, or it states where its below-list frontier capacity comes from.",
      "current": true
    },
    {
      "domains": [
        "commandcode.ai"
      ],
      "name": "Command Code",
      "checked_on": "2026-09-14",
      "reason": "A coding agent for open models whose cheapest plan is paid. The home page FAQ says \"Free tier for solo developers\", but the pricing page starts at \"Go $1 /month + processing fee\" with $10 of credits, then GOAT at $10/mo with $70. The free models it advertises — \"Free on Laguna S 2.1 Free on Ling 3.0 Flash Free on LongCat 2.0 Free on Ling 3.0 Flash Sante\", \"Requests cost no credits while capacity lasts\" — are listed inside those plans, not beside them.",
      "reopen_if": "Command Code offers a $0 plan with model usage included.",
      "current": true
    },
    {
      "domains": [
        "kimchi.dev"
      ],
      "name": "Kimchi (CAST AI)",
      "checked_on": "2026-09-14",
      "reason": "CAST AI's open-source coding agent. The $0 Community tier is the harness alone — \"Bring your own inference - Kimchi's managed API, an OpenAI-compatible endpoint, or any LLM provider. No hosted inference\" — and model usage starts on Coder at $20/mo, which \"Includes $25 monthly credits\". The \"no credit card\" on the home page is about installing the CLI.",
      "reopen_if": "The Community tier includes hosted inference or credits.",
      "current": true
    },
    {
      "domains": [
        "eurouter.ai"
      ],
      "name": "EUrouter",
      "checked_on": "2026-09-14",
      "reason": "An EU-compliance routing gateway whose Free plan prices the routing, not the tokens: \"Free €0 /mo Pay for what you use Monthly limit: 10K requests/month Rate limit: 60 RPM 15% markup\", and its keyless catalog prices every one of its 147 rows.",
      "reopen_if": "A model in the eurouter.ai catalog is priced at zero, or the Free plan includes token usage.",
      "current": true
    },
    {
      "domains": [
        "featherless.ai"
      ],
      "name": "Featherless AI",
      "checked_on": "2026-09-14",
      "reason": "Subscriptions only: \"Chat For roleplay, stories and long conversations ... $25 /month\" and \"Developer For coding agents and API traffic ... $50 /credits per month\", over a catalog of 40,000+ open models every row of which is priced. OmniRoute lists it with a free tier and then corrects itself — the only free access is an application-gated builder programme.",
      "reopen_if": "Featherless publishes a free plan or a free model lane.",
      "current": true
    },
    {
      "domains": [
        "stepfun.com",
        "stepfun.ai"
      ],
      "name": "StepFun (阶跃星辰)",
      "checked_on": "2026-09-14",
      "reason": "Every model on platform.stepfun.com/docs/zh/guides/pricing/details is priced, and the page records its free lanes ending rather than starting: \"Step Audio R1.1 已升级为 Step Audio R1.5。该模型已结束限时免费\" (the limited-time free period is over) and \"step-2x-large 已于 2026 年 06 月 12 日 结束限时免费\" (ended on 2026-06-12). The home page sells the Step Plan coding subscription. Step 3.7 Flash is free through Kilo, which this list carries.",
      "reopen_if": "StepFun's pricing page shows a zero-priced model or a signup grant.",
      "current": true
    },
    {
      "domains": [
        "zyloai.net"
      ],
      "name": "Zylo AI",
      "checked_on": "2026-09-14",
      "reason": "The Basic plan is real — \"$0 /mo 7.2k req/day · 10/min 200k Daily Tokens Basic models only ... No credits\", no card — and it can only reach the rows priced at zero, since Basic carries no credits. Those rows, in the keyless catalog's BASIC tier, are nemotron-3-ultra, mistral-large-3 (675B), qwen-3.5 (397B), qwen-3.5-flash, mistral-small-4, gpt-oss-20b, step-3.7, diffusiongemma and llama-3.2-3b, plus Zylo's own routers — the models NVIDIA's API catalog serves free for development, handed out here under a gateway's free plan without a word on where they run. Terms on zyloai.net/terms cover only linked-account enforcement.",
      "reopen_if": "Zylo states where its zero-priced Basic models are served from, or the Basic plan covers a model it serves itself.",
      "current": true
    },
    {
      "domains": [
        "speka.me"
      ],
      "name": "Speka",
      "checked_on": "2026-09-14",
      "reason": "A $1 monthly allowance with no card — \"Free $0.00 /mo ... $1 of model usage / month 10 requests / minute 1 API key Access to all open models\" — on a gateway that markets \"27 frontier models\" and serves seven from its keyless catalog: nemotron-3-ultra, nemotron-3-super, gpt-oss-20b, laguna-xs-2.1, llama-3.2-11b-vision, flux.1-dev and an embedder, ids spelled the way NVIDIA's API catalog spells them. Prices sit above the makers' (DeepSeek V4 Flash at $0.27/$1.10), which is not the relay pattern, but the terms (June 2026) name no company and nothing says whose capacity the allowance spends.",
      "reopen_if": "Speka names its operator and where its models are served, and the catalog carries what the home page claims.",
      "current": true
    },
    {
      "domains": [
        "logfare.ai"
      ],
      "name": "Logfare",
      "checked_on": "2026-09-14",
      "reason": "\"Free LLM Inference. No Limits\", with the price stated plainly — \"In exchange for free inference, we log every request — prompts, completions, and metadata. After PII scrubbing this may be used in our private, internal evaluation datasets\" — and an operator described only as \"an independent research and engineering group\"; /terms and /about answer 404, and the privacy policy names no company. The keyless catalog is 19 ids, and 14 of them — glm-5.3, kimi-k2.6, qwen-3.8-27b, gemma-4-26b, melotts, aura-2-en, nova-3, lucid-origin, phoenix-1.0 and the flux and whisper builds — are Cloudflare Workers AI's names, whose free allocation is 10,000 neurons a day per account. Unlimited free use of it is either paid for by someone unnamed or pooled.",
      "reopen_if": "Logfare publishes terms naming its operator and a stated quota, or says how the inference is paid for.",
      "current": true
    },
    {
      "domains": [
        "openadapter.dev",
        "openadapter.in"
      ],
      "name": "OpenAdapter",
      "checked_on": "2026-09-14",
      "reason": "OpenAdapter, Inc. sells a coding subscription — \"4x Cheaper than Claude Code\", Lite at $9/mo for \"~400 requests over 5h\" — across 72+ open models, and does have a free plan: \"Try OpenAdapter Strict daily quota across the full catalog. No credit card.\" The quota is never given a number, and the pitch is resale on its own words: \"Same models. Fraction of the price. One subscription replaces 3+ separate provider plans\", beside an \"0G Network\" section of privately hosted models. Nothing says which provider plans are being replaced, or under what licence.",
      "reopen_if": "OpenAdapter publishes the free plan's daily quota and where its models are served from.",
      "current": true
    },
    {
      "domains": [
        "free.ai"
      ],
      "name": "Free.ai",
      "checked_on": "2026-09-14",
      "reason": "A consumer suite of 477+ tools whose free allowance is real and small in the way that matters here: \"Anonymous users get 6,000 tokens/day. Sign up free for 30,000 tokens/day\", spent on \"Qwen 2.5 for chat\" — 2024-era 7B to 72B models on its own GPUs — while \"GPT-6, Claude, Veo + 584 premium models\" start at $5. The API sits at api.free.ai/v1/chat/ with ids like qwen7b rather than a model a coding agent would be pointed at.",
      "reopen_if": "The free daily allowance covers a current coding model on the API.",
      "current": true
    },
    {
      "domains": [
        "greenpt.com",
        "greenpt.ai"
      ],
      "name": "GreenPT",
      "checked_on": "2026-09-14",
      "reason": "EU-hosted chat on renewable energy, where the free part is a trial and the API is paid: \"All API usage requires an active Pro, Teams, or API-only subscription\", every plan comes \"with a 14-day free trial included\", and the entry plan is €4,50/month for 15 prompts a day.",
