← All models
Google · Language model
Gemini 2.5 Flash Lite
google/gemini-2.5-flash-lite- Language
Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...
Specifications
- Context window
- 1,048,576 tokens
- Max output
- 65,535 tokens
- Input
- text, image, file, audio, video
- Output
- text
- Reasoning
- supported
- Tokenizer
- Gemini
- Knowledge cutoff
- 2025-01-31
Supported parameters
Accepted by the model and forwarded as-is by the gateway.
- max_tokens
- reasoning
- response_format
- seed
- stop
- structured_outputs
- temperature
- tool_choice
- tools
- top_p
Use it
POST /api/v1/chat/completions · MCP chat · full reference
curl https://omnirail.org/api/v1/chat/completions \
-H "Authorization: Bearer $OMNIRAIL_KEY" -H "Content-Type: application/json" \
-d '{"model":"google/gemini-2.5-flash-lite","messages":[{"role":"user","content":"Hello"}],"max_tokens":300}'