> ## Documentation Index
> Fetch the complete documentation index at: https://dripart-codex-simplify-get-started.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Use FLUX.1 Kontext with Comfy Router

> Python, TypeScript and cURL snippets for calling FLUX.1 Kontext Pro and Kontext Max over HTTP through Comfy Router, plus the request fields and the result shape

API Reference for FLUX.1 Kontext. FLUX.1 Kontext is Black Forest Labs' instruction-driven image editing model: send an image and a text instruction, get the edited image back with the rest of the scene preserved.

## Quick start

Create a key in [your Comfy workspace](https://platform.comfy.org/profile/api-keys) and export it as `COMFY_API_KEY`. The Python and TypeScript snippets use the Comfy SDKs (`pip install comfy-sdk`, `npm install @comfyorg/sdk`); the cURL snippet is the same call over raw HTTP.

Pick the model you want to call. Everything below, from the snippets to the schema and examples, follows your choice.

<Tabs>
  <Tab title="Kontext Pro">
    **Model ID:** `bfl/flux-kontext-pro`

    **Endpoint:** `POST https://api.comfy.org/v2/models/bfl/flux-kontext-pro`

    <CodeGroup>
      ```python Python theme={null}
      import base64

      from comfy_sdk import Comfy

      with open("input.jpg", "rb") as f:
          input_image = base64.b64encode(f.read()).decode()

      # Reads COMFY_API_KEY from the environment.
      # The SDK automatically creates an idempotency key and reuses it for automatic retries.
      with Comfy() as client:
          result = client.models.run(
              "bfl/flux-kontext-pro",
              {
                  "prompt": "replace the background with a sunlit beach, keep the subject unchanged",
                  "input_image": input_image,
                  "aspect_ratio": "1:1",
              },
          )

      print("image:", result["result"]["sample"])
      ```

      ```typescript TypeScript theme={null}
      import { comfy } from "@comfyorg/sdk";
      import { readFile } from "node:fs/promises";

      const inputImage = (await readFile("input.jpg")).toString("base64");

      // Reads COMFY_API_KEY from the environment.
      // The SDK automatically creates an idempotency key and reuses it for automatic retries.
      type Result = { result: { sample: string } };
      const { data } = await comfy.models.run<Result>("bfl/flux-kontext-pro", {
        prompt: "replace the background with a sunlit beach, keep the subject unchanged",
        input_image: inputImage,
        aspect_ratio: "1:1",
      });

      console.log("image:", data.result.sample);
      ```

      ```bash cURL theme={null}
      INPUT_IMAGE=$(base64 < input.jpg | tr -d '\n')

      curl https://api.comfy.org/v2/models/bfl/flux-kontext-pro \
        -H "X-API-Key: $COMFY_API_KEY" \
        -H "Idempotency-Key: $(uuidgen)" \
        -H "Content-Type: application/json" \
        -d "{\"prompt\": \"replace the background with a sunlit beach, keep the subject unchanged\", \"input_image\": \"$INPUT_IMAGE\", \"aspect_ratio\": \"1:1\"}"
      ```
    </CodeGroup>

    <h2>Schema</h2>

    <h3>Input</h3>

    <ParamField body="aspect_ratio" type="string">
      Aspect ratio of the output between 21:9 and 9:21, e.g. 16:9. Defaults to the input image's aspect ratio when one is given, otherwise 1:1.
    </ParamField>

    <ParamField body="input_image" type="string">
      Image to edit, as a base64-encoded image or an http(s) URL. Optional; without it the model generates from the prompt alone.
    </ParamField>

    <ParamField body="input_image_2" type="string">
      Additional reference image, base64-encoded or an http(s) URL (experimental multi-reference).
    </ParamField>

    <ParamField body="input_image_3" type="string">
      Additional reference image, base64-encoded or an http(s) URL (experimental multi-reference).
    </ParamField>

    <ParamField body="input_image_4" type="string">
      Additional reference image, base64-encoded or an http(s) URL (experimental multi-reference).
    </ParamField>

    <ParamField body="output_format" type="string" default="&#x22;png&#x22;">
      Output image format.