      "reopen_if": "GreenPT's API gets a free allowance outside the subscription trial.",
      "current": true
    },
    {
      "domains": [
        "synthetic.new"
      ],
      "name": "Synthetic",
      "checked_on": "2026-09-14",
      "reason": "A flat subscription for open models — \"Subscription Packs ... $1 /day $30 /mo Rate Limit 500 requests/5hr\" — with the alternative \"All models are pay-per-token\". No free plan or grant on the pricing page.",
      "reopen_if": "Synthetic offers a free plan or signup allowance.",
      "current": true
    },
    {
      "domains": [
        "nlpcloud.com",
        "nlpcloud.io"
      ],
      "name": "NLP Cloud",
      "checked_on": "2026-09-14",
      "reason": "OmniRoute's changelog says the free tier \"is a recurring monthly free plan (10,000 requests/month)\", and nothing on the vendor's side can be read to confirm it: nlpcloud.com/pricing answers a Cloudflare \"Just a moment... Enable JavaScript and cookies to continue\" challenge from this network and from a GitHub runner alike (2026-09-14), and api.nlpcloud.io/v1/models is a 404. The same OmniRoute file marks its terms \"avoid\" for proxy use.",
      "reopen_if": "A pricing or docs page an ordinary HTTP client can read states the free plan.",
      "current": true
    },
    {
      "domains": [
        "baichuan-ai.com"
      ],
      "name": "Baichuan (百川)",
      "checked_on": "2026-09-14",
      "reason": "A mainland console with nothing readable: platform.baichuan-ai.com renders 108 characters, and api.baichuan-ai.com/v1/models answers api_key_empty. OmniRoute's own correction is that \"current reality is only a one-time 80 CNY trial credit for new users (valid 3 months)\" — a trial, and on the same mainland-registration terms that keep the other Chinese consoles off this list.",
      "reopen_if": "A readable page states the grant and a registration open outside the mainland.",
      "current": true
    },
    {
      "domains": [
        "gitlawb.com"
      ],
      "name": "gitlawb",
      "checked_on": "2026-09-14",
      "reason": "A crypto-native agent platform — \"Sponsored tips funded with USDC\", spending permissions \"on a Base wallet\" — whose opengateway catalog prices 13 of its 14 ids and zeroes one, nvidia/nemotron-3-ultra-550b-a55b:free, a model this list already carries free on five rows. OmniRoute's note is that its free MiMo access \"was removed in May 2026\" and the Nemotron row is \"a temporary promotional model\".",
      "reopen_if": "gitlawb publishes a free lane of its own beyond one promotional id.",
      "current": true
    },
    {
      "domains": [
        "monsterapi.ai"
      ],
      "name": "MonsterAPI",
      "checked_on": "2026-09-14",
      "reason": "Unreachable: monsterapi.ai and api.monsterapi.ai both answer SERVFAIL on Google's public resolver (2026-09-14), so no page or catalog can be read. The free tier OmniRoute last described was one-time trial credits with \"0 credits/month\" recurring.",
      "reopen_if": "The domain resolves again and a readable page states a free allowance.",
      "current": true
    },
    {
      "domains": [
        "ampcode.com"
      ],
      "name": "Amp",
      "checked_on": "2026-09-14",
      "reason": "Free today only with inference you bring. The Hobby tier announced on 2026-09-13 is \"Free\" with \"Use your ChatGPT sub & other subs\", \"Bring your own keys (BYOK)\" and \"Pay-as-you-go for orbs\", and the announcement says it outright: \"Amp is now free to use when you bring your own compute and model subscriptions/keys ... You can still pay for model inference through Amp if you want, with no markup.\" The bundled lane Amp was known for is gone: its 2025-10-15 Amp Free post now opens \"Update 4: Amp Free is paused. We don't intend to bring it back\", after the ad-funded $10 a day of 2026-01-08 and \"Amp Free Is Full (For Now)\" on 2026-02-10.",
      "reopen_if": "Amp brings back a free credit grant or a free mode that needs no subscription or key of your own.",
      "current": true
    },
    {
      "domains": [
        "factory.ai"
      ],
      "name": "Factory (Droid)",
      "checked_on": "2026-09-14",
      "reason": "No free plan. Individual plans start at \"Pro $20 / mo\", then Plus at $100 and Max at $200, and the free-sounding parts are inside them: \"Droid Core: free open-weight model pool with separate Rate Limits after Standard Usage runs out\" and \"BYOK is free up to an allowance on all Individual plans\" both describe what a subscription includes (docs.factory.ai/pricing/individuals).",
      "reopen_if": "Factory offers a $0 plan whose Droid Core or other model usage needs no subscription.",
      "current": true
    },
    {
      "domains": [
        "openhands.dev",
        "all-hands.dev"
      ],
      "name": "OpenHands Cloud",
      "checked_on": "2026-09-14",
      "reason": "The free hosted tier bundles no model usage: \"Individual Free — Bring your own key or use our providers at-cost\", ten conversations a day, and the FAQ spells out the second half — \"the OpenHands LLM provider (available within the Individual Tier), which provides multiple model options at cost, with no markup on a pay-as-you-go basis\". The agent is hosted free; the inference is yours to pay for or bring, the aider case.",
      "reopen_if": "OpenHands Cloud includes model credits or a free model on its Individual tier.",
      "current": true
    },
    {
      "domains": [
        "dev.meta.ai",
        "api.meta.ai",
        "developer.meta.com"
      ],
      "name": "Meta Model API (Muse Spark, Muse Code)",
      "checked_on": "2026-09-14",
      "reason": "Pay-as-you-go behind a card. dev.meta.ai/docs/pricing-rate-limits.md prices muse-spark-1.3 at $1.25/$4.25 per 1M and its Contributor tier — the model Cline's free lane carries as cline-free/muse-spark-1.3-contributor — at $0.10/$0.20, \"Heavily discounted token pricing in exchange for permission to use your prompts and completions to train future Meta models\". The help center's sign-up article: \"To start making requests, set up two more things: Add a payment method ... Create an API key.\" The docs mention \"platform free-tier credits\" with no figure; the only figure is in the site config shipped with every docs page for the dashboard's welcome dialog, \"You have $20 in free credits to start building right away\" — a one-off grant on the far side of that card. Meta's own cookbook README still says \"the preview is free\", the pricing page being the later word. Muse Code, the terminal agent on the same account, is billed per token or sold as monthly subscriptions. The help center renders only in a browser; the docs are readable as Markdown.",
      "reopen_if": "An account can make requests without a payment method, or a docs page states the free-tier credit as a figure.",
      "current": true
    },
    {
      "domains": [
        "qwenlm.github.io"
      ],
      "name": "Qwen Code (Qwen OAuth)",
      "checked_on": "2026-09-14",
      "reason": "The sign-in that made Qwen Code a free agent is gone, in its own docs: \"The Qwen OAuth free tier was discontinued on 2026-04-15. Existing cached tokens may continue working briefly, but new requests will be rejected.\" The /auth menu now offers Alibaba Cloud's Coding Plan (\"weekly quota included\", for a fixed monthly fee), a Token Plan, a Model Studio API key or a third-party key, which leaves a BYOK agent. Alibaba's free Model Studio quota is carried here as a row of its own.",
      "reopen_if": "Qwen Code's auth menu offers a sign-in with a free quota again.",
      "current": true
    },
    {
      "domains": [
        "sweep.dev"
      ],
      "name": "Sweep (JetBrains plugin)",
      "checked_on": "2026-09-14",
