Async Jobs

Create async image edit

Submits an image edit request for asynchronous execution. Returns a job ID immediately with HTTP 202. Poll the corresponding GET endpoint with the job ID to retrieve the result. Streaming is not supported for async requests.

Authorization

AuthorizationBearer <token>

Bearer token authentication. Use your MPilot virtual-key JWT or admin JWT. Virtual keys (prefixed with sk-bf-) can also be passed here.

In: header

Header Parameters

x-bf-async-job-result-ttl?integer

Time-to-live in seconds for the job result after completion. Defaults to 3600 (1 hour). After expiry, the job result is automatically cleaned up.

Default3600

Request Body

modelstring

Model identifier in format provider/model

prompt?string

Text prompt describing the edit. Required unless type is background_removal.

imagefile

Image file to edit. Use field name image for a single file or image[] for multiple files.

Formatbinary

mask?file

Optional mask image for inpainting (transparent areas indicate regions to edit)

Formatbinary

type?string

Type of edit operation

Value in"inpainting" | "outpainting" | "background_removal"

n?integer

Number of images to generate

Range1 <= value <= 10

size?string

Size of the output image

Value in"256x256" | "512x512" | "1024x1024" | "1536x1024" | "1024x1536" | "auto"

response_format?string

Format of the response

Default"url"

Value in"url" | "b64_json"

stream?boolean

When true, stream the response via Server-Sent Events

Defaultfalse

background?string

Background type for the image

Value in"transparent" | "opaque" | "auto"

input_fidelity?string

How closely to follow the original image

Value in"low" | "high"

partial_images?integer

Number of partial images to generate when streaming

Range0 <= value <= 3

quality?string

Quality of the output image

Value in"auto" | "high" | "medium" | "low" | "standard"

output_format?string

Output image format

Value in"png" | "webp" | "jpeg"

num_inference_steps?integer

Number of inference steps

seed?integer

Seed for reproducible editing

output_compression?integer

Compression level (0-100%)

Range0 <= value <= 100

negative_prompt?string

What to avoid in the edit

user?string

User identifier for tracking

fallbacks?array<Fallback>

Fallback models to try if primary model fails

Response Body

curl -X POST "https://loading/{AI_GATEWAY_URL}/v1/async/images/edits" \
  -H "x-bf-async-job-result-ttl: 3600" \
  -F model="string" \
  -F image="string"

curl -X POST "https://loading/{AI_GATEWAY_URL}/v1/async/images/edits" \  -H "x-bf-async-job-result-ttl: 3600" \  -F model="string" \  -F image="string"

{
  "id": "string",
  "status": "pending",
  "expires_at": "2019-08-24T14:15:22Z",
  "created_at": "2019-08-24T14:15:22Z",
  "completed_at": "2019-08-24T14:15:22Z",
  "status_code": 0,
  "result": null,
  "error": {
    "event_id": "string",
    "type": "string",
    "is_bifrost_error": true,
    "status_code": 0,
    "error": {
      "type": "string",
      "code": "string",
      "message": "string",
      "param": "string",
      "event_id": "string"
    },
    "extra_fields": {
      "provider": "openai",
      "model_requested": "string",
      "request_type": "string"
    }
  }
}

{
  "event_id": "string",
  "type": "string",
  "is_bifrost_error": true,
  "status_code": 0,
  "error": {
    "type": "string",
    "code": "string",
    "message": "string",
    "param": "string",
    "event_id": "string"
  },
  "extra_fields": {
    "provider": "openai",
    "model_requested": "string",
    "request_type": "string"
  }
}

{
  "event_id": "string",
  "type": "string",
  "is_bifrost_error": true,
  "status_code": 0,
  "error": {
    "type": "string",
    "code": "string",
    "message": "string",
    "param": "string",
    "event_id": "string"
  },
  "extra_fields": {
    "provider": "openai",
    "model_requested": "string",
    "request_type": "string"
  }
}

Create async embedding Create async image generation

On this page

No Headings