      Possible values: `jpeg`, `png`, `webp`
    </ParamField>

    <ParamField body="prompt" type="string" required>
      Text prompt describing the edit to apply to input\_image, or the image to generate when no input\_image is given.
    </ParamField>

    <ParamField body="prompt_upsampling" type="boolean" default="false">
      Whether to upsample the prompt. If active, the prompt is automatically modified for more creative generation.
    </ParamField>

    <ParamField body="safety_tolerance" type="integer" default="2">
      Tolerance level for input and output moderation, between 0 (most strict) and 6 (least strict).

      Range: `0` to `6`
    </ParamField>

    <ParamField body="seed" type="integer">
      Optional seed for reproducibility. A random seed is used when omitted.
    </ParamField>

    <ParamField body="webhook_secret" type="string">
      Optional secret for webhook signature verification.
    </ParamField>

    <ParamField body="webhook_url" type="string (uri)">
      URL to receive webhook notifications.

      Format: `uri`
    </ParamField>

    Generated from the schema Router serves at `GET /v2/models/bfl/flux-kontext-pro/openapi.json`, the same document it validates a call against before the request reaches the provider.

    <h3>Output</h3>

    <ResponseField name="cost" type="number">
      Provider-reported cost in credits, populated once the task is Ready.

      Format: `float`
    </ResponseField>

    <ResponseField name="id" type="string" required>
      BFL task identifier.
    </ResponseField>

    <ResponseField name="progress" type="number">
      Optional generation progress reported by BFL.

      Range: `0` to `1`

      Format: `float`
    </ResponseField>

    <ResponseField name="result" type="object" required>
      The finished generation. Not nullable here: this component's `required` entry is a promise that a `200` carries the result, and a nullable `result` would reduce it to a key-presence check.
    </ResponseField>

    <ResponseField name="result.cost" type="number">
      Provider-reported cost of the generation. This is BFL's number, not the Comfy charge.

      Format: `double`
    </ResponseField>

    <ResponseField name="result.duration" type="number">
      Provider-reported generation duration in seconds.

      Format: `double`
    </ResponseField>

    <ResponseField name="result.end_time" type="number">
      Provider-reported completion time of the generation, in seconds since the Unix epoch. `double` for the same reason as `start_time`.

      Format: `double`
    </ResponseField>

    <ResponseField name="result.prompt" type="string">
      The prompt the generation actually ran, after any prompt upsampling.
    </ResponseField>

    <ResponseField name="result.sample" type="string (uri)">
      Signed URL for the generated asset. Router re-hosts the asset onto Comfy storage and rewrites this field, so it is normally a Comfy-hosted URL valid for up to 24 hours - signed for 24 hours when minted, and replayed from a 23-hour memo, so a later poll can hand back one with as little as an hour left; a leaf whose re-host could not be performed keeps BFL's own short-lived delivery URL instead - roughly two hours for video, roughly ten minutes for images. Either way the link expires, so download the asset rather than storing the URL.

      Format: `uri`
    </ResponseField>

    <ResponseField name="result.seed" type="integer">
      The seed the generation used, whether supplied or chosen by the provider. Declared `int64` because BFL returns seeds above 2^31 (e.g. 2784347701), which an unformatted `integer` generates as a 32-bit field in many SDK generators.

      Format: `int64`
    </ResponseField>

    <ResponseField name="result.start_time" type="number">
      Provider-reported start time of the generation, in seconds since the Unix epoch. `double`, not `float`: float32 spacing near a present-day epoch value is \~128 seconds, which collapses a whole generation's span to a single decoded value.

      Format: `double`
    </ResponseField>

    <ResponseField name="status" type="string" required>
      Task status: Pending, Reasoning, Generating, Ready, Request Moderated, Content Moderated, Error, or Task not found.
    </ResponseField>

    <h2>Examples</h2>

    <h3>Input</h3>

    ```json theme={null}
    {
      "prompt": "replace the background with a sunlit beach, keep the subject unchanged",
      "input_image": "<base64 of input.jpg>",
      "aspect_ratio": "1:1"
    }
    ```

    <h3>Output</h3>

    ```json theme={null}
    {
      "id": "0a1b2c3d-...",
      "status": "Ready",
      "result": {
        "sample": "https://.../out.png",
        "prompt": "replace the background with a sunlit beach, keep the subject unchanged",
        "seed": 1234567890
      }
    }
    ```

    The URL is temporary. Download the image promptly if you need to keep it.
  </Tab>