      "reason": "A one-off trial on Sweep's own models with nothing readable about its terms. sweep.dev/pricing offers \"Free Trial Free Try Sweep risk-free 1,000 Autocompletes $5 API credits included\", then Basic at $10 a month for unlimited autocomplete, Pro at $20 and Ultra at $60. The documentation it links answers HTTP 402 (docs.sweep.dev, 2026-09-14) and its terms and blog URLs serve the home page, so neither the trial's conditions nor whether it takes a card can be read.",
      "reopen_if": "Sweep publishes the trial's terms on a page that answers, card or no card, or adds a recurring free allowance.",
      "current": true
    },
    {
      "domains": [
        "lingyiwanwu.com"
      ],
      "name": "01.AI (Yi API)",
      "checked_on": "2026-09-16",
      "reason": "01.AI closed its model API: api.lingyiwanwu.com answers GET /v1/models with HTTP 410 {\"error\":{\"code\":\"model_service_closed\",\"message\":\"Model service has been discontinued\"}}. The company is alive on the same domain — www.lingyiwanwu.com announces \"2026.07 万策平台发布\", an enterprise decision platform — so the offer ended, not the service. It sat on the blocklist from 2026-09-14 as a product that was gone, which would have buried a vendor that can reopen an API. OmniRoute's feed still names its \"Yi-Light\" free models.",
      "reopen_if": "api.lingyiwanwu.com/v1/models serves models again, or 01.AI publishes API pricing with a free allowance.",
      "current": true
    },
    {
      "domains": [
        "cerebras.ai"
      ],
      "name": "Cerebras Inference",
      "checked_on": "2026-09-16",
      "reason": "Listed from 2026-07-19 to 2026-09-16 as a trial marked with a card, and taken off because CONTRIBUTING excludes one-off credits that require one. inference-docs.cerebras.ai/support/rate-limits: \"New accounts receive $5 in free credits after adding a verified payment method. These credits expire 30 days after they’re granted\", \"If you skip adding a payment method at sign-up, Playground and API access remain inactive until you do\", and \"Is there a permanently free tier? No.\"",
      "reopen_if": "Cerebras grants credits without a payment method, or a free allowance that recurs.",
      "current": true
    },
    {
      "domains": [
        "infomaniak.com"
      ],
      "name": "Infomaniak AI Services",
      "checked_on": "2026-09-16",
      "reason": "Listed from 2026-09-02 to 2026-09-16 as a trial marked with a card, and taken off because CONTRIBUTING excludes one-off credits that require one: \"One million free credits allow you to test the service without commitment for one month\" and \"A credit card is required to start using the API\" (support guide 2845).",
      "reopen_if": "The trial credits stop requiring a card, or a free allowance recurs.",
      "current": true
    },
    {
      "domains": [
        "scaleway.com"
      ],
      "name": "Scaleway Generative APIs",
      "checked_on": "2026-09-16",
      "reason": "Listed from 2026-07-20 to 2026-09-16 as a free tier marked with a card, and taken off because CONTRIBUTING excludes one-off credits that require one. \"Every new customer gets 1,000,000 free tokens—start paying only from the 1,000,001st token\" is a once-per-customer grant, and Scaleway's account docs say \"Ordering Scaleway resources requires a valid credit card\".",
      "reopen_if": "The free tokens stop requiring a card, or become a recurring allowance.",
      "current": true
    },
    {
      "domains": [
        "aiberm.com",
        "aiberm.org"
      ],
      "name": "Aiberm",
      "checked_on": "2026-09-16",
      "reason": "A paid relay with nothing free found and no cause shown. It sat on the blocklist from 2026-09-14 on its own discount claim (\"85–90% off Claude, 90% off GPT\"), and a price is not provenance. Its FAQ separates \"claude-\" models, discounted and \"best suited for coding scenarios\", from \"anthropic/\" models \"Routed through AWS\", without saying where the first kind come from. aiberm.org is its mainland mirror.",
      "reopen_if": "Aiberm offers a free allowance, or states where its discounted Claude capacity comes from.",
      "current": true
    },
    {
      "domains": [
        "aki.io"
      ],
      "name": "AKI.IO",
      "checked_on": "2026-09-17",
      "reason": "A European inference API hosted in Germany whose free user account gets trial credit with no card — \"Business and professional users can create a free user account and receive trial credit for API evaluation. Depending on the models used, this covers millions of tokens. No credit card is required, and the trial does not automatically convert into a paid service.\" — but no page gives the credit a figure or the trial a length. The terms say only that \"The trial period ends as specified on the website when applying for the trial period\", and that the service \"is reserved for entrepreneurs\" acting in a trade, business or profession, with a company account (register number and VAT ID) needed once the trial ends. A credit with no figure gives a probe nothing that ends with it, the Baseten case.",
      "reopen_if": "AKI.IO publishes the size or the length of the trial credit on a readable page.",
      "current": true
    },
    {
      "domains": [
        "runinfra.ai"
      ],
      "name": "RunInfra",
      "checked_on": "2026-09-17",
      "reason": "Hosted model APIs on a prepaid balance, with a one-off dollar: the docs say \"Signing up is free and grants $1 once per account\" and the pricing page \"New accounts start with $1 free to test the Model APIs\", top-ups starting at $10 after that. A one-off credit is listed here when it asks for no card, and neither page, nor the pricing FAQ, says whether this one can be spent before a payment method is added (2026-09-17).",
      "reopen_if": "A RunInfra page says the $1 is spent without a payment method on file.",
      "current": true
    },
    {
      "domains": [
        "koscompute.com"
      ],
      "name": "Kosmik Compute",
      "checked_on": "2026-09-17",
      "reason": "A Prague-hosted API whose one chat model is Qwen3.8 27B, beside Whisper and text-to-speech models, offering \"€10 in free credits when you sign up to try our API for free\". Nothing on the home page or on any page its docs index lists says whether a card is needed before the credit is spent — the question that decides a one-off credit here, as it does on SiliconFlow.",
      "reopen_if": "A Kosmik page says the €10 is spent without a payment method on file.",
      "current": true
    },
    {
      "domains": [
        "modelishub.com"
      ],
      "name": "Modelis",
      "checked_on": "2026-09-17",
      "reason": "An OpenAI-compatible gateway whose free tier is a RapidAPI listing: modelishub.com/pricing says \"Subscribe on RapidAPI (free tier, no card to start)\", and the listing's BASIC plan is $0 with a hard limit of 100 requests a month. The same listing says tools and function calling are not supported on current plans and \"Output is capped at 1024 tokens\" — a lane that cannot call a tool cannot drive a coding agent, the AI Horde case.",
      "reopen_if": "The free plan accepts tool definitions and allows more than 100 requests a month.",
      "current": true
    },
    {
      "domains": [
        "trustedrouter.com"
      ],
      "name": "TrustedRouter",
      "checked_on": "2026-09-17",
      "reason": "The keyless catalog prices trustedrouter/free, a routing pool, at 0 — beside orchestration aliases that also read 0 — but the pricing page bills every route: \"Pay the provider price plus 5.5%, with no monthly plan\", and \"Prepaid text and embedding prices are provider cost + 5.5%, with a $0.01 per million token floor\", paid from prepaid credits, BYOK or usage-based billing. Its only credits are migration credits for \"Teams already spending more than $100/month on LLMs\", by approval.",
      "reopen_if": "TrustedRouter exempts trustedrouter/free from the floor or publishes a free allowance.",
      "current": true
