---
id: "google/gemini-3.1-flash-lite"
also: ["google/gemini-3.1-flash-lite-20260507", "requesty/google/gemini-3.1-flash-lite", "vercel/google/gemini-3.1-flash-lite"]
cheapest_list_usd_per_m: "0.125 in, 0.75 out, at google-ai-studio/flex on openrouter"
cheapest_effective_usd_per_m: "0.0684 in, 1.6417 out, at google-vertex/eu on openrouter"
context: 1048576
max_output: 65536
input: ["text", "image", "video", "file", "audio"]
output: ["text"]
released: "2026-05-07"
reasoning: ["high", "medium", "low", "minimal", "none"]
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["include_reasoning", "max_tokens", "reasoning", "reasoning_effort", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p"]
endpoints: 14
gateways: "openrouter (8), requesty (4), vercel (2)"
no_training: 13
trains: 0
retains_prompts: 3
---
# Google: Gemini 3.1 Flash Lite

Gemini 3.1 Flash Lite outperforms 2.5 Flash Lite on overall quality and lands close to 2.5 Flash performance across key capability areas. It is a workhorse model for high-volume use cases, with improvements across audio input/ASR, RAG snippet ranking, translation, data extraction, and code completion.