Gemini 2.5 Flash Lite (batch)

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 across common benchmarks compared to earlier Flash models. By default, "thinking" (i.e. multi-pass reasoning) is disabled to prioritize speed, but developers can enable it via the Reasoning API parameter to selectively trade off cost for intelligence.

Speech-to-textGoogle1M tokens$0.0545 / min

google/gemini-2.5-flash-lite:batch

Context
1M tokens
Completion cap
65,535
Tools
Yes
JSON
Yes
Released
2025-07-22

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-2.5-flash-lite:batch",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is Gemini 2.5 Flash Lite (batch)?
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 across common benchmarks compared to earlier Flash models. By default, "thinking" (i.e. multi-pass reasoning) is disabled to prioritize speed, but developers can enable it via the Reasoning API parameter to selectively trade off cost for intelligence. Gemini 2.5 Flash Lite (batch) runs on the Geek Hub API (OpenAI-compatible). Model id: google/gemini-2.5-flash-lite:batch.
Is Gemini 2.5 Flash Lite (batch) free?
No. $0.0545 per minute on Geek Hub.
What is the context length of Gemini 2.5 Flash Lite (batch)?
Gemini 2.5 Flash Lite (batch) has a 1M tokens context window. It supports up to 65,535 completion tokens.
When was Gemini 2.5 Flash Lite (batch) released?
Gemini 2.5 Flash Lite (batch) was released on 2025-07-22.

More models from Google