awesome-free-ai-coding · every free model · every provider · filter the list
7 rows on the list serve nemotron-3-ultra free: opencode, OpenRouter (free models), Kilo Code, Requesty, NVIDIA NIM (build.nvidia.com), AIHubMix (free models) and LLMTR. None asks for a card; Kilo Code answers with no account at all. The providers’ last scheduled probes were on 2026-10-26; their offers are rechecked twice a week. It measures notable: in the upper half of the Artificial Analysis Intelligence Index, below its strong bar.
Every free model · the whole list
🤖 Coding agents & CLIs · no card · last probe 2026-10-26 · listed since 2026-07-19
Open-source coding agent whose opencode Zen gateway prices a rotating set of models at zero — inside OpenCode only, no sign-in; any provider via BYOK
Free models work only inside OpenCode; other clients receive 403 FreeTierError: OpenCode's free tier can only be used from within OpenCode. Use opencode/<model-id> and select the Free variant. Offers rotate; each named free offer is “available on OpenCode for a limited time”. Collected free-model data may improve models; NVIDIA offers are trial-only and exclude personal or confidential data. Flint 40B Free allows training and retains data for 30 days. Beam Free’s provider does not train on inputs and retains them for 30 days; its listed territorial exclusions include Russia.
🧭 Aggregators (one key, many providers) · no card · last probe 2026-10-26 · listed since 2026-07-19
One API key for a rotating set of :free model variants, open-weight and stealth models among them
1,000 requests/day per account (after 10 credits purchased all-time)
OpenRouter’s FAQ says its free models “have low rate limits” and “are usually not suitable for production use”, and its limits page warns that a negative credit balance can produce errors “including for free models” and that a 429 can come from the upstream provider rather than the platform (read 2026-09-27). The docs define the daily counter as “Free-model requests recorded so far in the current UTC day”. The higher daily ceiling is granted “starting one credit below the table’s threshold” to absorb rounding and top-up fees.
https://openrouter.ai/api/v1OPENROUTER_API_KEY — get one at https://openrouter.ai/settings/keysANTHROPIC_BASE_URL): https://openrouter.ai/apiconfigs/codex/openrouter-free.config.toml — copy it to ~/.codex/, then codex -p openrouter-free; set up on the lane by the vendor’s own page, https://openrouter.ai/docs/cookbook/coding-agents/codex-cli: “Configure Codex for OpenRouter”nvidia/nemotron-3-ultra-550b-a55b:free🤖 Coding agents & CLIs · no card · not offered in Iran, Syria, Cuba and 1 more place · last probe 2026-10-26 · listed since 2026-08-05
Open-source coding agent with an Auto Free mode and a keyless OpenAI-compatible gateway, alongside BYOK and local models
The free-model lineup rotates. Auto Free routes over the free models in the catalog’s autoRouting list. Other models use pay-as-you-go credits or a Kilo Pass subscription.
https://api.kilo.ai/api/gatewayconfigs/codex/kilo-code.config.toml — copy it to ~/.codex/, then codex -p kilo-code -m nvidia/nemotron-3-ultra-550b-a55b:freenvidia/nemotron-3-ultra-550b-a55b:free🧭 Aggregators (one key, many providers) · no card · last probe 2026-10-26 · listed since 2026-08-11
OpenAI-compatible router with free models beside a metered catalog, routing, caching and fallbacks
No credit card for the Free plan, which serves free models only. Routing, caching, fallbacks, spend tracking and EU data residency are included. Past the free allowance the same key moves to pay-as-you-go.
https://router.requesty.ai/v1REQUESTY_API_KEY — get one at https://app.requesty.ai/api-keysANTHROPIC_BASE_URL): https://router.requesty.ainvidia/nemotron-3-ultra-550b-a55b🔌 LLM APIs with free tier · no card · not offered in Russia, Pakistan, Bangladesh and 11 more places · last probe 2026-10-26 · listed since 2026-09-22
Free endpoints for the models build.nvidia.com marks “Free Endpoint”, open-weight models from several labs among them, called with a free NVIDIA Developer Program key at integrate.api.nvidia.com/v1 (OpenAI-compatible)
No card, but an API key requires an NVIDIA Developer Program account and phone verification in a supported country. Published ceilings can vary by model and traffic can cause throttling. Vendor forum reports describe new personal keys that can list models but receive 404 on chat calls; an issued key alone does not establish working inference. Model pages identify available and deprecated endpoints; copy current IDs from the catalog.
