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

# Use FLUX 3 Image with Comfy Router

> Call bfl/flux-3-image through Comfy Router: endpoint, request shape and the response Router returns.

API Reference for `bfl/flux-3-image`, served by Comfy Router from Black Forest Labs.

**Input:** Text, Image · **Output:** Image

## Quick start

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

**Model ID:** `bfl/flux-3-image`

**Endpoint:** `POST https://api.comfy.org/v2/models/bfl/flux-3-image`

**Wait for the result**

```python Python theme={null}
from comfy_sdk import Comfy

# 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-3-image",
        {
            "aspect_ratio": "16:9",
            "prompt": "A mountain landscape at sunset",
            "resolution": "1k",
        },
    )

print(result)
```

```typescript TypeScript theme={null}
import { comfy } from "@comfyorg/sdk";

// Reads COMFY_API_KEY from the environment.
// The SDK automatically creates an idempotency key and reuses it for automatic retries.
const { data } = await comfy.models.run("bfl/flux-3-image", {
  aspect_ratio: "16:9",
  prompt: "A mountain landscape at sunset",
  resolution: "1k",
});

console.log(data);
```

```bash cURL theme={null}
curl https://api.comfy.org/v2/models/bfl/flux-3-image \
  -H "X-API-Key: $COMFY_API_KEY" \
  -H "Idempotency-Key: $(uuidgen)" \
  -H "Content-Type: application/json" \
  -d "{\"aspect_ratio\": \"16:9\", \"prompt\": \"A mountain landscape at sunset\", \"resolution\": \"1k\"}"
```

**Queue and collect later**

The same body, sent to `POST https://api.comfy.org/v2/models/bfl/flux-3-image/requests`. Router answers `201` with a `request_id` as soon as the run is admitted, and the result is collected once it is ready, from this process or another one. [Queued delivery](https://docs.comfy.org/development/comfy-router/queue.md) walks through status, cancellation and collection.

```python Python theme={null}
import asyncio
from comfy_sdk import AsyncComfy

# Reads COMFY_API_KEY from the environment.
# Each submit() call mints its own Idempotency-Key and reuses it for automatic retries.
async def main():
    async with AsyncComfy() as client:
        handle = await client.models.submit(
            "bfl/flux-3-image",
            {
                "aspect_ratio": "16:9",
                "prompt": "A mountain landscape at sunset",
                "resolution": "1k",
            },
        )
        print("request_id:", handle.request_id)  # with the model ID, all another process needs

        # Poll until the request completes, waiting the Retry-After the server names.
        async for update in handle.iter_events():
            print(update.status, update.queue_position)

        # The provider's own payload, the same value models.run() returns.
        # A request that failed or was cancelled raises the typed Router error here.
        result = await handle.get()

    print(result)

asyncio.run(main())
```

```typescript TypeScript theme={null}
import { comfy } from "@comfyorg/sdk";

// Reads COMFY_API_KEY from the environment.
// Each submit() call mints its own Idempotency-Key and reuses it for automatic retries.
const handle = await comfy.models.submit("bfl/flux-3-image", {
  aspect_ratio: "16:9",
  prompt: "A mountain landscape at sunset",
  resolution: "1k",
});
console.log("requestId:", handle.requestId); // with the model ID, all another process needs

// Poll until the request completes, waiting the Retry-After the server names.
for await (const update of handle.events()) {
  console.log(update.status, update.queuePosition);
}

// The same result models.run() returns. A request that failed or was cancelled rejects here.
const result = await handle.get();

console.log(result.data);
```

```bash cURL theme={null}
# 1. Submit. Router answers 201 with request_id, status_url, response_url and cancel_url.
curl https://api.comfy.org/v2/models/bfl/flux-3-image/requests \
  -H "X-API-Key: $COMFY_API_KEY" \
  -H "Idempotency-Key: $(uuidgen)" \
  -H "Content-Type: application/json" \
  -d "{\"aspect_ratio\": \"16:9\", \"prompt\": \"A mountain landscape at sunset\", \"resolution\": \"1k\"}"

# 2. Poll until status is COMPLETED, waiting the Retry-After seconds each response names.
REQUEST_ID="<request_id from the 201 body>"
curl -i https://api.comfy.org/v2/models/bfl/flux-3-image/requests/$REQUEST_ID/status \
  -H "X-API-Key: $COMFY_API_KEY"

# 3. Collect. 200 with the model's native output, 202 with the status body while it is still running.
curl https://api.comfy.org/v2/models/bfl/flux-3-image/requests/$REQUEST_ID \
  -H "X-API-Key: $COMFY_API_KEY"
```

## Schema

### Input

**aspect\_ratio** `string` (default: "auto")

Output aspect ratio: auto, 21:9, 2:1, 16:9, 3:2, 7:5, 4:3, 5:4, 1:1, 4:5, 3:4, 5:7, 2:3, 9:16, 1:2, or 9:21. auto follows the first reference image when one is present.

