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 · tokenharbor.ai · back to the whole list
OpenAI- and Anthropic-compatible gateway with a standing $0 plan: a rotating lineup of :free ids on a value-based allowance per rolling 7-day period, no card
deepseek-v4.1-flash, mimo-v2.6-flash
Free routes: Rolling 7-day list-price value allowance: amount not published per account
Free accounts: 60 requests/minute; 1,800 requests/hour per account
Free accounts: 100 requests/minute; 3,000 requests/hour per IP
Enable explicit :free routes in the dashboard before calling them; the rotating model set is listed under Free. The dashboard shows usage as a percentage. Exhausted free routes stop instead of charging the wallet. Request-rate caps apply to Free accounts across models and API keys. “There is no limit on concurrent requests, on any plan.” “Free accounts: up to 4 MB (4,000,000 bytes).” Oversized requests return 413 request_too_large. Permanent free routes require data sharing: staff and third-party AI tools may analyze retained prompts and responses for diagnostics and model or product improvement. Token Harbor says it does not train models itself; upstream providers may train under their own terms. Limited-time campaigns may expressly use the paid-route data policy instead. The operator is Token Harbor PTE. LTD., Singapore.
The vendor names no country it keeps the offer from (source, read 2026-09-26). In the vendor’s words: “the Service is restricted and not intended for use in certain jurisdictions”.
What you send may be used to train or improve models. In the vendor’s words: “Token Harbor does not train models on it itself. The providers that serve free models may also use these conversations under their own terms, including to train their own models.” (source).
https://tokenharbor.ai/v1TOKEN_HARBOR_API_KEY — get one at https://tokenharbor.ai/dashboard/api-keysANTHROPIC_BASE_URL): https://tokenharbor.aiconfigs/codex/token-harbor.config.toml — copy it to ~/.codex/, then codex -p token-harbor; set up on the lane by the vendor’s own page, https://tokenharbor.ai/docs/integrations/codex: “Point OpenAI Codex at Token Harbor manually”deepseek-v4.1-flash:free, mimo-v2.6-flash:freeTry it from your terminal with your key in TOKEN_HARBOR_API_KEY — it goes from your machine to the vendor and nowhere else:
curl -s https://tokenharbor.ai/v1/chat/completions \
-H "Authorization: Bearer $TOKEN_HARBOR_API_KEY" \
-H 'Content-Type: application/json' \
-d '{"model":"deepseek-v4.1-flash:free","messages":[{"role":"user","content":"2+2? MAKE NO MISTAKES."}]}'
Try Token Harbor with a free allowance and a rotating model lineup, Resets on a rolling 7-day periodEach line is a change to what this page publishes, dated the day it reached the list, in UTC.
2026-10-06 — Free models changed: added mimo-v2.6-flash2026-09-22 — Free models changed: dropped deepseek-v4-flash, mimo-v2.52026-09-18 — Free models changed: added deepseek-v4-flash2026-09-16 — Added: 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 cardGenerated from registry.yaml on 2026-11-01 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.