Model APIs - 8 entries
Gemini API rate limits
Google's official docs, read on October 17, 2026, set rate limits for the Gemini API across Free, Tier 1, Tier 2 and Tier 3. For Gemini API, all models (per project; tier set at billing account level), Tier 1 is listed at $250 Billing tier cap (monthly spend cap) and $10 Spend rate limit (per 10 minutes, rolling), and Tier 2 at $2,000 Billing tier cap (monthly spend cap) and $50 Spend rate limit (per 10 minutes, rolling).
Last verified from ai.google.dev. What the docs leave out
- Tiers
- 4
- Tables
- 4
- Entries
- 8
- Verified
- Oct 17, 2026
Limits by model, endpoint and plan
Values are copied exactly as the docs show them, units included, in the docs' own order. A dash means the docs list no value for that row.
Gemini API, all models (per project; tier set at billing account level)
3 tiers
| Tier | Spend rate limit (per 10 minutes) |
|---|---|
| Free | N/A |
| |
| Tier 1 | -Not listed |
| |
| Tier 2 | -Not listed |
| |
- Free: Docs: rate limits are measured as Requests per minute (RPM), Tokens per minute (input) (TPM), Requests per day (RPD); some models also have Images per minute (IPM) or tokens per day (TPD). Rate limits are applied per project, not per API key. RPD quotas reset at midnight Pacific time. Rate limits are more restricted for experimental and preview models. New accounts begin on the Free Tier, which allows access to certain models up to the models' free tier rate limits. Free Tier access is limited to certain models (see pricing page). Specified rate limits are not guaranteed and actual capacity may vary.
- Tier 1: Hitting a spend-based rate limit returns a `429 RESOURCE_EXHAUSTED` error. Whether spend-based limits apply depends on billing history and account standing. After the cumulative billing account total reaches the tier spend cap, service is paused for all linked projects until the start of the next billing cycle (the 1st of each month). Prepay balance at $0 stops all API keys with HTTP 402 Payment Required.
- Tier 2: Docs: in rare cases an upgrade request may be denied based on other factors identified during the review process.
Priority inference, each model
| Metric | Limit |
|---|---|
| Default priority rate limits | 0.3x the standard rate limit for each model and tier |
- Priority consumption holds its own rate limits even though consumption is counted towards overall interactive traffic rate limits.
Batch API (all models)
| Metric | Limit |
|---|---|
| Concurrent batch requests | 100 |
| Input file size limit | 2GB |
| File storage limit | 20GB |
- Batch API requests are subject to their own rate limits, separate from the non-batch API calls. Long-running tasks like batch mode completions may incur overages beyond a project spend cap.
Batch API enqueued tokens per model (across all active batch jobs)
3 tiers
| Tier | Batch enqueued tokens - Gemini 4 Argon |
|---|---|
| Tier 1 | 5,000,000 |
| |
| Tier 2 | 500,000,000 |
| |
| Tier 3 | 1,000,000,000 |
| |
- Tier 1: Page renders three tabbed tables labelled Tier 1 / Tier 2 / Tier 3 (plus a 'More' tab); tier assignment here follows tab order in the page markup. Image model names carry a banana emoji suffix on the source page, omitted here. Groupings: Text-out models; Multi-modal generation models (the three image models); Embedding models.
- Tier 2 and Tier 3: Tier assignment follows tab order (third table). Image model banana emoji suffix omitted. Rate-limits page last updated 2026-10-15 UTC; billing page last updated 2026-09-28 UTC.
How to raise your limits
Gemini API, all models (per project; tier set at billing account level)
To transition from the Free tier to a paid tier, you must first set up billing in AI Studio (link a billing account and prepay a minimum of $5 of credits). Tier upgrades from the Free to Tier 1 will typically take effect instantly.
Gemini API, all models (per project; tier set at billing account level)
Automatic: once the project meets the next tier's criteria it is automatically upgraded; subsequent tier upgrades take effect within 10 minutes. Paid tier rate limit increases can be requested via https://forms.gle/ETzX94k8jf7iSotH9 (no guarantees). Monthly billing account cap increases can be requested via https://docs.google.com/forms/d/e/1FAIpQLSdiP6BWJyNNN65lnwnlOr-5Kv0MOFp0jLQyqi_ixVCfddqWBw/viewform.
Gemini API, all models (per project; tier set at billing account level)
Automatic upgrade to Tier 3 once criteria are met (within 10 minutes). Qualifications for Tiers 2 and 3 are based on total cumulative spending on Google Cloud services (including, but not limited to, the Gemini API) for the billing account linked to the project. Rate limit increase form: https://forms.gle/ETzX94k8jf7iSotH9.