**grounding** `boolean` (default: true)

Let the model research the prompt with web search and image search before it generates. Set false to turn both off.

**images** `string | string[]`

One to ten reference images the prompt edits or draws from, each an http(s) URL or a base64 string. A single string is treated as a one-item list. Each image must be at least 256x256 pixels and at most 16 megapixels, with a base64 payload at most 20 MB; inputs are resized to the closest resolution bin, up to 2k.

**prompt** `string` *required*

Text description of the image to generate, or of the edit to apply to the reference images.

**resolution** `string` (default: "1k")

Output resolution class: 768sq, 1k, 1.5k, 2k, or 4k.

**safety\_tolerance** `integer` (default: 2)

Tolerance level for input and output moderation, 0 being most strict.

Range: `0` to `4`

**version** `string` (default: "latest")

Endpoint version. latest serves the current release; dated pinnable release tags are added as they are published.

Generated from the schema Router serves at `GET /v2/models/bfl/flux-3-image/openapi.json`, the same document it validates a call against before the request reaches the provider.

### Output

**cost** `number`

Provider-reported cost in credits, populated once the task is Ready.

Format: `float`

**id** `string` *required*

BFL task identifier.

**progress** `number`

Optional generation progress reported by BFL.

Range: `0` to `1`

Format: `float`

**result** `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.

**result.cost** `number`

Provider-reported cost of the generation. This is BFL's number, not the Comfy charge.

Format: `double`

**result.duration** `number`

Provider-reported generation duration in seconds.

Format: `double`

**result.end\_time** `number`

Provider-reported completion time of the generation, in seconds since the Unix epoch. `double` for the same reason as `start_time`.

Format: `double`

**result.prompt** `string`

The prompt the generation actually ran, after any prompt upsampling.

**result.sample** `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`

**result.seed** `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`

**result.start\_time** `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`

**status** `string` *required*

Task status: Pending, Reasoning, Generating, Ready, Request Moderated, Content Moderated, Error, or Task not found.

## Examples

### Input

```json theme={null}
{
  "aspect_ratio": "16:9",
  "prompt": "A mountain landscape at sunset",
  "resolution": "1k"
}
```

### Output

```json theme={null}
{
  "cost": null,
  "id": "b2e0c1a4-0f2f-4a55-9f2e-2f9a1c0d4e77",
  "progress": null,
  "result": {
    "cost": null,
    "duration": 3.4,
    "end_time": 1767225603.4,
    "prompt": "A watercolor painting of a lighthouse at dawn, soft light on the water",
    "sample": "https://example.invalid/bfl/flux-pro-1.1/sample.png",
    "seed": 2784347701,
    "start_time": 1767225600
  },
  "status": "Ready"
}
```

## 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, and a `413` means the request body was larger than Router accepts. Download generated assets promptly because [result URLs can expire](https://docs.comfy.org/development/comfy-router/reference.md#result-assets).

Any size limit named in a field description above is the provider's own bound on that field, quoted from the provider's specification. Router applies a separate cap to the whole request body, which base64-encoded media counts against: see [request body size](https://docs.comfy.org/development/comfy-router/limitations.md#request-bodies-are-capped).

This page documents one partner model called through Comfy Router. The same `comfy-sdk` / `@comfyorg/sdk` package also ships a second client, for running a whole ComfyUI workflow graph on Comfy Cloud: `Comfy(api_key=...)` / `new Comfy({ apiKey })`, with `client.workflows`, `client.assets` and `client.jobs`. See [Comfy SDKs](https://docs.comfy.org/development/api-development/sdks.md).

> **[Headers](https://docs.comfy.org/development/comfy-router/headers.md)**
>
> Authentication, idempotency, request IDs, error buckets, retry pacing, spend limits.

> **[Using the Router API](https://docs.comfy.org/development/comfy-router/api.md)**
>
> Model discovery, validation errors, retries, and billing.

> **[Limitations](https://docs.comfy.org/development/comfy-router/limitations.md)**
>
> What Router does not do today, and what to use instead.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.