    },
    {
      "domains": [
        "umans.ai"
      ],
      "name": "Umans AI (Umans Code)",
      "checked_on": "2026-09-17",
      "reason": "Open coding models on the vendor's own GPUs, paid from a wallet: \"A wallet with no credit at all — no paid top-up, no active promo grant — does not serve until it has some\", the first rate tier unlocks at \"Your first top-up\", and promo credit such as the founders' bonus serves only while it lasts. The keyless catalog prices one id at 0, umans-deepseek-v4.1-flash-lab, which the docs never name; the one lab they describe, DeepSeek V4 Pro, \"served here as a seat-gated pre-release lab\". models.dev also lists an Umans AI Coding Plan at cost 0, and the docs speak of plans only as archived plans.",
      "reopen_if": "Umans serves an account with no top-up, or documents a zero-priced model any account can call.",
      "current": true
    },
    {
      "domains": [
        "intelligence.io.solutions",
        "io.net"
      ],
      "name": "IO Intelligence (io.net)",
      "checked_on": "2026-09-17",
      "reason": "The plans page gives the default Standard plan \"free, light daily access\", with pay-as-you-go beyond \"the daily limit\", and the table on the same page describes Standard as \"Continuous access with PAYG\" with \"No refreshes, pay only for what you use\". No figure for the free access appears on any page read. The keyless catalog prices all 35 rows and opens four to the lowest access tier — GLM-4.5-Air, Gemma 4 26B A4B, gpt-oss-20b and Llama 3.3 70B — the rest needing a higher one.",
      "reopen_if": "io.net publishes the Standard plan's daily free allowance with a figure.",
      "current": true
    },
    {
      "domains": [
        "qiniu.com",
        "qnaigc.com"
      ],
      "name": "Qiniu AI inference (七牛云)",
      "checked_on": "2026-09-17",
      "reason": "New AI-inference users get a one-time package — 注册有奖活动：现在注册 qiniu.com/ai 开发者账号，立即获得 300万免费 Token 资源包, three million tokens counted at DeepSeek-V3.1's input price — issued after the first billed usage (使用服务并产生计费后自动发放). Two walls keep it off. The API FAQ says 目前AI产品仅支持中国大陆账号使用，暂不支持海外账号 — the AI products take mainland-China accounts only, not overseas ones — and a new user has a 24-hour grace period (24 小时免认证体验期) before real-name verification is required: the mainland real-name account this list does not carry, as for Baidu Qianfan and Volcengine.",
      "reopen_if": "Qiniu opens AI inference to accounts outside mainland China without real-name verification.",
      "current": true
    },
    {
      "domains": [
        "iteracompute.com"
      ],
      "name": "IteraCompute",
      "checked_on": "2026-09-17",
      "reason": "Nine chat models priced per token in a keyless catalog that marks every row `is_free: false`; neither the home page nor the docs page names a free allowance, a trial or a signup credit (2026-09-17).",
      "reopen_if": "A row marked free in the catalog, or a signup credit with a figure on a vendor page.",
      "current": true
    },
    {
      "domains": [
        "edenai.co",
        "edenai.run"
      ],
      "name": "Eden AI",
      "checked_on": "2026-09-17",
      "reason": "A unified API whose keyless catalog prices 1,064 rows, a handful at 0 — google/gemma-4-31b-it, google/gemma-4-26b-a4b-it and cohere/command-a-plus-05-2026 among them — while billing is a credit system: \"Eden AI uses a pay-per-use credit system\", credits are bought with a 5.5% platform fee, and the pricing page names no signup credit. Whether a zero-priced row answers an account with no credit is stated on no page read, the question NanoGPT's record turns on.",
      "reopen_if": "Eden AI's docs say zero-priced models run on an empty balance, or a signup credit is named.",
      "current": true
    },
    {
      "domains": [
        "vultrinference.com"
      ],
      "name": "Vultr Serverless Inference",
      "checked_on": "2026-09-17",
      "reason": "A paid subscription: the docs provision \"a Vultr Serverless Inference subscription\" before a key exists, and neither they nor the API reference at api.vultrinference.com name a free allowance. vultr.com's pricing pages answer 403 to a script (2026-09-17); the keyless catalog lists 16 models.",
      "reopen_if": "Vultr publishes a free inference allowance that needs no subscription.",
      "current": true
    },
    {
      "domains": [
        "wallabytoken.com"
      ],
      "name": "Wallaby",
      "checked_on": "2026-09-17",
      "reason": "Kimi K3 on a prepaid balance — \"Top up — prepaid USD, from $20\" — from Wallaby Data Pty Ltd in Australia. The terms mention a trial no page quantifies: \"new accounts may receive promotional trial credit\", which \"may be restricted to specific models and lower rate limits\".",
      "reopen_if": "Wallaby publishes a trial credit with a figure.",
      "current": true
    },
    {
      "domains": [
        "vivgrid.com"
      ],
      "name": "Vivgrid",
      "checked_on": "2026-09-17",
      "reason": "The Free plan is a platform tier rather than an allowance — \"$0 to start Pay-as-you-go model usage\" — and the credits on offer are the Growth plan's \"$25 in token credits included every month\", at $25 a month, and \"$200/mo credits available to approved open-source maintainers on request\", a grant by approval rather than a tier anyone can use. The operator is Allegro US, LLC.",
      "reopen_if": "The Free plan includes model usage with a figure.",
      "current": true
    },
    {
      "domains": [
        "nan.builders"
      ],
      "name": "NaN (nan.builders)",
      "checked_on": "2026-09-17",
      "reason": "A paid membership, not a free tier: \"A closed community of builders sharing dedicated GPUs to run open models. Every member pays to be here\", paid by \"Credit or debit card\", with a waitlist for spots. models.dev lists its seven models at cost 0 because the price is the flat subscription; the monthly token allowances per member are what it buys.",
      "reopen_if": "NaN offers a membership or an allowance at no charge.",
      "current": true
    },
    {
      "domains": [
        "ebcloud.com",
        "ebtech.com"
      ],
      "name": "EBCloud (英博云)",
      "checked_on": "2026-09-17",
      "reason": "The model API spends purchased compute points — 在正式使用模型API服务前，需先购买算力点。算力点购买仅支持通过英博云账户现金余额进行支付 — bought before the first call and only from cash balance, on an account that has done 注册和实名认证, registration and real-name verification. The ¥20 the home page gives for registering and verifying (注册认证送20元无门槛代金券) is a voucher, where the points are bought with cash balance only.",
      "reopen_if": "The model API accepts vouchers or offers a free allowance, without real-name verification.",
      "current": true
    },
    {
      "domains": [
        "berget.ai"
      ],
      "name": "Berget.AI",
      "checked_on": "2026-09-17",
      "reason": "A Swedish inference API whose Trial plan has \"€5 free starting credits\", but the pricing FAQ puts a card in front of them: \"The Trial plan includes €5 in starting credits so you can try the API without a subscription — a card is required at signup to prevent abuse, but nothing is charged.\" After the credit, \"an active plan (from €25 / month in prepaid credits) is required for continued API access\". One-off credits behind a card are what CONTRIBUTING excludes.",
      "reopen_if": "The €5 is granted without a card, or a free allowance recurs without a plan.",
      "current": true
    },
    {
      "domains": [
        "cloudferro.com"
      ],
      "name": "CloudFerro Sherlock",
      "checked_on": "2026-09-17",
      "reason": "Sherlock, CloudFerro's model API, is billed per token — \"Our pricing model is based on token usage - both input (received) and output (generated) tokens for each model\" — and \"To use Sherlock’s API, you have to be an admin user of an Organization registered at CloudFerro\", an organization that needs an EU VAT number or tax ID. The cloud's free trial (\"We grant up to 250 EUR for testing purposes within our infrastructure\") is not said on any page read to reach Sherlock tokens.",
