# Flux 3 Action API

> روبوٹ پالیسی ماڈل جو کیمرہ فریمز، جوائنٹ حالت اور ہدایت سے SO-101 بازو کے ایکشن حصوں کی پیش گوئی کرتا ہے

میڈیا کے بجائے، یہ متوقع `actions`، ان کی کنٹرول شرح، کالم لیبلز، اور نئے حصے کی درخواست کرنے سے پہلے عمل میں لائے جانے والے ابتدائی مراحل کی تعداد (`execute_steps`) کے ساتھ JSON واپس کرتا ہے۔ مطلوبہ ان پٹ میں متنی `prompt` (زیادہ سے زیادہ 2000 حروف)، `scene_image_url`، `wrist_image_url`، اور 6 قدروں پر مشتمل `state` شامل ہیں۔ اختیاری تاریخی ان پٹ (`state_history`، `command_history`، تاریخی تصاویر) زمانی سیاق فراہم کرتے ہیں۔ `num_inference_steps` کی حد 1 سے 8 تک اور `guidance_scale` کی حد 1 سے 10 تک ہے۔

- Model id: `flux-3-action/so101`
- Made by: Black Forest Labs
- Category: Video to Video
- Output: json
- Estimated price per run: $0.003 / run (cheapest run $0.003 (3 API credits))
- Run: `POST https://api.doitong.com/v1/run/flux-3-action/so101`
- Quote: `POST https://api.doitong.com/v1/quote/flux-3-action/so101`
- Docs page: https://doitong.com/ur/developers/models/flux-3-action/so101

## Pricing

Price: **$0.003 / run**. Estimated from the typical cost of one run. The quote is exactly what the run charges.

The full example input below costs $0.003 = 3 API credits (1 request × 3 API credits).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.com/v1/quote/flux-3-action/so101` with the same JSON body returns the exact price for that input; the quote is exactly what a run charges. Invalid input is never charged and failed or canceled requests are refunded automatically.

## Input parameters

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `prompt` |  | string | yes |  | 1 – 2000 characters | قدرتی زبان میں لکھی گئی روبوٹ ٹاسک ہدایات۔ |
| `scene_image_url` |  | string (image URL) | yes |  |  | ری سائز کرنے کے بعد 256x256 کی گئی، فکسڈ scene camera کے موجودہ فریم کو دکھانے والی بائیں tile کی تصویر۔ |
| `wrist_image_url` |  | string (image URL) | yes |  |  | موجودہ wrist-camera فریم، دائیں tile میں رکھا گیا اور 256x256 کیا گیا۔ |
| `state` |  | array of number | yes |  | 6 – 6 items | ترتیب سے ناپی گئی state values: shoulder pan اور lift، elbow flex، wrist flex اور roll، سب ڈگری میں، پھر gripper position بطور فیصد۔ |
| `state_history` |  | array of array of number \| null | no |  | 7 – 7 items | Measured-state history؛ نئے episode کے لیے اسے چھوڑا جاتا ہے، بصورت دیگر `command_history` درکار ہے۔ `state` سے فوراً پہلے کے 7 control ticks کی measurements، 30 Hz پر زمانی ترتیب میں فراہم کریں۔ |
| `command_history` |  | array of array of number \| null | no |  | 8 – 8 items | Absolute-command history، جس کے لیے `state_history` درکار ہے؛ آخری row میں حالیہ ترین بھیجا گیا command ہونا چاہیے۔ Rows، 8 observation ticks میں زمانی ترتیب سے، ہر tick پر مؤثر command بتاتی ہیں۔ |
| `history_scene_image_url` |  | string (image URL) \| null | no |  |  | Historical scene-frame ان پٹ، جس کے لیے `state_history` درکار ہے؛ اسے چھوڑنے پر موجودہ فریم استعمال ہوتا ہے۔ فراہم کردہ فریم 7 ticks پہلے کی سب سے ابتدائی history observation ہے۔ |
| `history_wrist_image_url` |  | string (image URL) \| null | no |  |  | سب سے ابتدائی history tick کا wrist-camera فریم؛ `state_history` درکار ہے۔ |
| `num_inference_steps` |  | integer | no | `4` | 1 – 8 | Euler denoising steps کی تعداد؛ checkpoint validation میں 4 steps استعمال ہوئے۔ |
| `guidance_scale` |  | number | no | `3` | 1 – 10 | ویڈیو اور action دونوں کے لیے classifier-free guidance کی طاقت؛ CFG غیر فعال کرنے کے لیے 1.0 مقرر کریں۔ |
| `seed` |  | integer \| null | no |  |  | Sampling seed؛ DROID کے reference-evaluation settings میں 0 اور SO-101 میں 42 ہے۔ اسے غیر متعین چھوڑنے پر seed تصادفی طور پر منتخب ہوتا ہے۔ |

File parameters (`scene_image_url`, `wrist_image_url`, `history_scene_image_url`, `history_wrist_image_url`) take a public `https://` URL, a `data:` URI up to 10 MB, or the `file_url` of an upload from `POST /files`.

