Each model variation has an associated rate limit (requests per minute, RPM). For details on those rate limits, see Gemini models.
If you're using the Gemini API with the Google AI SDKs and you'd like a higher rate limit than what we currently offer, you can continue on the no-cost plan and fill out this "Request rate limit increase" form with details about your project and use case. We offer no guarantees about increasing your rate limit, but we'll do our best to review your request and reach out to you if we're able to accommodate your capacity needs.
You can also consider migrating to the Vertex AI platform on Google Cloud which may offer higher limits. With minimal code changes, you can continue using the Gemini API through the Vertex AI SDKs.