Skip to main content

Uncensored — We add no content filter to this model, but like most chat models it declines a blunt request that comes with no context. It writes unrestricted fiction reliably once your system prompt sets up a fiction-writing context, or once the request is framed as a story. Legal and consent duties remain with the customer.Browse every model at this filtering level
deepseek/v4.1-flash/chat

DeepSeek V4.1 Flash chat through an OpenAI-compatible endpoint. It takes up to 1,048,576 tokens of text and image context and returns up to 384,000, with low or high reasoning effort, up to 128 tool definitions and JSON format.

Input $0.30Output $1.20per 1 million tokensCached input $0.006
Run model

Workbench

These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.

  • Input types
    Text
    Output types
    Text
    Input
    $0.30 / 1 million tokens
    Cached input
    $0.006 / 1 million tokens
    Output
    $1.20 / 1 million tokens
    Context
    1,048,576
    Max output
    384K

    $0.30/1.20per 1 million tokens · input / output

    triage

    Evidence, assumptions and next checks kept apart, at high effort - the default working setting.

    • 700
    • high
  • Input types
    Text
    Output types
    Text
    Input
    $0.30 / 1 million tokens
    Cached input
    $0.006 / 1 million tokens
    Output
    $1.20 / 1 million tokens
    Context
    1,048,576
    Max output
    384K

    $0.30/1.20per 1 million tokens · input / output

    repo-review

    The escalation shape: same messages, effort at high and a 32,000-token cap for a long finding list.

    • 32000
    • high
  • Input types
    Text
    Output types
    Text
    Input
    $0.30 / 1 million tokens
    Cached input
    $0.006 / 1 million tokens
    Output
    $1.20 / 1 million tokens
    Context
    1,048,576
    Max output
    384K

    $0.30/1.20per 1 million tokens · input / output

    json-extract

    response_format plus field names spelled out in the prompt, which is how you get the same keys back on every run.

    • 4000

This example starts at Input $0.30 / Output $1.20 per 1 million tokens. The Playground updates the estimate when you change the settings.