awesome-free-ai-coding · every free model · every provider · filter the list
3 rows on the list serve qwen3.6 free: Hetzner Inference API, FreeInference (Harvard SEAS) and OVHcloud AI Endpoints. None asks for a card; OVHcloud AI Endpoints answers with no account at all. The providers’ last scheduled probes were on 2026-10-26; their offers are rechecked twice a week.
Every free model · the whole list
🔌 LLM APIs with free tier · no card · last probe 2026-10-26 · listed since 2026-08-30
OpenAI-compatible API on Hetzner’s own EU hardware, free for as long as the experiment runs
Free while the Inference API remains experimental; Hetzner says it will email advance notice of a change. Per-key request and token windows both apply, with HTTP 429 at a cap. No daily, monthly or lifetime cap or end date is published. The service is offered as is for experimental use, without guaranteed availability or backups. Minting a token needs a Hetzner account; payment verification can include a card charge or other routes.
https://inference.hetzner.com/api/v1HETZNER_INFERENCE_API_KEY — get one at https://experiments.hetzner.com/inferenceQwen/Qwen3.6-35B-A3B-FP8🔌 LLM APIs with free tier · no card · last probe 2026-10-26 · listed since 2026-09-05
Harvard SEAS’s MadSys Lab serving open models free to every account behind both an OpenAI-shaped and an Anthropic-shaped endpoint, with a documented Claude Code setup
No card. This is an experimental research service with capacity-dependent limits. Prompts and responses may be logged for research; sanitized content, usage statistics and routing metrics may be published or open-sourced. Only models marked Free accept a Free key; Pro catalog rows need a Pro-enabled key.
https://freeinference.org/v1FREEINFERENCE_API_KEY — get one at https://freeinference.orgANTHROPIC_BASE_URL): https://freeinference.org/anthropicqwen3.6-35b🔌 LLM APIs with free tier · no card · last probe 2026-10-26 · listed since 2026-08-19
EU-hosted serverless API for open models, with anonymous OpenAI-compatible access and no signup, key or card
The documentation attributes the anonymous cap to IP and model. Tests on 2026-09-24 instead observed callers sharing a model’s anonymous capacity, so its effective sharing scope remains disputed. Anonymous requests can receive 429 before a caller has spent the documented cap. Authenticated API keys are metered per token and use the paid project/model limits; they do not create a larger free allowance.
https://oai.endpoints.kepler.ai.cloud.ovh.net/v1Qwen3.6-27Bqwen3.6-27b — free at Alibaba Cloud Model Studio (DashScope, international)qwen3.6-35b-a3b — free at Alibaba Cloud Model Studio (DashScope, international)qwen3.6-plus — free at Alibaba Cloud Model Studio (DashScope, international)Generated 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.