Gemini 3 Flash

by Google · chat

High-speed thinking model with 1M context for agentic workflows, multi-turn chat, and coding with configurable reasoning effort.

Pricing

Input: $0.465/M tokens · Output: $2.79/M tokens

Capabilities

Vision, Function Calling, JSON Mode, Streaming, Reasoning

Context: 1049K tokens

Max output: 66K tokens

Routes: 1/1 healthy

Performance

TTFT: 2212ms · Latency: 3641ms · Throughput: 500.1 tok/s