gemini-3.1-flash-lite · Gemini · text
Gemini 3.1 Flash Lite is Google DeepMind's ultra-fast, budget model with a 1M context window, offering ultra-low latency and outstanding value. It supports implicit caching, vision understanding, and Function Call. Ideal for large-scale classification, tagging, and summarization scenarios.
1M context; implicit caching (cache_read 25% input); vision understanding; Function Call; JSON mode; fast responses.
Large-scale classification and tagging; summary generation; lightweight code completion; image recognition; batch data processing; embedded applications.
No image generation; implicit caching is not a guaranteed hit; pricing doubles when context exceeds 128k; max_tokens capped at 8K.
Anthropic official CLI coding agent. Multi-file edits, tool use, long-context reasoning.
export ANTHROPIC_AUTH_TOKEN="YOUR_API_KEY"
export ANTHROPIC_BASE_URL="https://api.robovai.com"
export ANTHROPIC_MODEL="gemini-3.1-flash-lite"
claude