Gemini 3.7 Flash is Google's high-speed chat model for everyday coding, agentic tool use and multi-step tasks, through an OpenAI-compatible API. It reads up to 1,048,576 tokens and replies up to 65,536, with three reasoning-effort levels.
Workbench
These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.
- Input types
- Text
- Output types
- Text
- Input
- $0.675 / 1 million tokens
- Cached input
- $0.0675 / 1 million tokens
- Output
- $3.375 / 1 million tokens
- Context
- 1,048,576
- Max output
- 65,536
$0.675/3.38per 1 million tokens · input / output
patch-review The everyday coding call: a fixed system message, one diff, effort on low. This is the shape most requests on this endpoint take.
- 2000
- low
- Input types
- Text
- Output types
- Text
- Input
- $0.675 / 1 million tokens
- Cached input
- $0.0675 / 1 million tokens
- Output
- $3.375 / 1 million tokens
- Context
- 1,048,576
- Max output
- 65,536
$0.675/3.38per 1 million tokens · input / output
agent-step One step of a tool loop. The model either answers or returns tool_calls; your runtime executes the call and appends a tool message before the next request.
- 2000
- auto
- medium
- Input types
- Text
- Output types
- Text
- Input
- $0.675 / 1 million tokens
- Cached input
- $0.0675 / 1 million tokens
- Output
- $3.375 / 1 million tokens
- Context
- 1,048,576
- Max output
- 65,536
$0.675/3.38per 1 million tokens · input / output
structured-extract JSON output. response_format shapes the reply; parsing and validation stay on your side.
- 3000
This example starts at Input $0.675 / Output $3.375 per 1 million tokens. The Playground updates the estimate when you change the settings.