      "reopen_if": "A CloudFerro page says the trial credits pay for Sherlock, without a card or a company tax ID.",
      "current": true
    },
    {
      "domains": [
        "crusoe.ai",
        "crusoecloud.com"
      ],
      "name": "Crusoe",
      "checked_on": "2026-09-17",
      "reason": "The pricing page offers \"$5 in free credits\" to \"Fine-tune and serve models in Crusoe Intelligence Foundry\", while managed inference is pay-as-you-go per million tokens, and the account docs put a card in front of both: \"To provision resources or use the managed inference service, you must enable billing on your account. You will need a valid, non-prepaid credit card to proceed.\"",
      "reopen_if": "The $5 can be spent on inference before a card is added.",
      "current": true
    },
    {
      "domains": [
        "digitalocean.com",
        "do-ai.run"
      ],
      "name": "DigitalOcean Serverless Inference",
      "checked_on": "2026-09-17",
      "reason": "A new team gets a signup credit — \"When you create your first team, DigitalOcean automatically applies a $5 signup credit\" and \"Signup credits expire 90 days after signup\" — but a payment method comes first (\"You must add a valid payment method before you can create Droplets or other resources\"), and \"Serverless inference is prepaid only. You must maintain a positive prepaid account balance to send serverless inference requests\". Whether the signup credit counts toward that balance is not stated.",
      "reopen_if": "DigitalOcean documents the signup credit paying for serverless inference with no payment method on file.",
      "current": true
    },
    {
      "domains": [
        "evroc.com"
      ],
      "name": "evroc Think",
      "checked_on": "2026-09-17",
      "reason": "evroc's shared models are billed per token, and two posts from September 2026 offer a campaign: \"For the first 100 signups, we are offering €300 credits to help you get a started building on evroc and using evroc Think.\" The sign-up form's own script saves a card before the account exists — \"Save Payment Method (€0 charge)\" — and the billing docs say \"At least one card must remain on your account\". A first-100 grant behind a card is excluded twice over.",
      "reopen_if": "evroc offers credits that are claimed without saving a card.",
      "current": true
    },
    {
      "domains": [
        "gmicloud.ai",
        "gmi-serving.com"
      ],
      "name": "GMI Cloud (Inference Engine)",
      "checked_on": "2026-09-17",
      "reason": "Serverless models are paid from bought credit, their prices kept in the console (\"Rather than mirror prices here (where they would go stale), the up-to-date rates live in the console\"), and usage tiers follow purchases — \"Please note that voucher redemptions do not count towards purchase\". No page read names a signup credit or a zero-priced model; the GMI Router's free model selection routes to paid models.",
      "reopen_if": "GMI publishes a signup credit or a zero-priced serverless model.",
      "current": true
    },
    {
      "domains": [
        "inceptron.io"
      ],
      "name": "Inceptron",
      "checked_on": "2026-09-17",
      "reason": "\"Only pay for what you run. Simple, transparent, and built for real usage. No hidden fees.\" — six serverless models, every one priced in the keyless catalog, plus dedicated GPUs from $3 an hour with commitment discounts; no free tier, trial credit or zero price on any page read.",
      "reopen_if": "A signup credit or a zero-priced model on an Inceptron page or catalog.",
      "current": true
    },
    {
      "domains": [
        "inco.ai"
      ],
      "name": "Inco",
      "checked_on": "2026-09-17",
      "reason": "A prepaid, per-token API behind a waitlist: \"Access is prepaid. Credit is consumed per token at the rates shown at the time of each request. Requests are rejected when your balance reaches zero.\" The terms also say \"Inco is an experimental prototype.\" No starting credit is named.",
      "reopen_if": "Inco grants starting credit at sign-up.",
      "current": true
    },
    {
      "domains": [
        "jalapeno-cloud.ai"
      ],
      "name": "Jalapeno Cloud",
      "checked_on": "2026-09-17",
      "reason": "The offer exists only in the site's JavaScript, and the same scripts disagree with it. The pricing page's script says \"Flexible token pricing, high usage limits, and postpaid billing—plus $1 in free credits to get you started!\", a partner campaign's says \"Sign in to get $1 in free credits instantly.\", and the home page's quick start says \"Top up your account with credits to enable API calls.\" Every one of the 20 models in the keyless catalog is priced. The operator named in the recharge agreement is Magik Compute Technology (Shanghai) Co., Ltd.",
      "reopen_if": "A server-rendered Jalapeno page states the $1 grant and that it is spent without a top-up.",
      "current": true
    },
    {
      "domains": [
        "klokintegration.se",
        "ipaas.se"
      ],
      "name": "Klok AI-API (klokintegration.se)",
      "checked_on": "2026-09-17",
      "reason": "A Swedish integration company's model API, currently DeepSeek V4 Flash behind the name Kloker: \"Usage is billed per million tokens, excl. VAT. Input is €0.20. Output is €1.\", with keys by request — \"Not on the platform yet? Email klokintegration@integrera.com and ask for a token.\" The 30-day free trial on the home page belongs to its chat assistant, not the API.",
      "reopen_if": "Klok grants a free token allowance for the AI-API.",
      "current": true
    },
    {
      "domains": [
        "getlilac.com"
      ],
      "name": "Lilac",
      "checked_on": "2026-09-17",
      "reason": "Four open models on idle enterprise GPUs, per token from prepaid credits: \"You need a positive credit balance before you can make API requests.\" The personal subscriptions ($10, $30 and $100 a month) include usage worth $20, $75 and $300, all paid; no starting credit is named.",
      "reopen_if": "Lilac grants starting credit without a top-up.",
      "current": true
    },
    {
      "domains": [
        "lucidquery.com"
      ],
      "name": "LucidQuery",
      "checked_on": "2026-09-17",
      "reason": "A French lab's own models, AGI 01 Swift and Frontier, on a metered API — \"Metered usage, no monthly minimum. Pay only for the tokens your app sends and receives.\" Its $0 Free plan, \"A restrained entry into AGI 01, LucidArc, and LucidCode\", covers the vendor's own chat, desktop and CLI apps with unpublished limits (the CLI offers \"Connect with /login: free, subscription, or API key.\"), and nothing ties that plan to the API.",
      "reopen_if": "LucidQuery says the Free plan's allowance works through api.lucidquery.com with a key other clients can use.",
      "current": true
    },
    {
      "domains": [
        "melious.ai"
      ],
      "name": "Melious",
      "checked_on": "2026-09-17",
      "reason": "\"Access 60+ open-weight models on a pay-as-you-go basis. No commitments, no minimums. Just top up credits and go.\" The free Explorer plan in the pricing page's data carries a daily energy allowance for the vendor's studio but not API usage, and for plans like it the docs say \"API calls are `credits_only`, even if you have energy left\". The coding plans that do include API usage are paid and \"intended exclusively for businesses as defined by § 14 BGB\".",
      "reopen_if": "Melious lets the Explorer plan or a signup grant pay for API calls.",
      "current": true
    },
    {
      "domains": [
        "modeloracle.com"
      ],
      "name": "Model Oracle AI",
      "checked_on": "2026-09-17",
