awesome-free-ai-coding · every free model · every provider · filter the list

Experiential Labs free tier

🧭 Aggregators (one key, many providers) · card required · requires $1 one-time charge · live — last verified by a probe on 2026-10-26 · experientiallabs.ai · back to the whole list

What you get

Open-source AI gateway backed by Y Combinator with recurring model-specific free quotas after a settled payment, separate from its paid credit wallet

Free models

No free model family is currently listed here; callable ids, where the row has them, are under Connect.

Limits, in the vendor’s words

Astra promotional input: 500,000 tokens/day; 200,000 tokens/hour per organization per model; for gpt-6-astra:free

Astra promotional output: 100,000 tokens/day; 40,000 tokens/hour per organization per model; for gpt-6-astra:free

Fable 5.1 promotional input: 375,000 tokens/day; 100,000 tokens/hour per organization per model; for claude-fable-5.1:free

Fable 5.1 promotional output: 75,000 tokens/day; 30,000 tokens/hour per organization per model; for claude-fable-5.1:free

Free core models: 10 requests/minute; 250,000 tokens/minute; 1,000,000 tokens/day per service plan

The documented promotional free tiers require a saved card and one settled $1+ charge; adding a card alone is insufficient. The :free aliases stop at their quota instead of switching to paid credit. Cached input does not count toward these promotional quotas. The separate pricing-page Free core caps apply to its advertised DeepSeek V4.1 Flash and GPT-6 Luna routes, not these promotional aliases. That page has no general monthly credits; its Free card speed conflicts with its detailed table and FAQ, and its chat claims conflict with positive Free-selected catalog prices. Jev uses a decision API rather than chat. Free prompt and response storage cannot be disabled without a paid plan.

Where it is offered

The vendor names no country it keeps the offer from (source, read 2026-09-26).

Connect

Try it from your terminal with your key in EXPERIENTIAL_LABS_API_KEY — it goes from your machine to the vendor and nowhere else:

curl -s https://api.experientiallabs.ai/v1/chat/completions \
  -H "Authorization: Bearer $EXPERIENTIAL_LABS_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{"model":"gpt-6-astra:free","messages":[{"role":"user","content":"2+2? MAKE NO MISTAKES."}]}'

Evidence

History

Each line is a change to what this page publishes, dated the day it reached the list, in UTC.


Generated from registry.yaml on 2026-10-28 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.