  <Tab title="Kontext Max">
    **Model ID:** `bfl/flux-kontext-max`

    **Endpoint:** `POST https://api.comfy.org/v2/models/bfl/flux-kontext-max`

    <CodeGroup>
      ```python Python theme={null}
      import base64

      from comfy_sdk import Comfy

      with open("input.jpg", "rb") as f:
          input_image = base64.b64encode(f.read()).decode()

      # Reads COMFY_API_KEY from the environment.
      # The SDK automatically creates an idempotency key and reuses it for automatic retries.
      with Comfy() as client:
          result = client.models.run(
              "bfl/flux-kontext-max",
              {
                  "prompt": "replace the background with a sunlit beach, keep the subject unchanged",
                  "input_image": input_image,
                  "aspect_ratio": "1:1",
              },
          )

      print("image:", result["result"]["sample"])
      ```

      ```typescript TypeScript theme={null}
      import { comfy } from "@comfyorg/sdk";
      import { readFile } from "node:fs/promises";

      const inputImage = (await readFile("input.jpg")).toString("base64");

      // Reads COMFY_API_KEY from the environment.
      // The SDK automatically creates an idempotency key and reuses it for automatic retries.
      type Result = { result: { sample: string } };
      const { data } = await comfy.models.run<Result>("bfl/flux-kontext-max", {
        prompt: "replace the background with a sunlit beach, keep the subject unchanged",
        input_image: inputImage,
        aspect_ratio: "1:1",
      });

      console.log("image:", data.result.sample);
      ```

      ```bash cURL theme={null}
      INPUT_IMAGE=$(base64 < input.jpg | tr -d '\n')

      curl https://api.comfy.org/v2/models/bfl/flux-kontext-max \
        -H "X-API-Key: $COMFY_API_KEY" \
        -H "Idempotency-Key: $(uuidgen)" \
        -H "Content-Type: application/json" \
        -d "{\"prompt\": \"replace the background with a sunlit beach, keep the subject unchanged\", \"input_image\": \"$INPUT_IMAGE\", \"aspect_ratio\": \"1:1\"}"
      ```
    </CodeGroup>

    <h2>Schema</h2>

    <h3>Input</h3>

    <ParamField body="aspect_ratio" type="string">
      Aspect ratio of the output between 21:9 and 9:21, e.g. 16:9. Defaults to the input image's aspect ratio when one is given, otherwise 1:1.
    </ParamField>

    <ParamField body="input_image" type="string">
      Image to edit, as a base64-encoded image or an http(s) URL. Optional; without it the model generates from the prompt alone.
    </ParamField>

    <ParamField body="input_image_2" type="string">
      Additional reference image, base64-encoded or an http(s) URL (experimental multi-reference).
    </ParamField>

    <ParamField body="input_image_3" type="string">
      Additional reference image, base64-encoded or an http(s) URL (experimental multi-reference).
    </ParamField>

    <ParamField body="input_image_4" type="string">
      Additional reference image, base64-encoded or an http(s) URL (experimental multi-reference).
    </ParamField>

    <ParamField body="output_format" type="string" default="&#x22;png&#x22;">
      Output image format.

      Possible values: `jpeg`, `png`, `webp`
    </ParamField>

    <ParamField body="prompt" type="string" required>
      Text prompt describing the edit to apply to input\_image, or the image to generate when no input\_image is given.
    </ParamField>

    <ParamField body="prompt_upsampling" type="boolean" default="false">
      Whether to upsample the prompt. If active, the prompt is automatically modified for more creative generation.
    </ParamField>

    <ParamField body="safety_tolerance" type="integer" default="2">
      Tolerance level for input and output moderation, between 0 (most strict) and 6 (least strict).

      Range: `0` to `6`
    </ParamField>

    <ParamField body="seed" type="integer">
      Optional seed for reproducibility. A random seed is used when omitted.
    </ParamField>

    <ParamField body="webhook_secret" type="string">
      Optional secret for webhook signature verification.
    </ParamField>

    <ParamField body="webhook_url" type="string (uri)">
      URL to receive webhook notifications.

      Format: `uri`
    </ParamField>

    Generated from the schema Router serves at `GET /v2/models/bfl/flux-kontext-max/openapi.json`, the same document it validates a call against before the request reaches the provider.