https://integrate.api.nvidia.com/v1NVIDIA_NIM_API_KEY — get one at https://build.nvidia.comnvidia/nemotron-3-ultra-550b-a55b🧭 Aggregators (one key, many providers) · no card · last probe 2026-10-26 · listed since 2026-09-24
OpenAI-compatible model gateway with zero-priced routes and an Anthropic-format endpoint for coding clients
xiaomi-mimo-v2.6-pro-free, coding-glm-5.3-flash-free, coding-glm-5.3-free, xiaomi-mimo-v2.6-flash-free, coding-glm-5.2-free, coding-kimi-k3-free, coding-glm-5.1-free, coding-minimax-m2.7-free, coding-glm-5-free, coding-glm-5-turbo-free, coding-minimax-m2.5-free500/day coding routes: 5 requests/minute; 500 requests/day; 1,000,000 tokens/day per account per model; for coding-minimax-m3-free, glm-4.7-flash-free, coding-glm-4.7-free, k2.6-code-preview-free, coding-minimax-m2.1-free, kimi-for-coding-free, coding-glm-4.6-free, coding-minimax-m2-free
Other free routes: Usage allowance: amount not published (period not published); scope not published; for agents-a1-free, intern-s2-free, dots-3-note-preview-free, lfm-2.5-2.6b-free, nemotron-3.5-lightning-free, nemotron-3-super-120b-a12b-free, nemotron-3-nano-omni-30b-a3b-reasoning-free, nemotron-3-ultra-550b-a55b-free, north-mini-code-free, laguna-xs-2.1-free, laguna-s-2.1-free, mimo-v2-flash-free
Gemma 4 free routes: Usage allowance: amount not published (period not published); scope not published; for gemma-4-26b-a4b-it-free, gemma-4-31b-it-free
Free IDs end in -free; paid twins are metered at list prices. The daily request and token caps are independent per account and model, rather than a pool to split across models. Published caps apply to their named model IDs; the remaining routes have no numerical budget published. Request limits and campaign durations apply to their named IDs. nemotron-3.5-content-safety-free is a classifier; the lfm-2.5-2.6b-free developer advises against agentic coding use.
https://aihubmix.com/v1AIHUBMIX_API_KEY — get one at https://aihubmix.com/tokenANTHROPIC_BASE_URL): https://aihubmix.comconfigs/codex/aihubmix.config.toml — copy it to ~/.codex/, then codex -p aihubmix -m nemotron-3-ultra-550b-a55b-free; set up on the lane by the vendor’s own page, https://docs.aihubmix.com/en/api/Codex-CLI: “Connect AIHubMix in Codex (CLI and desktop app)”nemotron-3-ultra-550b-a55b-free🧭 Aggregators (one key, many providers) · no card · last probe 2026-10-26 · listed since 2026-09-02
Turkish OpenAI-compatible gateway with free models on a zero balance and dated previews; some previews require a previous top-up
nvidia/nemotron-3-ultra-550b-a55b, nvidia/nemotron-3-super-120b-a12b, qwen/qwen3.8-27b-freeHeabsy Qwen3.8 27B: Daily usage allowance: amount not published per account; for heabsy/qwen3.8-27b-heabsy-free
Nemotron3.5 Super VL: Daily usage allowance: amount not published; scope not published; for nvidia/nemotron-3.5-super-vl-free
Jais 3 MoVA: 200,000 tokens/day per account per model (Input and output count together; lower first-day allowance for new accounts); for ifm/jais-3-mova-36b-a4b. 00:00’da (TSİ)
K2 Horizon: 200,000 tokens/day per account per model (Input, output and reasoning count together; lower first-day allowance for new accounts); for ifm/k2-horizon-375b-a23b. 00:00’da (TSİ)
MiniMax M3.1 Flash: 5,000,000 tokens/day per account per model; for minimax/minimax-m3.1-flash-free. 00:00’da (TSİ)
Shanghai AI Lab models: 500,000 tokens/day sharing scope disputed (Per model; model pages say per person, the guide says per account. Input, output and reasoning count; new accounts have a lower first-day allowance.); for internlm/intern-s2-free, internlm/atria-dawn-free, internlm/atria-dawn-preview-free, internlm/agents-a1-free, internlm/sage-a1.5-free. 00:00’da (TSİ)
Free chat rows can be called on a new account with zero balance before any top-up. Paid use is prepaid; an 8% margin applies once at top-up, not to model prices. Prompt and response bodies are not permanently written to the usage and billing database. Heabsy requires provider-specific data-transfer consent: “Heabsy models cannot be called until your account has granted the data-transfer consent for Heabsy”. Its stream is buffered until completion, and reasoning_effort is unsupported. For free Nemotron3.5 Super VL, inputs “may be retained by the provider and used to improve the model”. Shanghai AI Lab prompts and completions may be logged by the provider and used to improve models.
https://llmtr.com/v1LLMTR_API_KEY — get one at https://llmtr.com/dashboard/api-keysnvidia/nemotron-3-ultra-550b-a55bnemotron-3-nano-omni — free at OpenRouter (free models), Kilo Code, Requesty, NVIDIA NIM (build.nvidia.com), AIHubMix (free models) and TokenRouter (PaleBlueDot)nemotron-3.5-lightning — free at opencode, OpenRouter (free models), Kilo Code, Requesty, NVIDIA NIM (build.nvidia.com) and AIHubMix (free models)nemotron-3-super — free at Requesty and LLMTRnemotron-3-nano-30b — free at RequestyGenerated from registry.yaml on 2026-10-27 and re-verified twice a week; every free model on the list is at https://mvalentsev.github.io/awesome-free-ai-coding/models/, and the full list, the Atom feed and the machinery at https://github.com/mvalentsev/awesome-free-ai-coding.