awesome-free-ai-coding · every free model · every provider · filter the list
🧭 Aggregators (one key, many providers) · card required · live — last verified by a probe on 2026-11-01 · vercel.com · back to the whole list
OpenAI-compatible model gateway with $5 of monthly credit after adding a payment method, plus separate zero-priced model routes
laguna-s-2.1, nemotron-3.5-lightning, beam-1.0
Gateway credit: $5/month per team
Free credit rate limits: Requests allowance: amount not published (period not published); scope not published (Limits apply per model.)
Beam launch offer: Usage allowance: amount not published (period not published); scope not published (The free route stops at the end of the launch offer; the end date and numerical allowance are unpublished.); for reflection/beam-free
A team must add a valid payment method before using free credit; otherwise requests return 403 customer_verification_required. Credit spends at provider list rates and excludes BYOK. Buying credit ends the monthly free credit. Zero-priced model routes remain a separate free mode and do not spend that balance. Use their exact free IDs: a similarly named route without its free suffix can be metered.
The vendor names no country it keeps the offer from (source, read 2026-09-26).
What you send may be used to train or improve models unless you turn that off. In the vendor’s words: “By default, AI Gateway does not route based on the training data policy of providers. If we do not know a provider’s training data stance or have not yet established an agreement with them, we assume that they train on your data.” (source).
https://ai-gateway.vercel.sh/v1VERCEL_AI_GATEWAY_API_KEY — get one at https://vercel.com/dashboard/ai-gateway/api-keysANTHROPIC_BASE_URL): https://ai-gateway.vercel.shconfigs/codex/vercel-ai-gateway.config.toml — copy it to ~/.codex/, then codex -p vercel-ai-gateway; Codex’s base is https://ai-gateway.vercel.sh/codex/v1; set up on the lane by the vendor’s own page, https://vercel.com/docs/ai-gateway/coding-agents/openai-codex: “Point Codex at its own compatibility endpoint”poolside/laguna-s-2.1-free, stealth/glyph-cluster, nvidia/nemotron-3.5-lightning-free, reflection/beam-freeTry it from your terminal with your key in VERCEL_AI_GATEWAY_API_KEY — it goes from your machine to the vendor and nowhere else:
curl -s https://ai-gateway.vercel.sh/v1/chat/completions \
-H "Authorization: Bearer $VERCEL_AI_GATEWAY_API_KEY" \
-H 'Content-Type: application/json' \
-d '{"model":"poolside/laguna-s-2.1-free","messages":[{"role":"user","content":"2+2? MAKE NO MISTAKES."}]}'
Each line is a change to what this page publishes, dated the day it reached the list, in UTC.
2026-10-30 — Free models changed: added beam-1.02026-10-29 — Free models changed: added nemotron-3.5-lightning2026-10-15 — Free models changed: dropped ling-3.1-flash2026-10-13 — Free models changed: added ling-3.1-flash2026-10-05 — Free models changed: dropped ling-3.0-flash-sante2026-09-26 — Free models changed: dropped ling-3.0-flash-fin2026-09-19 — Free models changed: added ling-3.0-flash-sante2026-09-17 — Free models changed: added ling-3.0-flash-fin2026-08-20 — Free models changed: dropped glm-4.6v-flash2026-08-14 — Free models changed: added laguna-s-2.1; dropped laguna-s-2.1-free2026-08-14 — Free models changed: added glm-4.6v-flash2026-08-11 — Free models changed: dropped ling-3.0-flash-free2026-08-03 — Added: One OpenAI-compatible endpoint for 300+ models, with $5 of gateway credits included every monthGenerated 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.