Google AI Studio (Gemini API)
partially verifiedpermanent free · model_vendor · confidence 85% · mixed · last verified 2026-08-17 · field guide →
Subject record
| Base URLs | https://generativelanguage.googleapis.com/v1beta native https://generativelanguage.googleapis.com/v1beta/openai openai-compatible |
|---|---|
| API key required | yes |
| Credit card | no |
| Phone verification | unknown |
| May train on prompts | yes |
| Quota | free_tier [rpm, rpd, tpm] “Gemini 2.5 Flash: 250,000 tokens/minute, 20 requests/day, 5 requests/minute; Gemini 3.1 Flash-Lite: 250,000 tokens/minute, 500 requests/day, 15 requests/minute; Gemma 3 27B Instruct: 15,000 tokens/minute, 14,400 requests/day, 30 requests/minute (per model)” |
| Signup friction | 3 steps · ~5m to first key |
| Env var | GEMINI_API_KEY |
| Notes | OpenAI-compatible base URL confirmed from official docs: https://generativelanguage.googleapis.com/v1beta/openai/ (streaming, function calling, and image input all documented as supported). Regional caveat conflict between repo sources: mnfst says free tier unavailable in EU/UK/Switzerland; cheahjs says data is used for training only when used outside UK/CH/EEA/EU — unresolved, treat availability in those regions as unknown. LIVE PROBE 2026-07-25 caught DRIFT: the synthetic completion returned model_unavailable, so the specific Gemini model the probe targeted is retired/renamed at the endpoint — status dropped verified → partially_verified. The provider itself is fine (key + endpoint respond); this is MODEL drift. REVISIT: refresh the cataloged Gemini model list against the live /models response and re-point the probe at a current model id. RESOLVED 2026-07-25: live /models (OpenAI-compat endpoint, real key) returns only gemini-2.5-* and gemini-2.0-* — there is NO gemini-3.x line. The cataloged `gemini-3.5-flash` was a PHANTOM (imported from speculative repo sources, never existed at the endpoint) and has been REMOVED; it was the cause of the synthetic model_unavailable. Real free models retained and confirmed live: gemini-2.5-flash, gemini-2.5-flash-lite. |
Models (3)
| model | capabilities | context | free | limits |
|---|---|---|---|---|
| gemini-2.5-flash-lite ⚠ deprecated | chat, vision, tool_calling | ? | yes | 10 rpm · 20 rpd · 250000 tpm |
| gemini-2.5-flash | chat, vision, audio_in, tool_calling, reasoning | 1,048,576 | yes | 5 rpm · 20 rpd · 250000 tpm |
| gemma-3-27b-it | chat | ? | yes | 30 rpm · 14400 rpd · 15000 tpm |
Provenance
| source_google_ai_studio_docs | official_docs | trust: high | checked 2026-07-17 |
| source_repo_cheahjs | curated_repo | trust: medium_high | checked 2026-07-17 |
| source_repo_mnfst | curated_repo | trust: medium_high | checked 2026-07-17 |