Free LLM APIs and coding agents arriving, changing and dying, as the twice-weekly probes see it. https://mvalentsev.github.io/awesome-free-ai-coding/feed.xml 2026-09-17T10:05:42Z freetier-radar tag:mvalentsev.github.io,2026:awesome-free-ai-coding/models/aihubmix/20260917T100542Z 2026-09-17T10:05:42Z

added glm-5.3, kimi-k3 · free models: glm-5.3, kimi-k3, glm-5, mimo-v2.5, north-mini-code, gpt-oss

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/added/amazon-q-developer/20260917T100542Z 2026-09-17T10:05:42Z

AWS's coding assistant in the IDE and the CLI; its perpetual Free Tier gives a Builder ID user 50 agentic requests a month

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/removed/cerebras-free/20260917T100542Z 2026-09-17T10:05:42Z

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

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/models/cline/20260917T100542Z 2026-09-17T10:05:42Z

dropped deepseek-v4-flash · free models: laguna-s-2.1

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/models/freebuff/20260917T100542Z 2026-09-17T10:05:42Z

added deepseek-v4.1-flash; dropped deepseek-v4-flash · free models: glm-5.3-flash, deepseek-v4.1-flash, gpt-5.6-luna, mimo-v2.5

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/removed/infomaniak-ai/20260917T100542Z 2026-09-17T10:05:42Z

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

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/removed/kenari/20260917T100542Z 2026-09-17T10:05:42Z

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

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/added/llm7/20260917T100542Z 2026-09-17T10:05:42Z

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

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/added/nous-portal/20260917T100542Z 2026-09-17T10:05:42Z

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 · free models: step-3.7-flash, laguna-s-2.1

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/models/opencode/20260917T100542Z 2026-09-17T10:05:42Z

added muse-spark-1.3-contributor; dropped muse-spark-1.2 · free models: big-pickle, mimo-v2.5, ling-3.0-flash-fin, nemotron-3-ultra, nemotron-3.5-lightning, muse-spark-1.3-contributor

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/models/routeway/20260917T100542Z 2026-09-17T10:05:42Z

added deepseek-v4-flash, minimax-m2.7 · free models: deepseek-v4-flash, minimax-m2.7, muse-glimmer-30b

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/models/sarvam/20260917T100542Z 2026-09-17T10:05:42Z

dropped deepseek-v4-flash, glm-5.3-flash · free models: sarvam-105b

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/removed/scaleway-generative/20260917T100542Z 2026-09-17T10:05:42Z

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

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/added/token-harbor/20260917T100542Z 2026-09-17T10:05:42Z

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 · free models: deepseek-v4.1-flash, mimo-v2.5

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/models/yolo-auto/20260917T100542Z 2026-09-17T10:05:42Z

added qwen3.8-flash; dropped qwen3.8 · free models: qwen3.8-flash

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/added/zed/20260917T100542Z 2026-09-17T10:05:42Z

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 · free models: gpt-5.6-luna

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/added/agnes-ai/20260914T104639Z 2026-09-14T10:46:39Z

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 · free models: agnes-3.0-flash, agnes-2.5-flash

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/added/cline/20260914T104639Z 2026-09-14T10:46:39Z

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 · free models: deepseek-v4-flash, laguna-s-2.1

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/added/jetbrains-ai/20260914T104639Z 2026-09-14T10:46:39Z

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

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/models/routeway/20260914T104639Z 2026-09-14T10:46:39Z

added muse-glimmer-30b · free models: muse-glimmer-30b

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/added/yolo-auto/20260914T104639Z 2026-09-14T10:46:39Z

One model, Qwen3.8-27B in FP8, served on the vendor's own flat-rate API for coding agents; the free plan is a small daily allowance with no card · free models: qwen3.8

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/models/alibaba-model-studio/20260912T080334Z 2026-09-12T08:03:34Z

added qwen3.8-max · free models: qwen3.8-max, qwen3-max, qwen3-coder

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/models/inception-labs/20260912T080334Z 2026-09-12T08:03:34Z

added mercury-2.5 · free models: mercury-2.5, mercury-2, mercury-edit-2

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/added/routerplex/20260912T080334Z 2026-09-12T08:03:34Z

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

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/models/google-ai-studio/20260910T095008Z 2026-09-10T09:50:08Z

added gemini-3.8-flash · free models: gemini-3.8-flash, gemini-3.7-flash, gemini-3.5-flash-lite, gemini-2.5-pro

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/models/groq-free/20260910T095008Z 2026-09-10T09:50:08Z

added qwen3.8; dropped llama-3.3 · free models: gpt-oss, qwen3.6, qwen3.8

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/models/llmtr/20260910T095008Z 2026-09-10T09:50:08Z

dropped mercury-2 · free models: nemotron-3-ultra, qwen3.6

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/models/ovh-ai-endpoints/20260910T095008Z 2026-09-10T09:50:08Z

added qwen3.8 · free models: gpt-oss, qwen3.6, qwen3.8, qwen3-coder

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/added/standardcompute/20260910T095008Z 2026-09-10T09:50:08Z

