CrossModel
Gemini 2.5 Flash Lite
gemini/gemini-2.5-flash-lite
Back to model catalog

Gemini · Model guide

Gemini 2.5 Flash Lite

Compare
gemini/gemini-2.5-flash-lite

The fastest and lightest Gemini 2.5 model, a native-multimodal sparse MoE with a 1M-token window and optional thinking. It targets classification, extraction, translation and other latency-sensitive traffic.

Modalities
TextImageAudioVideoText
Context
1M
Max output
66K
Price / 1M tokens
$ 0.10in$ 0.40out
StreamingTool callingJSON outputImage inputThinking mode · can be turned off

What this model is good at

What the vendor positions it for, and which of our models to reach for instead.

VendorThe most cost-efficient 2.5 multimodal model for high-frequency lightweight tasks.source

Best for

  • Classification and extraction · Google recommends it for high-volume classification and simple data extraction.(vendor claim)source

  • Fast translation · The model card positions it for latency-sensitive translation workloads.(vendor claim)source

Neighbouring models
  • gemini/gemini-2.5-flashstronger —Choose 2.5 Flash when broader reasoning and agent quality justify the higher cost.
Compare them side by side →

Pricing and billing

Billed per token. Cached input is charged at the cache-read rate.

Price / 1M tokensYou pay
Input$ 0.10
Output$ 0.40
Cache read$ 0.010
Cache write$ 0.10
Estimate a request
$ 0.0018
Estimated cost per request
10.0K × $ 0.10
+ 2.0K × $ 0.40
≈ $ 1.80 per 1,000 requests

Capabilities and limits

What CrossModel guarantees across every route this model can take right now.

Context window
1.0M tokens
Max output
65.5K tokens
Input / output modalities
Text + Image + Audio + Video → Text
Streaming
Supported
Tool calling
Supported
Structured output (JSON)
Supported
Image input
Supported
Thinking mode
Supported· can be turned off
Reasoning effort
none · minimal · low · medium · high
Available endpoints
/v1/chat/completions · /v1/responses · /v1/messages
First-party sources:Specsai.google.dev 1storage.googleapis.com 2Capabilitiesai.google.dev

Published benchmarks

Scores the vendor reported, with the evaluation setup each one came from.

Coding
  • SWE-Bench Verified
    resolved_rate·Google DeepMind · 2025-06enabledsetup not fully disclosed

    06-17 model, thinking, single attempt.

    27.6%
Math reasoning
  • AIME 2025
    accuracy·Google DeepMind · 2025-06enabledsetup not fully disclosed

    06-17 model, thinking.

    63.1%
Multimodal reasoning
  • MMMU
    accuracy·Google DeepMind · 2025-06enabledsetup not fully disclosed

    06-17 model, thinking.

    72.9%
Reasoning
  • Humanity's Last Exam
    accuracy·Google DeepMind · 2025-06enabledsetup not fully disclosed

    06-17 model, thinking.

    6.9%
Scientific reasoning
  • GPQA Diamond
    accuracy·Google DeepMind · 2025-06enabledsetup not fully disclosed

    06-17 model, thinking.

    66.7%

Vendor-reported numbers, not CrossModel measurements. Scores are only comparable when the benchmark version, metric and evaluation setup match, so nothing here is averaged or ranked.

Use it in your tools

Point the base URL at CrossModel and paste this model ID — every tool below has a setup guide.

Claude Code
Anthropic's official command-line coding assistant
Cursor
AI-first code editor
Cline
Open-source AI coding agent for VS Code
Codex
OpenAI's coding agent for ChatGPT desktop and the terminal
OpenCode
Open-source terminal coding assistant
Zed
High-performance, AI-native code editor
Open WebUI
Open-source, self-hosted AI chat interface
Continue
Open-source AI coding assistant for VS Code & JetBrains
See all integration guides →

Frequently asked questions

What is Gemini 2.5 Flash Lite?
Gemini 2.5 Flash Lite is available on CrossModel as gemini/gemini-2.5-flash-lite. It has a 1M-token context window and can return up to 66K tokens per request.
How much does Gemini 2.5 Flash Lite cost?
Currently $ 0.10 per 1M input tokens and $ 0.40 per 1M output tokens. Cached input is billed at $ 0.010 per 1M.
Does Gemini 2.5 Flash Lite support tool calling and structured output?
Tool calling: Supported · Structured output (JSON): Supported · Image input: Supported · Streaming: Supported · Thinking mode: Supported
Which endpoint do I call?
For text models, OpenAI Chat Completions (/v1/chat/completions), OpenAI Responses (/v1/responses) and Anthropic Messages (/v1/messages) all work — pick whichever your SDK already speaks.
Can I try it without writing code?
Yes. Sign in and open the Playground on this page to chat with the model directly — no API key needed. Usage is billed from your wallet at the normal rate.

Chat first, integrate later

Chat first, then wire it in once you like the answers.