    <h3>Output</h3>

    <ResponseField name="cost" type="number">
      Provider-reported cost in credits, populated once the task is Ready.

      Format: `float`
    </ResponseField>

    <ResponseField name="id" type="string" required>
      BFL task identifier.
    </ResponseField>

    <ResponseField name="progress" type="number">
      Optional generation progress reported by BFL.

      Range: `0` to `1`

      Format: `float`
    </ResponseField>

    <ResponseField name="result" type="object" required>
      The finished generation. Not nullable here: this component's `required` entry is a promise that a `200` carries the result, and a nullable `result` would reduce it to a key-presence check.
    </ResponseField>

    <ResponseField name="result.cost" type="number">
      Provider-reported cost of the generation. This is BFL's number, not the Comfy charge.

      Format: `double`
    </ResponseField>

    <ResponseField name="result.duration" type="number">
      Provider-reported generation duration in seconds.

      Format: `double`
    </ResponseField>

    <ResponseField name="result.end_time" type="number">
      Provider-reported completion time of the generation, in seconds since the Unix epoch. `double` for the same reason as `start_time`.

      Format: `double`
    </ResponseField>

    <ResponseField name="result.prompt" type="string">
      The prompt the generation actually ran, after any prompt upsampling.
    </ResponseField>

    <ResponseField name="result.sample" type="string (uri)">
      Signed URL for the generated asset. Router re-hosts the asset onto Comfy storage and rewrites this field, so it is normally a Comfy-hosted URL valid for up to 24 hours - signed for 24 hours when minted, and replayed from a 23-hour memo, so a later poll can hand back one with as little as an hour left; a leaf whose re-host could not be performed keeps BFL's own short-lived delivery URL instead - roughly two hours for video, roughly ten minutes for images. Either way the link expires, so download the asset rather than storing the URL.

      Format: `uri`
    </ResponseField>

    <ResponseField name="result.seed" type="integer">
      The seed the generation used, whether supplied or chosen by the provider. Declared `int64` because BFL returns seeds above 2^31 (e.g. 2784347701), which an unformatted `integer` generates as a 32-bit field in many SDK generators.

      Format: `int64`
    </ResponseField>

    <ResponseField name="result.start_time" type="number">
      Provider-reported start time of the generation, in seconds since the Unix epoch. `double`, not `float`: float32 spacing near a present-day epoch value is \~128 seconds, which collapses a whole generation's span to a single decoded value.

      Format: `double`
    </ResponseField>

    <ResponseField name="status" type="string" required>
      Task status: Pending, Reasoning, Generating, Ready, Request Moderated, Content Moderated, Error, or Task not found.
    </ResponseField>

    <h2>Examples</h2>

    <h3>Input</h3>

    ```json theme={null}
    {
      "prompt": "replace the background with a sunlit beach, keep the subject unchanged",
      "input_image": "<base64 of input.jpg>",
      "aspect_ratio": "1:1"
    }
    ```

    <h3>Output</h3>

    ```json theme={null}
    {
      "id": "0a1b2c3d-...",
      "status": "Ready",
      "result": {
        "sample": "https://.../out.png",
        "prompt": "replace the background with a sunlit beach, keep the subject unchanged",
        "seed": 1234567890
      }
    }
    ```

    The URL is temporary. Download the image promptly if you need to keep it.
  </Tab>
</Tabs>

## Before you ship

The SDKs create an `Idempotency-Key` and reuse it for automatic retries. For manual retries, reuse the original key. Router can hold the connection for up to 10 minutes.

When a request fails, Router sends an `X-Comfy-Error-Type` response header explaining why. A `422` means Router rejected the input before calling the provider. Download generated assets promptly because [result URLs can expire](/development/comfy-router/reference#result-assets).

<CardGroup cols={3}>
  <Card title="Headers" icon="list" href="/development/comfy-router/headers">
    Authentication, idempotency, request IDs, error buckets, retry pacing, spend limits.
  </Card>

  <Card title="Using the Router API" icon="code" href="/development/comfy-router/api">
    Model discovery, validation errors, retries, and billing.
  </Card>

  <Card title="Limitations" icon="triangle-exclamation" href="/development/comfy-router/limitations">
    What Router does not do today, and what to use instead.
  </Card>
</CardGroup>