All modelsGoogle
Gemini 3.8 Flash
Fast Gemini with reasoning: images, video, audio
This model is not in the catalog right now.
See available modelsAbout the model
Gemini 3.8 Flash is the fast variant of Google's Gemini line, built for high-volume tasks. The model accepts text, images, video and audio and is suited to analyzing screenshots, video clips and recorded conversations. It includes a reasoning mode for complex multi-step tasks while still answering quickly on routine ones. Context is up to a million tokens and tool calling is supported, so the model is suited to agents and integrations. It handles Russian.
Strengths
- Text, images, video and audio as input
- Reasoning mode for complex tasks
- Context up to 1M tokens
- Tool calling (function-calling)
- Fast answers at volume
Where to use it
- Assistants that analyze images
- Analyzing video and audio recordings
- Analyzing images and documents
- High-volume request processing
- Agent scenarios with tools