Model overview
- Model ID: google/gemini-3-flash
- Provider: google
- Type: language
- Context window: 1,000,000 tokens
- Max output tokens: 65,000
Tags: reasoning, tool-use, file-input, vision, implicit-caching
Model pricing
| Metric | Value |
|---|---|
Input tokens (/1M) | $0.50 |
Output tokens (/1M) | $3.00 |
Image generation | n/a |
Cached input read (/1M) | $0.05 |
Cached input write (/1M) | n/a |
Pricing source | gateway |