      "reason": "A gateway for coding agents billed from a balance: \"Prepaid usage with no subscription. Add prepaid usage balance with a card.\" Managed requests deduct the catalog provider cost and BYOK requests a 5% fee; no free allowance is named.",
      "reopen_if": "Model Oracle grants balance at sign-up without a card.",
      "current": true
    },
    {
      "domains": [
        "neosmith.ai"
      ],
      "name": "NeoSmith",
      "checked_on": "2026-09-17",
      "reason": "A router that distills small models from an agent's own traces, not an open lane: \"NeoSmith is currently free for design partners during early access\", and the self-serve route is a booked demo that ends with a pilot key — \"Walk away with a 14-day pilot key (no credit card)\". A key issued after a sales call is not an offer a reader can take.",
      "reopen_if": "NeoSmith issues keys with a free allowance through self-serve sign-up.",
      "current": true
    },
    {
      "domains": [
        "neuralwatt.com"
      ],
      "name": "Neuralwatt",
      "checked_on": "2026-09-17",
      "reason": "Energy-priced inference whose trial asks for a card first: the quick start says \"adding a payment method unlocks $1.00 in free trial credit (no charge required; the credit is valid for 30 days)\", and the pricing page \"Add a payment method to get $1.00 in free credits — no charge required — then add more when you need them.\"",
      "reopen_if": "The trial credit is granted without adding a payment method.",
      "current": true
    },
    {
      "domains": [
        "openreason.app"
      ],
      "name": "OpenReason",
      "checked_on": "2026-09-17",
      "reason": "Company AI sold per person to businesses, with a price still unset — \"We are not going to invent one to fill this page\" — and no plan for one developer: \"There is no single-seat plan and there will not be one.\" Its \"Free to try\" has no published terms.",
      "reopen_if": "Published trial terms that give an individual developer an API key with a free allowance.",
      "current": true
    },
    {
      "domains": [
        "routing.run"
      ],
      "name": "routing.run",
      "checked_on": "2026-09-17",
      "reason": "A membership router: \"Basic is $10/month and includes $10 in routing credit. Add more whenever you need it.\", and the API quick start requires \"An active Basic membership with a positive Routing balance\". Every row in the keyless catalog is priced.",
      "reopen_if": "A free tier or signup credit usable without the Basic membership.",
      "current": true
    },
    {
      "domains": [
        "302.ai"
      ],
      "name": "302.AI",
      "checked_on": "2026-09-17",
      "reason": "A pay-as-you-go aggregator — 302.AI采用0月费和按用量付费模式，先充值，后扣费 (no monthly fee, pay by usage: top up first, then it is deducted) — and \"The minimum recharge is $5 to use all AI products.\" A $1 test credit exists on paper with changing conditions: a help FAQ last modified 2024-11-07 gives it to every user who binds a phone, and a changelog entry of 2025-03-03 narrows it to 新用户只有填写邀请码才可以获得1美金测试额度 — only new users who enter an invite code; the referral-code page that entry links to answers 404.",
      "reopen_if": "A current 302.AI page grants new accounts API credit without an invite code or a top-up.",
      "current": true
    },
    {
      "domains": [
        "abacus.ai"
      ],
      "name": "Abacus.AI RouteLLM API",
      "checked_on": "2026-09-17",
      "reason": "The RouteLLM API comes with a subscription: \"Sign up as a ChatLLM subscriber to access RouteLLM API\", and \"A ChatLLM subscription is $10 per user per month. You will be billed $10 when you sign up.\" No free API access is named.",
      "reopen_if": "A RouteLLM API key is available to an unsubscribed account.",
      "current": true
    },
    {
      "domains": [
        "above.dev"
      ],
      "name": "above.dev",
      "checked_on": "2026-09-17",
      "reason": "A router sold in prepaid packs, with no account before payment: \"Buy a credit pack at https://above.dev/pricing ($10, $20 or $50). Checkout creates your account, emails your API key, and opens the dashboard for usage and balance history.\"",
      "reopen_if": "An account or key obtainable before checkout, with a stated free credit.",
      "current": true
    },
    {
      "domains": [
        "aiand.com"
      ],
      "name": "ai&",
      "checked_on": "2026-09-17",
      "reason": "Open models hosted in Japan on prepaid credit: \"ai& uses a prepaid credit model. You add credits to your organization, and inference requests deduct from that balance as they complete.\" Redemption codes add credit without a card, but \"Redemption codes are handed out at events, hackathons and workshops\". A cookbook page calls qwen/qwen3.6-27b \"free for prototyping\", while the keyless catalog prices it at $0.32 in and $3.20 out per million tokens (2026-09-17).",
      "reopen_if": "A zero-priced model in the keyless catalog, or a public signup credit.",
      "current": true
    },
    {
      "domains": [
        "aixy-gateway.com"
      ],
      "name": "Aixy",
      "checked_on": "2026-09-17",
      "reason": "A governance gateway over the customer's own provider credentials — \"Connect a provider, create a project API key, and call the gateway.\" — selling paid plans of its own, billed apart from inference: \"This page describes inference cost attribution, not the price of an Aixy subscription.\" It hosts no capacity to give away. The site answers 403 to scripts; its llms-full.txt is readable.",
      "reopen_if": "Aixy-hosted model capacity with a free allowance that needs no provider key of your own.",
      "current": true
    },
    {
      "domains": [
        "ambient.xyz"
      ],
      "name": "Ambient",
      "checked_on": "2026-09-17",
      "reason": "A verified-inference network whose API needs paid credit: \"The Anthropic-compatible endpoint requires paid credits, like the OpenAI-compatible one: on the free tier requests return `402`.\" Its cheapest plan is $1 a month — \"A small paid tier for trying Ambient.\" — and the keyless catalog prices all four models.",
      "reopen_if": "Ambient's free tier or its drops can make API calls that do not return 402.",
      "current": true
    },
    {
      "domains": [
        "auriko.ai"
      ],
      "name": "Auriko",
      "checked_on": "2026-09-17",
      "reason": "A router whose Free plan and \"14-day free trial. No credit card required.\" are platform tiers, with inference bought separately: \"Pro is a flat $89/mo subscription billed separately from inference costs. You purchase credits at provider token prices with zero markup. Credits work the same on Free and Pro.\" The keyless directory at api.auriko.ai/v1/directory/models prices five routes at 0, three to Z.ai and two to Google AI Studio, and no page says whether they answer an account with no credit.",
      "reopen_if": "Auriko documents its zero-priced routes answering an account with no purchased credit.",
      "current": true
    },
    {
      "domains": [
        "ant-ling.com",
        "tbox.cn"
      ],
      "name": "Ant Ling (Ant Group)",
      "checked_on": "2026-09-17",
      "reason": "A real daily quota behind an Alipay payment agreement. The pricing page: \"Each account receives 500,000 free tokens per day (shared across input and output). The quota resets daily at 2:00 AM UTC+8 and does not roll over.\", on Ling-3.0-flash, Ling-2.6-1T, Ling-2.6-flash and Ring-2.6-1T at 2 QPS. But \"Before your first API call, bind an Alipay account and activate the Ling service\", the FAQ adds \"You need to sign the Mini Program Cloud auto-debit agreement and activate the Ling model service\", and \"Only personal Alipay accounts are supported for payment.\" An auto-debit agreement is a payment method on file, and whether an Alipay account opened outside mainland China can sign it is stated on no page read. Ling 3.0 Flash variants are already free on rows this list carries. models.dev still lists the service as Bailing at api.tbox.cn.",