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

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/models/llmtr/20260907T102903Z 2026-09-07T10:29:03Z

dropped minimax-m3 · free models: nemotron-3-ultra, qwen3.6, mercury-2

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/archived/ai21-labs/20260907T102810Z 2026-09-07T10:28:10Z

vendor-announced shutdown on 2026-08-09

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/added/freeinference/20260907T102810Z 2026-09-07T10:28:10Z

Harvard SEAS's MadSys Lab serving frontier 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 · free models: deepseek-v4-flash, glm-5.1, glm-5.3-flash, minimax-m3, qwen3.6

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/added/ibm-watsonx-ai/20260907T102810Z 2026-09-07T10:28:10Z

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

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/added/opentyphoon/20260907T102810Z 2026-09-07T10:28:10Z

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

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/models/routeway/20260907T102810Z 2026-09-07T10:28:10Z

dropped gemma-4, gpt-oss

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/added/sarvam/20260907T102810Z 2026-09-07T10:28:10Z

India's Sarvam AI credits every new account ₹100 to spend on any of its APIs — its own Sarvam-105B chat model beside hosted DeepSeek V4 Flash, GLM 5.3 Flash and Gemma 4 — through an OpenAI-shaped chat endpoint · free models: sarvam-105b, deepseek-v4-flash, glm-5.3-flash

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/models/cerebras-free/20260903T213808Z 2026-09-03T21:38:08Z

added qwen3.8; dropped gemma-4 · free models: gpt-oss, qwen3.8

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/models/antigravity/20260903T213517Z 2026-09-03T21:35:17Z

added gemini-3.6-flash, gemini-3.7-flash, gemini-3.8-flash; dropped gemini-3.5-flash · free models: gemini-3.1-pro, gemini-3.8-flash, gemini-3.7-flash, gemini-3.6-flash, claude-opus-4.6, claude-sonnet-4.6, gpt-oss

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/models/kenari/20260903T213517Z 2026-09-03T21:35:17Z

dropped glm-4.7-flash · free models: nemotron-3-ultra, nemotron-3-super, step-3.7-flash, laguna-s-2.1

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/added/codebuddy/20260903T095524Z 2026-09-03T09:55:24Z

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

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/added/freebuff/20260903T095524Z 2026-09-03T09:55:24Z

Ad-funded coding agent in five surfaces — CLI, desktop, browser app builder, cloud sandbox on any GitHub repo, and chat — with no account, no API key and no card; GLM 5.3 Flash by default, with GPT-5.6 Luna, DeepSeek V4 Flash and MiMo 2.5 in the picker · free models: glm-5.3-flash, gpt-5.6-luna, deepseek-v4-flash, mimo-v2.5

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/added/infomaniak-ai/20260903T095524Z 2026-09-03T09:55:24Z

Swiss sovereign-cloud API over open-weight models with a one-month trial wallet of one million credits, one credit per LLM token

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/added/kenari/20260903T095524Z 2026-09-03T09:55:24Z

Indonesian OpenAI- and Anthropic-compatible gateway whose :free ids are billed Rp 0 behind a per-minute and a daily cap — twelve on 2026-09-02, GLM-4.7-Flash, Nemotron 3 Ultra, Hy3 and Mistral Medium 3.5 among them · free models: glm-4.7-flash, nemotron-3-ultra, nemotron-3-super, step-3.7-flash, laguna-s-2.1

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/added/llmtr/20260903T095524Z 2026-09-03T09:55:24Z

Turkish OpenAI-compatible gateway with a daily-quota free lane that answers on a zero balance — eleven zero-priced ids on 2026-09-02, MiniMax M3, Nemotron 3 Ultra, Qwen3.6 27B and Mercury 2 among them · free models: nemotron-3-ultra, minimax-m3, qwen3.6, mercury-2

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/added/meganova/20260903T095524Z 2026-09-03T09:55:24Z

OpenAI-compatible gateway whose no-card Tier 1 account gets a daily free quota on Mistral Small 3.2 and the house Manta routers — 50 a day per model, 550 across the lane · free models: mistral-small-3.2

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/added/qodo/20260903T095524Z 2026-09-03T09:55:24Z

Agentic PR code review plus Git and IDE integrations on a 14-day Pro Team trial with unlimited reviews and credits and no card

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/added/hetzner-inference/20260831T113939Z 2026-08-31T11:39:39Z

OpenAI-compatible API on Hetzner's own EU hardware, free for as long as the experiment runs · free models: qwen3.6, qwen3.8

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/models/opencode/20260831T113939Z 2026-08-31T11:39:39Z

added ling-3.0-flash-fin; dropped hy3 · free models: big-pickle, mimo-v2.5, ling-3.0-flash-fin, nemotron-3-ultra, nemotron-3.5-lightning, muse-spark-1.2

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/added/regolo/20260831T113939Z 2026-08-31T11:39:39Z

EU (Italian) zero-retention inference; a month of full model access on a daily token allowance, no card · free models: glm-5, gpt-oss, qwen3.8, llama-3.3, apertus-70b

tag:mvalentsev.github.io,2026:awesome-free-ai-coding/models/routeway/20260831T113939Z 2026-08-31T11:39:39Z

dropped llama-3.3, step-3.7-flash · free models: gpt-oss, gemma-4