Google · Direct API
Gemini 3.1 Pro Preview pricing
Prompts over 200K tokens use long-context rates; Google publishes the same cache-read rate for Batch and Standard.
DirectOfficial provider
This is a first-party rate checked against the model provider's official pricing page.
Caching
2,000 input + 500 output tokens$0.01 / request
Calculate a complete workload →