DeepSeek / Model reference

DeepSeek V4 Flash

Name: DeepSeek V4 Flash
Author: DeepSeek

DeepSeek model available through the Celeste SDK. Explore its supported operations and parameters.

See the code

Model IDdeepseek-v4-flash

What it can do.

Streaming

celeste.text.generateGenerate text

Parameters.

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

DeepSeek V4 Flash parameters and constraints
Parameter	Accepted values
`max_tokens`	1 – 384000Step: 1
`output_schema`	Pydantic BaseModel
`temperature`	0 – 2Step: 0.01
`thinking_level`	`disabledhighmax`
`tool_choice`	toolchoicesupport
`tools`	List of tool definitions

Start with a few lines

Put it to work.

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

import celeste
response = await celeste.text.generate(
    model="deepseek-v4-flash",
    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.