Google AI Studio / Gemini API
Strong free prototyping surface with Gemini models and project-level quotas.
- Card required
- No
Google AI Studio / Gemini API is listed in LLM. The main constraint: Free tier exists; exact RPM, TPM, and RPD vary by model, project, region, and the live limits shown in Google AI Studio.
Show the math
Key metrics
Models
18 free · 34 totalLimits may be stale — last re-verified outside this section's freshness window.
| Model | Family | Context | Limits | AA | Access |
|---|---|---|---|---|---|
| Gemini 3.5 Flash | Gemini | 1M | 10 rpm · 250K tpm · 250 rpd | 50.2 | free |
| Gemini 3 Flash Preview deprecated | Gemini | 1M | 10 rpm · 250K tpm · 250 rpd | 27.4 | free |
| Gemini 3.1 Flash-Lite | Gemini | 1M | 15 rpm · 250K tpm · 1K rpd | 25 | free |
| Gemini 2.5 Flash | Gemini | 1M | 10 rpm · 250K tpm · 250 rpd | 14.1 | free |
| Gemini 2.5 Flash Live Preview | Gemini | — | — | 14.1 | free |
| Gemini 2.5 Flash Native Audio (Live API) | Gemini | — | — | 14.1 | free |
| Gemini 2.5 Flash Preview TTS | Gemini | — | — | 14.1 | free |
| Gemini 2.5 Flash-Lite | Gemini | 1M | 15 rpm · 250K tpm · 1K rpd | 14.1 | free |
| Gemini 2.5 Flash-Lite Preview (09-2025) | Gemini | 1M | 15 rpm · 250K tpm · 1K rpd | 14.1 | free |
| Gemini 2.0 Flash deprecated | Gemini | 1M | 15 rpm · 1M tpm · 200 rpd | — | free |
| Gemini 2.0 Flash-Lite deprecated | Gemini | 1M | 30 rpm · 1M tpm · 200 rpd | — | free |
| Gemini 3.1 Flash Live Preview | Gemini | — | — | — | free |
| Gemini 3.1 Flash TTS Preview | Gemini | — | — | — | free |
| Gemini Embedding (embedding-001) | Gemini | — | — | — | free |
| Gemini Embedding 2 | Gemini | — | — | — | free |
| Gemini Robotics-ER 1.6 Preview | Gemini | — | — | — | free |
| Gemma 4 | Gemma | — | — | — | free |
| Lyria RealTime Experimental | Lyria | — | — | — | free |
| Gemini 3.1 Pro Image (Nano Banana Pro) | Gemini | — | — | 46.5 | paid |
| Gemini 3.1 Pro Preview | Gemini | — | — | 46.5 | paid |
| Gemini 3 Pro Image | Gemini | — | — | 39.5 | paid |
| Gemini 2.5 Pro | Gemini | — | — | 27 | paid |
| Gemini 2.5 Pro Preview TTS | Gemini | — | — | 27 | paid |
| Gemini 2.5 Flash Image (Nano Banana) | Gemini | — | — | 14.1 | paid |
| Antigravity Agent Preview | Gemini | — | — | — | paid |
| Gemini 2.5 Computer Use Preview | Gemini | — | — | — | paid |
| Gemini 3.1 Flash Image (Nano Banana) | Gemini | — | — | — | paid |
| Gemini Deep Research Max Preview | Gemini | — | — | — | paid |
| Gemini Deep Research Preview | Gemini | — | — | — | paid |
| Imagen 4 | Imagen | — | — | — | paid |
| Lyria 3 (Pro / Clip Preview) | Lyria | — | — | — | paid |
| Veo 2 | Veo | — | — | — | paid |
| Veo 3 | Veo | — | — | — | paid |
| Veo 3.1 Preview | Veo | — | — | — | paid |
What you get
Free tier exists
Limits vary by model
Units: RPM / TPM / TPD
Check live limits in AI Studio
Gotchas
- Data used to improve Google products
Free-tier requests are used by Google to improve their models and products; opting out requires upgrading to a paid tier.
Sources
-
"Specified rate limits are not guaranteed and actual capacity may vary."
https://ai.google.dev/gemini-api/docs/rate-limits -
"Start building free of charge with generous limits, then scale up with prepaid then pay-as-you-go pricing for your production ready applications."
https://ai.google.dev/gemini-api/docs/pricing -
"Gemini 3.5 Flash (high) is amongst the leading models in intelligence ... 50 Artificial Analysis Intelligence Index"
https://artificialanalysis.ai/models/gemini-3-5-flash
Alternatives
Same category · similar quota
Cloud-hosted open models at NATIVE weights (GLM 5.2 1M-ctx, Kimi K2.7 Code, DeepSeek V4 Pro) with a free tier in the $0 plan; Pro $20/mo (50x usage, 3 concurrent), Max $100/mo (5x Pro, 10 concurrent); zero data retention.
Zhipu AI's BigModel open platform exposes permanently free GLM 'Flash' models (GLM-4.5-Flash, GLM-4.7-Flash, GLM-4.6V-Flash vision) with no credit card required.