## Create a generation

**post** `/generations`

Submit an image generation or edit job. Returns immediately with an opaque job ID to poll via GET /generations/{id}.

### Body Parameters

- `prompt: string`

  Text prompt

- `aspect_ratio: optional "3:1" or "2:1" or "16:9" or 6 more`

  Output aspect ratio

  - `"3:1"`

  - `"2:1"`

  - `"16:9"`

  - `"3:2"`

  - `"1:1"`

  - `"2:3"`

  - `"9:16"`

  - `"1:2"`

  - `"1:3"`

- `image_ref: optional array of object { data, media_type, url }`

  Reference images for style/content guidance. Up to 9 for type 'image', up to 8 for type 'image_edit'.

  - `data: optional string`

    Base64-encoded image data

  - `media_type: optional string`

    MIME type (e.g. image/jpeg). Required with data.

  - `url: optional string`

    Publicly accessible image URL

- `model: optional Model`

  Model identifier. `uni-1` is the default tier; `uni-1-max` produces higher-quality output than `uni-1` at a higher per-image price. Both models are available to all accounts — see Pricing for per-image rates.

  - `"uni-1"`

  - `"uni-1-max"`

- `output_format: optional "png" or "jpeg"`

  Output image format

  - `"png"`

  - `"jpeg"`

- `source: optional object { data, media_type, url }`

  Reference image for guided generation. Provide either url or inline base64 data (not both).

  - `data: optional string`

    Base64-encoded image data

  - `media_type: optional string`

    MIME type (e.g. image/jpeg). Required with data.

  - `url: optional string`

    Publicly accessible image URL

- `style: optional "auto" or "manga"`

  Style preset (auto, manga)

  - `"auto"`

  - `"manga"`

- `type: optional "image" or "image_edit"`

  The kind of generation to perform

  - `"image"`

  - `"image_edit"`

- `user_id: optional string`

  Your end-user's stable opaque identifier (no PII). Forwarded to upstream model providers as their per-user tagging field so trust & safety violations can be attributed to a specific end-user rather than the whole API account. Also used for per-end-user usage breakdowns in /v1/usage. Strongly recommended for partner integrations.

- `web_search: optional boolean`

  Enable web search grounding — the agent can search the web and download reference images before generating.

### Returns

- `Generation = object { id, created_at, model, 5 more }`

  Generation status and output

  - `id: string`

    Generation identifier

  - `created_at: string`

    Creation timestamp

  - `model: Model`

    Model used

    - `"uni-1"`

    - `"uni-1-max"`

  - `state: "queued" or "processing" or "completed" or "failed"`

    Current state of the generation

    - `"queued"`

    - `"processing"`

    - `"completed"`

    - `"failed"`

  - `type: "image" or "image_edit"`

    The kind of generation to perform

    - `"image"`

    - `"image_edit"`

  - `failure_code: optional GenerationFailureCode`

    Machine-readable failure code for programmatic handling

    - `"content_moderated"`

    - `"generation_failed"`

    - `"budget_exhausted"`

    - `"output_not_found"`

    - `"image_too_large"`

    - `"unsupported_format"`

    - `"corrupt_input"`

    - `"invalid_request"`

    - `"rate_limited"`

  - `failure_reason: optional string`

    Human-readable failure description

  - `output: optional array of GenerationOutput`

    Generated outputs (populated on completion)

    - `type: string`

      Media type (e.g. image)

    - `url: string`

      Presigned URL (1hr expiry)

### Example

```http
curl https://agents.lumalabs.ai/v1/generations \
    -H 'Content-Type: application/json' \
    -H "Authorization: Bearer $LUMA_AGENTS_API_KEY" \
    -d '{
          "prompt": "A glass of iced coffee on a marble countertop, morning light streaming through a window"
        }'
```

#### Response

```json
{
  "id": "182bd5e5-6e1a-4fe4-a799-aa6d9a6ab26e",
  "created_at": "created_at",
  "model": "uni-1",
  "state": "queued",
  "type": "image",
  "failure_code": "content_moderated",
  "failure_reason": "failure_reason",
  "output": [
    {
      "type": "type",
      "url": "https://example.com"
    }
  ]
}
```