## Start a generation run

**post** `/runs/generation`

Starts a model generation run in a project canvas using a prompt, workspace, project, optional model, and optional model parameters. Mutating public API requests support an optional Idempotency-Key header for client retries; duplicate keys within two hours return idempotency_duplicate.

### Body Parameters

- `project_id: string`

  Project identifier

- `prompt: string`

  Generation prompt

- `type: "image" or "video" or "audio" or "text"`

  Generation type

  - `"image"`

  - `"video"`

  - `"audio"`

  - `"text"`

- `workspace_id: string`

  Workspace identifier

- `model: optional string`

  Model endpoint ID

- `params: optional map[unknown]`

  Model parameters

### Returns

- `charged_cost: number`

- `estimated_seconds: number`

- `run_id: string`

  Run identifier

- `type: "generation" or "technique" or "action"`

  Run type

  - `"generation"`

  - `"technique"`

  - `"action"`

- `action: optional object { action_id }`

  - `action_id: "split-text" or "find-and-replace-text" or "concat-text" or 34 more`

    Action identifier

    - `"split-text"`

    - `"find-and-replace-text"`

    - `"concat-text"`

    - `"ken-burns-video"`

    - `"color-grade-image"`

    - `"change-image-ar"`

    - `"rotate-image"`

    - `"flip-image"`

    - `"color-filter-image"`

    - `"color-tint-image"`

    - `"filter-color-image"`

    - `"blur-image"`

    - `"duplicate-image"`

    - `"side-by-side-composite"`

    - `"add-shape-to-image"`

    - `"generate-shape-image"`

    - `"add-text-to-image"`

    - `"generate-text-image"`

    - `"qr-code-generator"`

    - `"stitch-videos"`

    - `"split-video"`

    - `"extract-video-frames"`

    - `"color-grade-video"`

    - `"video-to-frame-grid"`

    - `"boomerang-video"`

    - `"reverse-video"`

    - `"video-to-long-exposure"`

    - `"video-effect"`

    - `"color-filter-video"`

    - `"speed-up-video"`

    - `"slow-down-video"`

    - `"duplicate-video"`

    - `"greenscreen-video"`

    - `"resize-video"`

    - `"change-video-ar"`

    - `"split-audio-from-video"`

    - `"merge-audio-into-video"`

- `model: optional object { model_id }`

  - `model_id: string`

    Model identifier

- `poll_url: optional string`

- `project_id: optional string`

  Project identifier

- `technique: optional object { name, technique_id }`

  - `name: string`

    Technique name

  - `technique_id: string`

    Technique identifier

### Example

```http
curl https://app.flora.ai/api/v1/runs/generation \
    -H 'Content-Type: application/json' \
    -H "Authorization: Bearer $FLORA_API_KEY" \
    -d '{
          "project_id": "prj_abc123",
          "prompt": "A cinematic product photo of a ceramic mug on a sunlit table",
          "type": "image",
          "workspace_id": "ws_abc123"
        }'
```

#### Response

```json
{
  "charged_cost": 0,
  "estimated_seconds": 0,
  "run_id": "run_abc123",
  "type": "generation",
  "action": {
    "action_id": "split-text"
  },
  "model": {
    "model_id": "t2i-flux-2-pro"
  },
  "poll_url": "https://example.com",
  "project_id": "prj_abc123",
  "technique": {
    "name": "name",
    "technique_id": "tech_abcd1234"
  }
}
```