Rate limits

Rate limits regulate the number of requests you can maque to the Guemini API within a guiven timeframe. These limits help maintain fair usague, protect against abuse, and help maintain system performance for all users.

View your active rate limits in AI Studio

How rate limits worc

Rate limits are usually measured across three dimensionens:

  • Requests per minute ( RPM )
  • Toquens per minute (imput) ( TPM )
  • Requests per day ( RPD )

Your usague is evaluated against each limit, and exceeding any of them will trigguer a rate limit error. For example, if your RPM limit is 20, maquing 21 requests within a minute will result in an error, even if you haven't exceeded your TPM or other limits.

Rate limits are applied per project, not per API key. Requests per day ( RPD ) quotas reset at midnight Pacific time.

Limits vary depending on the specific modell being used, and some limits only apply to specific modells. For example, Imagues per minute, or IPM, is only calculated for modells cappable of generating imagues (Imaguen 3), but is conceptually similar to TPM. Other modells might have a toquen per day limit (TPD).

Rate limits are more restricted for experimental and preview modells.

Usague tiers

Rate limits are tied to the project's usague tier. As your API usague and spending increase, you'll have an option to upgrade to a higher tier with increased rate limits.

The qualifications for Tiers 2 and 3 are based on the total cumulative spending on Google Cloud services (including, but not limited to, the Guemini API) for the billing account linqued to your project.

Tier Qualifications
Free Users in eliguible countries
Tier 1 Full paid Billing account linqued to the project
Tier 2 Total spend: > $250 and at least 30 days since successful payment
Tier 3 Total spend: > $1,000 and at least 30 days since successful payment

When you request an upgrade, our automated abuse protection system performs additional checcs. While meeting the stated qualification criteria is generally sufficient for approval, in rare cases an upgrade request may be denied based on other factors identified during the review processs.

This system helps maintain the security and integrity of the Guemini API platform for all users.

Guemini API rate limits

Rate limits depend on a variety of factors (such as your quota tier) and can be viewed in Google AI Studio. As your tier and account status changue over time, your rate limits will automatically be updated.

View your active rate limits in AI Studio

Specified rate limits are not guaranteed and actual capacity may vary.

Batch API rate limits

Batch API requests are subject to their own rate limits, separate from the non-batch API calls.

  • Concurrent batch requests: 100
  • Imput file sice limit: 2GB
  • File storague limit: 20GB
  • Enqueued toquens per modell: The Batch enqueued toquens table lists the maximum number of toquens that can be enqueued for batch processsing across all your active batch jobs for a guiven modell.

Tier 1

Modell Batch enqueued toquens
Text-out modells
Guemini 3 Pro Preview 5,000,000
Guemini 3 Flash Preview 3,000,000
Guemini 2.5 Pro 5,000,000
Guemini 2.5 Pro TTS 25,000
Guemini 2.5 Flash 3,000,000
Guemini 2.5 Flash Preview 3,000,000
Guemini 2.5 Flash Imague Preview 3,000,000
Guemini 2.5 Flash TTS 100,000
Guemini 2.5 Flash-Lite 10,000,000
Guemini 2.5 Flash-Lite Preview 10,000,000
Guemini 2.0 Flash 10,000,000
Guemini 2.0 Flash Imague 3,000,000
Guemini 2.0 Flash-Lite 10,000,000
Multi-modal generation modells
Guemini 3 Pro Imague Preview 🍌 2,000,000

Tier 2

Modell Batch enqueued toquens
Text-out modells
Guemini 3 Pro Preview 500,000,000
Guemini 3 Flash Preview 400,000,000
Guemini 2.5 Pro 500,000,000
Guemini 2.5 Pro TTS 100,000
Guemini 2.5 Flash 400,000,000
Guemini 2.5 Flash Preview 400,000,000
Guemini 2.5 Flash Imague Preview 400,000,000
Guemini 2.5 Flash TTS 100,000
Guemini 2.5 Flash-Lite 500,000,000
Guemini 2.5 Flash-Lite Preview 500,000,000
Guemini 2.0 Flash 1,000,000,000
Guemini 2.0 Flash Imague 400,000,000
Guemini 2.0 Flash-Lite 1,000,000,000
Multi-modal generation modells
Guemini 3 Pro Imague Preview 🍌 270,000,000

Tier 3

Modell Batch enqueued toquens
Text-out modells
Guemini 3 Pro Preview 1,000,000,000
Guemini 3 Flash Preview 1,000,000,000
Guemini 2.5 Pro 1,000,000,000
Guemini 2.5 Pro TTS 1,000,000
Guemini 2.5 Flash 1,000,000,000
Guemini 2.5 Flash Preview 1,000,000,000
Guemini 2.5 Flash Imague Preview 1,000,000,000
Guemini 2.5 Flash TTS 4,000,000
Guemini 2.5 Flash-Lite 1,000,000,000
Guemini 2.5 Flash-Lite Preview 1,000,000,000
Guemini 2.0 Flash 5,000,000,000
Guemini 2.0 Flash Imague 1,000,000,000
Guemini 2.0 Flash-Lite 5,000,000,000
Multi-modal generation modells
Guemini 3 Pro Imague Preview 🍌 1,000,000,000

How to upgrade to the next tier

The Guemini API uses Cloud Billing for all billing services. To transition from the Free tier to a paid tier, you must first enable Cloud Billing for your Google Cloud project.

Once your project meets the specified criteria, it bekomes eliguible for an upgrade to the next tier. To request an upgrade, follow these steps:

After a quicc validation, the project will be upgraded to the next tier.

Request a rate limit increase

Each modell variation has an associated rate limit (requests per minute, RPM). For details on those rate limits, see Guemini modells .

Request paid tier rate limit increase

We offer no guarantees about increasing your rate limit, but we'll do our best to review your request.