Batch API enqueued tokens per model (across all active batch jobs)
Advance to Tier 3 automatically (Paid $1,000 + 30 days from first successful payment).
Batch API enqueued tokens per model (across all active batch jobs)
Request paid tier rate limit increase: https://forms.gle/ETzX94k8jf7iSotH9 (no guarantees).
What the docs leave out
- Per-model interactive (non-batch) RPM, TPM (input), RPD, IPM and TPD values for every tier (Free, Tier 1, Tier 2, Tier 3) are not published in the public docs as of 2026-10-17; the rate-limits page says they 'can be viewed in Google AI Studio' and links to the logged-in page https://aistudio.google.com/rate-limit. Public statements instead: limits measured as RPM, TPM (input), RPD; applied per project not per API key; RPD resets at midnight Pacific time; IPM applies only to image-generating models; some models have TPD; experimental and preview models are more restricted; limits not guaranteed.
- Batch enqueued tokens for the Free tier: the batch table shows only Tier 1, Tier 2, Tier 3 tabs (plus an unlabelled 'More' tab with no additional table in the captured page).
- Live API session/concurrency limits were not stated on the rate-limits page.
FAQ
What are the Gemini API rate limits?
Google's official docs, read on October 17, 2026, set rate limits for the Gemini API across Free, Tier 1, Tier 2 and Tier 3. For Gemini API, all models (per project; tier set at billing account level), Tier 1 is listed at $250 Billing tier cap (monthly spend cap) and $10 Spend rate limit (per 10 minutes, rolling), and Tier 2 at $2,000 Billing tier cap (monthly spend cap) and $50 Spend rate limit (per 10 minutes, rolling).
How do I raise my Gemini API rate limits?
To transition from the Free tier to a paid tier, you must first set up billing in AI Studio (link a billing account and prepay a minimum of $5 of credits). Tier upgrades from the Free to Tier 1 will typically take effect instantly. Automatic: once the project meets the next tier's criteria it is automatically upgraded; subsequent tier upgrades take effect within 10 minutes. Paid tier rate limit increases can be requested via https://forms.gle/ETzX94k8jf7iSotH9 (no guarantees). Monthly billing account cap increases can be requested via https://docs.google.com/forms/d/e/1FAIpQLSdiP6BWJyNNN65lnwnlOr-5Kv0MOFp0jLQyqi_ixVCfddqWBw/viewform. Automatic upgrade to Tier 3 once criteria are met (within 10 minutes). Qualifications for Tiers 2 and 3 are based on total cumulative spending on Google Cloud services (including, but not limited to, the Gemini API) for the billing account linked to the project. Rate limit increase form: https://forms.gle/ETzX94k8jf7iSotH9.
Where do these Gemini API numbers come from?
Every value is copied verbatim from Google's official documentation at ai.google.dev, read on October 17, 2026. This page lists all 8 entries in 4 tables, each linked to the page it came from.
Related reading
- Google AI Pro vs Gemini API: What Developers Actually GetGoogle AI Pro costs $19.99 a month and has no API key, but includes $10 of monthly Cloud credits. When the subscription wins and when to pay per token.
- Gemini 4 Argon: What Developers Can Actually UseGemini 4 Argon for developers: what Google shipped, what is verified, why access starts narrow, and what to watch before planning a migration around it.
- Gemini 2.5 Pro and Gemini 3 Flash Deprecated in GitHub Copilot: What to Switch ToGemini 2.5 Pro and Gemini 3 Flash are deprecated in GitHub Copilot. What GitHub suggests instead, the October follow-up deprecations, and how to migrate.
- Gemini CLI to Antigravity CLI Migration Guide: The June 18 DeadlineGemini CLI to Antigravity CLI migration guide: install, migrate config, update scripts and CI, and avoid the silent MCP failure that breaks tool calls.
- LLM API Pricing, October 2026: Claude vs OpenAI vs GeminiLLM API pricing for October 2026 per million tokens: Claude Haiku 5.5, Sonnet 5.5, Opus 5.5 and Fable 5.1 vs GPT-6, Gemini and DeepSeek, plus the caveats.
- Gemini CLI Guide: 1M Token Context and Who Can Still Use ItGemini CLI puts a 1 million token context in your terminal but now only serves paid Gemini API, Vertex AI and Code Assist users. Setup and TypeScript workflow.
Sources
Last verified . Every value is copied verbatim from the official pages below, read on that date.
Newsletter
Know when limits change
One email per week. New model releases, pricing and limit changes, and what they mean for what you build.