      "reopen_if": "The daily quota works without the auto-debit agreement, or a page says an Alipay account from outside mainland China can sign it.",
      "current": true
    },
    {
      "domains": [
        "claudin.io"
      ],
      "name": "Claudinio",
      "checked_on": "2026-09-17",
      "reason": "Flat-rate subscriptions for coding agents. The account docs say \"The first time you sign in, your account is created automatically on the Free plan, so you can try it before paying anything\", but no page gives the Free plan an allowance, and the API reference lists `402` \"No active subscription\". The site's source carries promotional strings for a signup credit and daily free credits that no rendered page shows.",
      "reopen_if": "A page states the Free plan's API allowance, or a signup or daily credit usable without a subscription.",
      "current": true
    },
    {
      "domains": [
        "coralbricks.ai"
      ],
      "name": "CoralBricks",
      "checked_on": "2026-09-17",
      "reason": "Gated by request: \"Coral Inference is currently a design-partner program. To get access, contact hello@coralbricks.ai.\", and ungranted accounts get `403 access_denied`. Usage is billed from a prepaid balance.",
      "reopen_if": "Open self-serve access with a stated free credit or free model.",
      "current": true
    },
    {
      "domains": [
        "crossmodel.ai"
      ],
      "name": "CrossModel",
      "checked_on": "2026-09-17",
      "reason": "\"Usage-based pricing, one unified bill, no subscriptions.\", funded by Stripe top-ups with a 5.5% service fee — \"There is no minimum fee — but the minimum top-up is $10.\" No signup credit or zero-priced model is named.",
      "reopen_if": "A signup credit or a zero-priced model on CrossModel's own pages.",
      "current": true
    },
    {
      "domains": [
        "dinference.com"
      ],
      "name": "DInference",
      "checked_on": "2026-09-17",
      "reason": "Open models hosted in Tokyo at per-token prices, with direct keys handed out on request and aimed at high-volume users; the site renders only in a browser, and no page names a free tier or credit (2026-09-17).",
      "reopen_if": "A self-serve key with a stated free allowance.",
      "current": true
    },
    {
      "domains": [
        "d.run"
      ],
      "name": "d.run (DaoCloud)",
      "checked_on": "2026-09-17",
      "reason": "A mainland platform whose token API is pay-as-you-go — MaaS by Token：使用 Token 计费，共享资源 — on an account that must pass real-name verification: 根据适用法律要求，您需要进行实名认证以使用我们的产品或服务。 The docs home still shows an undated \"DeepSeek free for two weeks\" banner with no terms behind it.",
      "reopen_if": "A dated, current page grants free token usage or a signup voucher without mainland real-name verification.",
      "current": true
    },
    {
      "domains": [
        "frogbot.ai"
      ],
      "name": "FrogBot",
      "checked_on": "2026-09-17",
      "reason": "API usage draws on a paid balance — \"Your subscription payments and added funds become a USD balance.\" — and in the plan table API access belongs to the $25 Pro plan; the Free plan's 300 credits a month cover the vendor's own agents and flows.",
      "reopen_if": "Free-plan credits can be spent through an API key.",
      "current": true
    },
    {
      "domains": [
        "infer.flow7.org"
      ],
      "name": "Infer by Flow7",
      "checked_on": "2026-09-17",
      "reason": "\"Infer by Flow7 provides public paid access. Anyone can create an account; email verification and wallet funding are required before metered API use.\" Accounts start at $0, every selector in the keyless catalog is priced, and \"Serving suppliers remain private.\"",
      "reopen_if": "A free wallet credit, or a zero-priced selector in the public catalog.",
      "current": true
    },
    {
      "domains": [
        "qhaigc.net"
      ],
      "name": "QuanHex (QiHang)",
      "checked_on": "2026-09-17",
      "reason": "A reseller gateway paid by Alipay top-ups from ¥10, with email verification; the only zero-priced entry in its pricing data is an internal test model (启航测试模型，不计费，仅用于测试 — a test model, not billed, for testing only). No registration bonus is named.",
      "reopen_if": "A registration bonus, or a zero-priced production model.",
      "current": true
    },
    {
      "domains": [
        "vancine.com"
      ],
      "name": "Vancine",
      "checked_on": "2026-09-17",
      "reason": "Free credit for new accounts ended on 2026-09-02: \"Effective immediately, newly registered users will no longer automatically receive complimentary API credits.\" Since then the only credit is a one-time bonus after a first top-up of at least $5, and no model is priced at 0.",
      "reopen_if": "The revised trial the 2026-09-02 announcement promises grants credit without a top-up.",
      "current": true
    },
    {
      "domains": [
        "salad.com",
        "salad.cloud"
      ],
      "name": "SaladCloud AI Gateway",
      "checked_on": "2026-09-17",
      "reason": "A gateway in early access, paid per token from a credit balance or by a monthly subscription arranged with support: \"The organization must have a positive credit balance before it can process AI Gateway requests.\" The pricing FAQ answers its own question about a free trial: \"No. SaladCloud and the Transcription API are pay-as-you-go with no minimum commitment\".",
      "reopen_if": "Salad grants new organizations credit, without a card, that the AI Gateway accepts.",
      "current": true
    },
    {
      "domains": [
        "sakana.ai"
      ],
      "name": "Sakana AI (Fugu)",
      "checked_on": "2026-09-17",
      "reason": "Paid subscriptions from $20 a month or pay-as-you-go credits — the terms read \"To use the Service, You must purchase credits that may be used within the Service\" — and \"we do not provide services to users in EU (European Union) or EEA (European Economic Area) member states\". The console's pricing page ships interface strings for a free usage allowance that no public page describes.",
      "reopen_if": "A public Sakana page states a free API allowance for accounts without a subscription.",
      "current": true
    },
    {
      "domains": [
        "scnet.cn"
      ],
      "name": "SCNet (超算互联网)",
      "checked_on": "2026-09-17",
      "reason": "China's national supercomputing marketplace runs a promotion from 2026-08-13 to 2026-10-13 whose new-user package is 1000万 token 量包 — ten million tokens of GLM-5-Base, valid 30 days — under 仅限活动期间新注册用户，每个账号限领1次。福利总量有限，先到先得 (new accounts only, once each, while supplies last). A base model is not what a coding agent runs, new accounts are told apart by phone number, ID-card number and payment account, and the API docs say API access may have to be opened through a business advisor (如有需要，可联系您的专属业务顾问或平台客服开通调用 API 权限). The Token Plan itself is a paid subscription for AI tools only.",
      "reopen_if": "A recurring or chat-model allowance that opens without mainland real-name verification.",
      "current": true
    },
    {
      "domains": [
        "kuaecloud.net",
        "mthreads.com"
      ],
      "name": "KUAE Cloud Coding Plan (Moore Threads)",
      "checked_on": "2026-09-17",
      "reason": "A GLM-4.7 coding plan with a 30-day free trial described as a promotion — 用户在推广活动期间可申请30天免费试用 — at about 40 prompts per five hours, and 套餐仅限于指定的编程工具中使用 (usable only in the listed coding tools). The claim page is client-rendered and answers \"please log in first\" to a script, and the launch page's own bundle limits the trial to 100 developers a day, so whether it can be claimed today, and with what account, cannot be read.",
      "reopen_if": "A readable page shows the trial open now, with a sign-up a reader outside mainland China can complete.",
      "current": true
    },
    {
      "domains": [
        "scx.ai"
      ],