## Example input

Required parameters only:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "scene_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
  "wrist_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
  "state": [
    -18.94,
    134.52,
    120.15,
    28.3,
    -32.17,
    27.02
  ]
}
```

A fuller example:

```json
{
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
  "scene_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
  "wrist_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
  "state": [
    -18.94,
    134.52,
    120.15,
    28.3,
    -32.17,
    27.02
  ]
}
```

## Run it

Set `DOITONG_API_KEY` to a key from https://doitong.com/developers/dashboard#keys. `?wait=20` returns the finished request in the same call when it is ready within 20 seconds; otherwise poll `GET /requests/{id}` (it also accepts `?wait=`), or pass `webhook_url`.

### curl

```bash
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/flux-3-action/so101?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "scene_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "wrist_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "state": [
      -18.94,
      134.52,
      120.15,
      28.3,
      -32.17,
      27.02
    ]
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"
```

### JavaScript

```javascript
const API = "https://api.doitong.com/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/flux-3-action/so101?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "scene_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "wrist_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "state": [
      -18.94,
      134.52,
      120.15,
      28.3,
      -32.17,
      27.02
    ]
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
```

### Python

```python
import os
import requests

API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "scene_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "wrist_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "state": [
        -18.94,
        134.52,
        120.15,
        28.3,
        -32.17,
        27.02,
    ],
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/flux-3-action/so101", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
```

### MCP

The MCP server at `https://api.doitong.com/v1/mcp` exposes the tools `search_models`, `get_model`, `quote`, `run`, `get_request`, `cancel_request`, `list_requests`, `create_upload` and `get_account`. A `run` call for this model:

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "flux-3-action/so101",
      "input": {
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
        "scene_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
        "wrist_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
        "state": [
          -18.94,
          134.52,
          120.15,
          28.3,
          -32.17,
          27.02
        ]
      },
      "wait_seconds": 20
    }
  }
}
```

## Response

Every call returns a request object. `status` is one of `queued`, `running`, `succeeded`, `failed`, `canceled`. `outputs` lists the generated files with URLs on our storage (kept forever, or 7 days with `?storage=temporary`; `storage` says which); `output` is the model's own result object with the same URLs.

```json
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "flux-3-action/so101",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 3,
    "usd": "0.003",
    "charged": 3,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "scene_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "wrist_image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "state": [
      -18.94,
      134.52,
      120.15,
      28.3,
      -32.17,
      27.02
    ]
  },
  "output": {
    "actions": [
      [
        1.0
      ]
    ],
    "action_labels": [
      "string"
    ],
    "action_hz": 1.0,
    "execute_steps": 1,
    "seed": 42,
    "timings": {}
  },
  "outputs": [
    {
      "type": "file",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `actions` | array of array of number | پیش گوئی کردہ action array، جس کی زمانی rows control steps کی نمائندگی کرتی ہیں؛ values unclipped ہیں، اس لیے robot پر joint، velocity اور workspace limits نافذ کرنا ضروری ہے۔ 30 Hz پر SO-101، deg اور gripper % میں 42x6 absolute commands فراہم کرتا ہے؛ 15 Hz پر DROID، rad میں 32x8 absolute joint targets اور gripper کا closed fraction فراہم کرتا ہے۔ |
| `action_labels` | array of string | action columns سے مطابقت رکھنے والے نام۔ |
| `action_hz` | number | action rows کی control frequency۔ |
| `execute_steps` | integer | دوبارہ chunk طلب کرنے سے پہلے execute کیے جانے والے ابتدائی actions کی تعداد۔ |
| `seed` | integer | sampling کے دوران استعمال ہونے والا random seed۔ |
| `timings` | object | سرور سے حاصل شدہ timing measurements، سیکنڈ میں۔ |

## Related models

- [Flux 3 Draft Enhance](https://doitong.com/developers/models/blackforestlabs/flux-3/draft-enhance.md) (`blackforestlabs/flux-3/draft-enhance`): $3.48 / run
- [Flux 3 Extend Video](https://doitong.com/developers/models/blackforestlabs/flux-3/extend-video.md) (`blackforestlabs/flux-3/extend-video`): from $0.41 / second
- [Flux 3 Extend Video Draft](https://doitong.com/developers/models/blackforestlabs/flux-3/extend-video/draft.md) (`blackforestlabs/flux-3/extend-video/draft`): $0.12 / second
- [Flux 3 FAST Edit Video](https://doitong.com/developers/models/blackforestlabs/flux-3/edit-video.md) (`blackforestlabs/flux-3/edit-video`): $0.03 / second of input video
- [AMT Interpolation](https://doitong.com/developers/models/amt-interpolation.md) (`amt-interpolation`): $0.000575 / second of processing time
- [AnimateDiff Turbo · Video to Video](https://doitong.com/developers/models/fast-animatediff/turbo/video-to-video.md) (`fast-animatediff/turbo/video-to-video`): $0.00125 / second of processing time
- [AnimateDiff · Video to Video](https://doitong.com/developers/models/fast-animatediff/video-to-video.md) (`fast-animatediff/video-to-video`): $0.00125 / second of processing time
- [Auto-Captioner](https://doitong.com/developers/models/auto-caption.md) (`auto-caption`): $0.10 / video

## Links

- HTML page: https://doitong.com/developers/models/flux-3-action/so101
- All models and guides for AI agents: https://doitong.com/developers/llms.txt
- OpenAPI 3.1 with this model's typed request body: https://doitong.com/developers/openapi.json?model=flux-3-action/so101
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/flux-3-action/so101