Gemini 3.1 Flash Lite

Gemini 3.1 Flash Lite is a Google model available in Agent Serve. Gemini 3.1 Flash Lite is a Google model tracked in Agent Serve. It supports a 1.05M token context window. Pricing starts at $0.25/1M input tokens and $1.5/1M output tokens. Key capabilities include Temperature 0-2, Tool choice, Structured outputs.

Gemini 3.1 Flash Lite starts at $0.25/1M input tokens, $0.025/1M cached input tokens, and $1.5/1M output tokens.

Gemini 3.1 Flash Lite supports a context window of 1.05M tokens in Agent Serve. In an agent, this determines how much conversation history, tool outputs, and retrieved documents the model can hold in a single call.

Gemini 3.1 Flash Lite supports the following capabilities in Agent Serve: Temperature 0-2, Tool choice, Structured outputs, Thinking minimal, low, medium, high, Max output 66k.

Best for reasoning-heavy tasks that need more deliberate model control. When used in an Agent Serve workflow, it can be selected in any Agent block from the model picker.