      "name": "SCX.ai",
      "checked_on": "2026-09-17",
      "reason": "An Australian sovereign inference provider priced per token, with monthly plans in compute units from A$500; the site answers 403 to scripts and its rendered pricing and plan pages name no free tier, trial or credit (2026-09-17).",
      "reopen_if": "A sign-up credit or trial for new accounts on an SCX page.",
      "current": true
    },
    {
      "domains": [
        "stackit.com",
        "stackit.cloud",
        "onstackit.cloud"
      ],
      "name": "STACKIT AI Model Serving",
      "checked_on": "2026-09-17",
      "reason": "A free 30-day test by application, for companies: \"All registrations are manually checked by us. If you qualify, you will receive your personal token to use STACKIT AI Model Serving within 24 hours. The trial period ends automatically after 30 days.\" The request form requires a company name, and a customer account needs to \"Provide the company’s VAT ID and Commercial Register number.\"",
      "reopen_if": "Self-serve sign-up, without approval or a company, that grants a free token or credit.",
      "current": true
    },
    {
      "domains": [
        "subconscious.dev"
      ],
      "name": "Subconscious",
      "checked_on": "2026-09-17",
      "reason": "\"Usage based pricing or monthly plans to power your agents efficiently.\" — per-token credits from the dashboard or plans from $100 a month; no free plan or trial is named.",
      "reopen_if": "Free starting credits or a free plan on the pricing page or in the docs.",
      "current": true
    },
    {
      "domains": [
        "submodel.ai"
      ],
      "name": "Submodel (InstaGen)",
      "checked_on": "2026-09-17",
      "reason": "Per-token open models from a funded balance, and the FAQ rules out a trial in so many words: \"We don't currently offer refunds or trial credits due to the overhead of processing these requests.\"",
      "reopen_if": "Trial credits or zero-priced models in the InstaGen docs.",
      "current": true
    },
    {
      "domains": [
        "tensorx.ai"
      ],
      "name": "TensorX",
      "checked_on": "2026-09-17",
      "reason": "EU inference on prepaid credits bought by card, with no free tier: \"When your balance falls below $0.05, your account and API keys will be disabled.\"",
      "reopen_if": "A starting credit without payment, or a zero-priced model.",
      "current": true
    },
    {
      "domains": [
        "thinkingmachines.ai",
        "thinkingmachines.dev"
      ],
      "name": "Tinker (Thinking Machines)",
      "checked_on": "2026-09-17",
      "reason": "A fine-tuning API with sampling endpoints, billed by use — \"Tinker uses a pricing plan that reflects usage. All prices are in USD per million tokens.\" — whose serverless inference is a beta for Thinking Machines' own Inkling models; research grants are the only credit mentioned.",
      "reopen_if": "Free credits for new accounts without an application.",
      "current": true
    },
    {
      "domains": [
        "tinfoil.sh"
      ],
      "name": "Tinfoil",
      "checked_on": "2026-09-17",
      "reason": "Confidential inference whose API key comes after checkout: \"Complete the checkout by entering your payment details. You're only charged based on usage.\" Every model in the keyless catalog is priced.",
      "reopen_if": "A starting credit without payment details, or a zero-priced model.",
      "current": true
    },
    {
      "domains": [
        "tokengo.com"
      ],
      "name": "TokenGo",
      "checked_on": "2026-09-17",
      "reason": "\"TokenGO uses a pay-as-you-go model. You only pay for the tokens you actually consume, priced per million tokens.\", funded through Stripe before the first request; the \"Free\" row in its rate-limit table is a speed tier, not a balance.",
      "reopen_if": "A free balance at sign-up, or a public code that grants credit without payment.",
      "current": true
    },
    {
      "domains": [
        "vispark.in"
      ],
      "name": "Vispark Lab",
      "checked_on": "2026-09-17",
      "reason": "Three vision models paid in units bought in rupees — the app's own text is \"Buy units to continue — you'll return here after payment.\" — and priced in the keyless catalog; no free units are named.",
      "reopen_if": "Free units at sign-up, or a zero-priced model.",
      "current": true
    },
    {
      "domains": [
        "wafer.ai"
      ],
      "name": "Wafer",
      "checked_on": "2026-09-17",
      "reason": "\"Access Wafer models through an OpenAI-compatible API. Add credits, create an API key, and pay per token.\", or a paid Wafer Pass subscription. Its $500 of free credits belong to a startup program that begins with \"a 25-minute conversation with our team\".",
      "reopen_if": "Credits for any new account without an application, or a free Wafer Pass tier.",
      "current": true
    },
    {
      "domains": [
        "xpersona.co"
      ],
      "name": "Xpersona",
      "checked_on": "2026-09-17",
      "reason": "Paid entry only: \"Choose monthly capacity from $20—or try the API with $2 prepaid credits.\" Every priced model in the catalog is paid.",
      "reopen_if": "Credits granted without payment.",
      "current": true
    },
    {
      "domains": [
        "zenifra.com"
      ],
      "name": "Zenifra",
      "checked_on": "2026-09-17",
      "reason": "A Brazilian platform whose sign-up credit reaches its AI API with no card — \"Ao criar sua conta, você ganha R$30,00 em créditos automaticamente\" and \"Você não precisa ter cartão de crédito para começar\" (a new account gets R$30 of credit automatically; no credit card is needed to start), usable on AI (\"Os R$30,00 recebidos ao criar a conta também podem ser usados com a oferta de IA\") — but registration asks for a \"CPF ou CNPJ válido\" and \"residência no Brasil\", a Brazilian tax ID and residence: a national identity wall, like the mainland real-name accounts recorded above.",
      "reopen_if": "Zenifra opens registration without a Brazilian tax ID and residence.",
      "current": true
    },
    {
      "domains": [
        "tracerml.ai"
      ],
      "name": "Echo by Tracer",
      "checked_on": "2026-09-17",
      "reason": "A workspace API for agent runs rather than a chat endpoint — \"The workspace API has a saved-run contract; OpenAI Chat Completions SDK request fields do not apply.\" — paid from workspace credit or with your own provider key: \"No Tracer fee on the first $30,000/month in eligible usage per workspace with your own API key.\" One model in its public library, the anonymous Union Alpha preview, is flagged free, with its availability unstated.",
      "reopen_if": "A free credit for new workspaces, or a free model callable through the API without payment.",
      "current": true
    },
    {
      "domains": [
        "helicone.ai"
      ],
      "name": "Helicone AI Gateway",
      "checked_on": "2026-09-17",
      "reason": "The free Hobby plan's \"10,000 free requests\" are observability logs, not inference; the gateway serves models from bought credits or your own provider keys, and a call with neither fails — the error guide's case is \"No Helicone credits, no BYOK\".",
      "reopen_if": "Free inference credit for new accounts.",
      "current": true
    },
    {
      "domains": [
        "near.ai"
      ],
      "name": "NEAR AI Cloud",
      "checked_on": "2026-09-17",
      "reason": "Confidential inference on purchased credits (\"purchase credits based on your needs\"), every model in the keyless catalog priced. The one way in without a card is a stake: \"Stake NEAR to fund private inference and deploy always-on IronClaw agents. Credits scale with your stake. No credit card required.\" — credits paid by the staking rewards on tokens the reader must own.",
      "reopen_if": "Starting credits for new accounts without a purchase or a stake.",
      "current": true
    }
  ]
}