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

Google AI Studio (Gemini API) free tier

🔌 LLM APIs with free tier · no card · not offered in mainland China, Russia, Hong Kong and 13 more places · live — last verified by a probe on 2026-11-01 · aistudio.google.com · back to the whole list

What you get

Free tier on the Gemini API, priced model by model rather than as one account quota

Free models

gemini-3.8-flash, gemini-3.6-flash, gemini-3.5-flash-lite, gemini-3.1-flash-lite, gemini-3-flash, gemma-4

Limits, in the vendor’s words

Usage allowance: see your account for values (period not published) per project per model

Free eligibility is priced per model. The current Flash, Flash-Lite and Gemma rows have a free input/output column; Gemini 3.1 Pro Preview and Omni Flash do not. Access to the 2.5 models is restricted to projects that previously used them. Actual rate limits are visible after signing in to AI Studio. Free-tier prompts and responses may be used to improve Google products; paid usage has different data-use terms. Context caching is free on the Flash models and unavailable on the Flash-Lite ones.

Where it is offered

Offered in the 230 countries and territories its list names, not in mainland China, Russia, Hong Kong, Iran, Belarus, Myanmar, Syria, Afghanistan and 8 more places (source, read 2026-09-26). That leaves out 10.5% of the developers GitHub counts, beyond the countries under comprehensive US embargo (Innovation Graph, 2026 Q1). In the vendor’s words: “The Gemini API and Google AI Studio are available in the following countries and territories”.

What happens to what you send

What you send may be used to train or improve models. In the vendor’s words: “When you use Unpaid Services, including, for example, Google AI Studio and the unpaid quota on Gemini API, Google uses the content you submit to the Services and any generated responses to provide, improve, and develop Google products and services and machine learning technologies” (source).

Connect

Base URL: https://generativelanguage.googleapis.com/v1beta/openai/
Key: GOOGLE_AI_STUDIO_API_KEY — get one at https://aistudio.google.com/apikey
Callable ids: gemini-3.8-flash, gemini-3.6-flash, gemini-3.5-flash-lite, gemini-3.1-flash-lite, gemini-3-flash-preview, gemma-4-31b-it, gemma-4-26b-a4b-it, gemini-2.5-pro, gemini-2.5-flash, gemini-2.5-flash-lite
Note: Pass the key as Bearer. The 2.5 IDs require projects that previously used those models; new projects should choose the current Flash or Gemma IDs.

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

curl -s https://generativelanguage.googleapis.com/v1beta/openai/chat/completions \
  -H "Authorization: Bearer $GOOGLE_AI_STUDIO_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{"model":"gemini-3.8-flash","messages":[{"role":"user","content":"2+2? MAKE NO MISTAKES."}]}'

Evidence

Probe: the page at https://ai.google.dev/gemini-api/docs/pricing, anchored on gemini-3.8-flash, free of charge
Source: https://ai.google.dev/gemini-api/docs/pricing
Source: https://ai.google.dev/gemini-api/docs/rate-limits
Source: https://ai.google.dev/gemini-api/docs/changelog
Source: https://ai.google.dev/gemma/docs/core/gemma_on_gemini_api
Source: https://ai.google.dev/gemini-api/docs/models/gemini-3.7-flash
Source: https://ai.google.dev/gemini-api/docs/models/gemini-3.5-flash

History

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

2026-10-28 — Free models changed: dropped gemini-3.5-flash, gemini-3.7-flash
2026-09-25 — Free models changed: added gemini-3-flash, gemini-3.1-flash-lite, gemini-3.5-flash, gemini-3.6-flash, gemma-4
2026-09-23 — Free models changed: dropped gemini-2.5-pro
2026-09-07 — Free models changed: added gemini-3.8-flash
2026-08-14 — Free models changed: added gemini-2.5-pro, gemini-3.5-flash-lite, gemini-3.7-flash; dropped gemini-2.5
2026-07-19 — Added: Free tier for Gemini 2.5 Flash/Pro API

Generated 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.

Something wrong or missing? Suggest a service or a change — or read how the list works.