Skip to main content

Explore Celeste

All models

Google / Model reference

Gemini 2.5 Flash Lite

Google's fastest flash model optimized for cost-efficiency and high throughput.

See the code
Model IDgemini-2.5-flash-lite

What it can do.

Streaming
celeste.text.generateGenerate text
celeste.images.analyzeUnderstand media
celeste.audio.analyzeUnderstand media
celeste.videos.analyzeUnderstand media

Parameters.

Supported controls from Celeste’s model registry. Values and availability differ between models.

Gemini 2.5 Flash Lite parameters and constraints
ParameterAccepted values
temperature0 – 2
max_tokens1 – 65536
thinking_budget512 – 24576Also accepts: -1, 0
toolsList of tool definitions
output_schemaPydantic BaseModel
imageImage artifacts
videovideos
audioaudio

Start with a few lines

Put it to work.

Use your provider credentials. Call the model through the SDK and build around its output.

Generate
import celeste
response = await celeste.text.generate(
    model="gemini-2.5-flash-lite",
    prompt="Write a project brief for a neighborhood repair café."
)
print(response.content)

This example uses text.generate. Explore the quickstart for installation and authentication.