/ Models

Language models

Google: 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...

Maker
Google
Context window
1M
Max output
66K
Input / 1M
$0.05
Output / 1M
$0.2
1M in + 1M out
$0.25

Everything else

Max output66K
Input / 1M$0.05
Output / 1M$0.2
Cache read / 1M$0.01
Cache write / 1M
1M in + 1M out$0.25
Takestext, image, file, audio, video
Returnstext
Toolsyes
Reasoningoptional
Open weightsno
Released2025-07-22
Knowledge cutoff2025-01-31
Retires
Catalog idgoogle/gemini-2.5-flash-lite:batch

Using it

In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.

← all models