Gemini 3.7 Flash
High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning
Live
Open / InstallLast updated October 22, 2026
Description
High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning. Supports a context window of 1,048,576 tokens. Supports extended reasoning. Supports tool calling. Input priced at $0.75 per million tokens. Weights are not publicly released; access is via the provider API.
Community Metrics
Views
0
Avg Rating
N/A
Ratings
0
Likes
0
Comments
—
Author
Platform
api
Pricing model
paid
Categories
- Coding
- Research
- Design
- Productivity
Tags
- llm
- closed-weights
- google
- gemini-flash
- reasoning
- tool-calling
- text
- image
- video
- audio
Capabilities
- Text generation
- 1,048,576 token context
- Extended reasoning
- Tool calling
- File attachments
- Image input
- Audio input
Information
TypeLarge Language Model
Model TypeText Generation
SourceModels Dev
AddedOctober 21, 2026