awesome-free-ai-coding · every free model · every provider · filter the list
🧭 Aggregators (one key, many providers) · no card · live — last verified by a probe on 2026-11-01 · routeway.ai · back to the whole list
OpenAI-compatible gateway with a rotating :free chat-model lane beside metered models
Rate-limits documentation: 5 requests/minute (published sources disagree) per account
FAQ: 20 requests/minute (published sources disagree) per account
Free models: 200 requests/day per account
The FAQ and rate-limit docs disagree on the per-minute cap; both publish the same daily cap. Free IDs end in :free, rotate and may be removed at any time. At a cap they return 429; paid twins require a positive balance. The FAQ describes signup and key creation without payment, but the older terms list a payment method. No legal entity is named; support is email and Discord.
The vendor names no country it keeps the offer from (source, read 2026-09-26).
https://api.routeway.ai/v1ROUTEWAY_API_KEY — get one at https://routeway.ai/dashboard/keysconfigs/codex/routeway.config.toml — copy it to ~/.codex/, then codex -p routeway; set up on the lane by the vendor’s own page, https://docs.routeway.ai/integrations/agents/codex: “Use OpenAI’s Codex with Routeway by adding a custom provider”deepseek-v4.1-flash:free, minimax-m3.1-flash:free, muse-glimmer-30b:freeTry it from your terminal with your key in ROUTEWAY_API_KEY — it goes from your machine to the vendor and nowhere else:
curl -s https://api.routeway.ai/v1/chat/completions \
-H "Authorization: Bearer $ROUTEWAY_API_KEY" \
-H 'Content-Type: application/json' \
-d '{"model":"deepseek-v4.1-flash:free","messages":[{"role":"user","content":"2+2? MAKE NO MISTAKES."}]}'
:free, each listed family checked for a zero priceEach line is a change to what this page publishes, dated the day it reached the list, in UTC.
2026-11-01 — Free models changed: dropped deepseek-v4-flash, minimax-m2.72026-09-16 — Free models changed: added deepseek-v4-flash, minimax-m2.72026-09-14 — Free models changed: added muse-glimmer-30b2026-09-05 — Free models changed: dropped gemma-4, gpt-oss2026-08-30 — Free models changed: dropped llama-3.3, step-3.7-flash2026-08-11 — Free models changed: dropped ling-3.0-flash2026-08-05 — Free models changed: added gemma-4, llama-3.32026-08-05 — Added: OpenAI-compatible gateway whose catalog carries eleven live :free ids priced at zero — gpt-oss-120b, Ling 3.0 Flash, Step 3.7 Flash, Gemma 4 and the Llama 3.x line — beside a metered 100+ model catalogGenerated from registry.yaml on 2026-11-02 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.