> ## Documentation Index
> Fetch the complete documentation index at: https://docs.myrouter.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# FLUX.1 Kontext Dev

FLUX.1 Kontext Dev is a model that improves prompt adherence and font generation consistency while maintaining efficient speed and suitability for editing tasks.

## Request Headers

<ParamField header="Content-Type" type="string" required={true}>
  Enum: `application/json`
</ParamField>

<ParamField header="Authorization" type="string" required={true}>
  Bearer authentication format: Bearer \{\{API Key}}.
</ParamField>

## Request Body

<ParamField body="prompt" type="string" required={true}>
  The prompt used for image generation.
</ParamField>

<ParamField body="images" type="string[]" required={false}>
  List of images used for image generation. Supports up to 4 images.
</ParamField>

<ParamField body="fast_mode" type="boolean" required={false}>
  Whether to enable fast mode. When enabled, generation is faster but quality may be reduced and the price is lower.

  Default: `false`.
</ParamField>

<ParamField body="size" type="string" required={false}>
  Size of the generated media (in pixels, width\*height). Each dimension range: \[256 \~ 1536].
</ParamField>

<ParamField body="num_inference_steps" type="integer" required={false}>
  Number of inference steps. Default: 28. Range: \[1 \~ 50].
</ParamField>

<ParamField body="guidance_scale" type="number" required={false}>
  Guidance scale for controlling generation. Default: 2.5. Range: \[1.0 \~ 20.0].
</ParamField>

<ParamField body="num_images" type="integer" required={false}>
  Number of images to generate. Default: 1. Range: \[1 \~ 4].
</ParamField>

<ParamField body="seed" type="integer" required={false}>
  Random seed. Default: -1, where -1 means use a random seed. Range: \[-1 \~ 2147483647].
</ParamField>

<ParamField body="output_format" type="string" required={false}>
  Format of the output image. Default: jpeg.<br />
  Options: `jpeg`, `png`, `webp`
</ParamField>

## Response

<ResponseField name="task_id" type="string" required={true}>
  The task\_id of the async task. Use the task\_id to call the [Get Async Task Result API](/docs/models/reference-get-async-task-result) to retrieve the generated result.
</ResponseField>