🔌 LLM APIs with free tier · no card · provisional — added recently, two weeks of probes still to pass · live — last verified by a probe on 2026-09-17 · freeinference.org · back to the whole list
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
deepseek-v4-flash, glm-5.1, glm-5.3-flash, minimax-m3, qwen3.6
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
https://freeinference.org/v1FREEINFERENCE_API_KEY — get one at https://freeinference.orgANTHROPIC_BASE_URL): https://freeinference.org/anthropicdeepseek-v4-flash, qwen3.6-35b, diffusiongemmafree accounts can use models marked; ids checked in https://freeinference.org/v1/models2026-09-07 — Added to the list: 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 setupGenerated from registry.yaml on 2026-09-18 and re-verified twice a week; the full list, the Atom feed and the machinery are at https://github.com/mvalentsev/awesome-free-ai-coding.