# FLUX.2 [flex]

> Generate images from a text prompt with adjustable inference steps and guidance scale for fine-tuned control over speed, fidelity, and text rendering.

## Overview

- **Endpoint**: `https://queue.modelrunner.run/black-forest-labs/flux-2/flex`
- **Model ID**: `black-forest-labs/flux-2/flex`
- **Category**: text-to-image
- **Kind**: inference
- **Tags**: flux, flux-2, black-forest-labs, text-to-image, image-generation, flex

## Pricing

- **up to 1 megapixels**: $0.05
- **up to 2 megapixels**: $0.1
- **up to 3 megapixels**: $0.15
- **up to 4 megapixels**: $0.2
- **up to 5 megapixels**: $0.25

## Request Lifecycle

This model runs on the ModelRunner **asynchronous queue API** — a single POST does not return the output. Every call requires an `Authorization: Key $MODEL_RUNNER_KEY` header. Run three steps:

1. **Submit** — `POST https://queue.modelrunner.run/black-forest-labs/flux-2/flex` with a JSON body. The response carries request handles only (no output yet):

```json
{
  "status": "IN_QUEUE",
  "request_id": "<21-char id>",
  "status_url": "https://queue.modelrunner.run/black-forest-labs/flux-2/flex/requests/<request_id>/status",
  "response_url": "https://queue.modelrunner.run/black-forest-labs/flux-2/flex/requests/<request_id>",
  "cancel_url": "https://queue.modelrunner.run/black-forest-labs/flux-2/flex/requests/<request_id>/cancel"
}
```

2. **Poll status** — `GET <status_url>` until `status` is `COMPLETED`. Possible values are `IN_QUEUE`, `IN_PROGRESS`, `COMPLETED`, `FAILED`, `CANCELLED`. A `FAILED` request responds with HTTP 400 and an `error` field.

3. **Read result** — `GET <response_url>`. Returns the finished request, including the generated `output`:

```json
{ "id": "<request_id>", "status": "COMPLETED", "output": ..., "input": ... }
```

The JavaScript and Python SDKs below perform steps 2–3 for you. In any language without an SDK (Swift, Go, Kotlin, etc.) you must implement the polling loop and the final result fetch yourself — see the cURL example for the full flow.

### Input Schema

- **`seed`** (`integer | null`, _optional_):
  The same seed and the same prompt given to the same version of the model will output the same image every time.

- **`prompt`** (`string`, _required_):
  The text prompt describing the image to generate.

- **`image_size`** (`ImageSize | ImageSizeEnum`, _optional_):
  The size of the generated image. Use a preset string (e.g. 'landscape_16_9') or a custom {width, height} object.
  - Default: `"landscape_4_3"`
  - Options: `"square_hd"`, `"square"`, `"portrait_4_3"`, `"portrait_16_9"`, `"landscape_4_3"`, `"landscape_16_9"`

- **`output_format`** (`OutputFormatEnum`, _optional_):
  The format of the generated image.
  - Default: `"jpeg"`
  - Options: `"jpeg"`, `"png"`

- **`guidance_scale`** (`number`, _optional_):
  The guidance scale to use for generation. Higher values follow the prompt more literally; lower values give the model more freedom.
  - Default: `3.5`
  - Range: `1.5` to `10`

- **`safety_tolerance`** (`SafetyToleranceEnum`, _optional_):
  The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive.
  - Default: `"2"`
  - Options: `"1"`, `"2"`, `"3"`, `"4"`, `"5"`

- **`num_inference_steps`** (`integer`, _optional_):
  The number of inference steps. More steps generally improve fidelity at the cost of speed.
  - Default: `28`
  - Range: `2` to `50`

- **`enable_safety_checker`** (`boolean`, _optional_):
  If set to true, the safety checker will be enabled.
  - Default: `true`

### Output Schema

_No `Output` schema properties are available._

## Default Example

**Input**

```json
{
  "prompt": "A vintage travel poster for the Swiss Alps at golden hour, bold legible title text reading 'ZERMATT', snow-capped peaks and a red cog railway, warm cinematic lighting, clean typographic layout",
  "image_size": "portrait_4_3",
  "output_format": "png",
  "guidance_scale": 4.5,
  "safety_tolerance": "2",
  "num_inference_steps": 40,
  "enable_safety_checker": true
}
```

**Output**

```json
[
  "https://media.modelrunner.ai/9aQNtaSJ5MflZtkudj5Ga.png"
]
```
## Usage Examples

### cURL

The queue API is asynchronous: submit the request, poll `status_url` until it is `COMPLETED`, then read the result from `response_url`. Requires `jq`.

```bash
# 1. Submit the request (returns request handles, not the output)
SUBMIT=$(curl --silent --request POST \
  --url https://queue.modelrunner.run/black-forest-labs/flux-2/flex \
  --header "Authorization: Key $MODEL_RUNNER_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "prompt": "A vintage travel poster for the Swiss Alps at golden hour, bold legible title text reading '\''ZERMATT'\'', snow-capped peaks and a red cog railway, warm cinematic lighting, clean typographic layout",
  "image_size": "portrait_4_3",
  "output_format": "png",
  "guidance_scale": 4.5,
  "safety_tolerance": "2",
  "num_inference_steps": 40,
  "enable_safety_checker": true
}')

STATUS_URL=$(echo "$SUBMIT" | jq -r '.status_url')
RESPONSE_URL=$(echo "$SUBMIT" | jq -r '.response_url')

# 2. Poll until the request leaves the queue / in-progress state
while true; do
  STATUS=$(curl --silent --url "$STATUS_URL" \
    --header "Authorization: Key $MODEL_RUNNER_KEY" | jq -r '.status')
  echo "Status: $STATUS"
  case "$STATUS" in
    COMPLETED) break ;;
    FAILED|CANCELLED) echo "Request $STATUS"; exit 1 ;;
  esac
  sleep 1
done

# 3. Read the finished request, including the generated output
curl --silent --url "$RESPONSE_URL" \
  --header "Authorization: Key $MODEL_RUNNER_KEY"
```

### JavaScript

```javascript
import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("black-forest-labs/flux-2/flex", {
  input: {
  "prompt": "A vintage travel poster for the Swiss Alps at golden hour, bold legible title text reading 'ZERMATT', snow-capped peaks and a red cog railway, warm cinematic lighting, clean typographic layout",
  "image_size": "portrait_4_3",
  "output_format": "png",
  "guidance_scale": 4.5,
  "safety_tolerance": "2",
  "num_inference_steps": 40,
  "enable_safety_checker": true
}
});

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

### Python

```python
import asyncio
import modelrunner_ai

async def main():
    response = await modelrunner_ai.submit_async(
        "black-forest-labs/flux-2/flex",
        arguments={
  "prompt": "A vintage travel poster for the Swiss Alps at golden hour, bold legible title text reading 'ZERMATT', snow-capped peaks and a red cog railway, warm cinematic lighting, clean typographic layout",
  "image_size": "portrait_4_3",
  "output_format": "png",
  "guidance_scale": 4.5,
  "safety_tolerance": "2",
  "num_inference_steps": 40,
  "enable_safety_checker": true
}
    )
    result = await response.get()
    print(result["output"])

asyncio.run(main())
```

## Additional Resources

- [Playground](https://modelrunner.ai/models/black-forest-labs/flux-2/flex)
- [OpenAPI Schema](https://modelrunner.ai/models/black-forest-labs/flux-2/flex/openapi.json)
- [LLM Instructions](https://modelrunner.ai/models/black-forest-labs/flux-2/flex/llms.txt)