> **Building with AI coding agents?** Install the authstack plugin with one command. This equips your agent with accurate Scalekit implementation patterns.
>
> **Recommended** (the `-y` flags skip prompts, so the command runs without an interactive terminal):
> ```bash
> npx -y @scalekit-inc/cli setup -y
> ```
>
> Global:
> ```bash
> npm install -g @scalekit-inc/cli
> scalekit setup -y
> ```
>
> Supports Claude Code, Cursor, GitHub Copilot, Codex + skills for other Agent Skills-compatible agents in `~/.agents/skills`.
> Skills: integrate-agentkit, implement-saaskit, add-mcp-oauth, implement-sso, implement-scim.
> [Full setup guide](https://docs.scalekit.com/dev-kit/build-with-ai/)

---

# Connect AI agents to Apiframe

The Apiframe connector lets your AI agent act in each user's Apiframe account. Each user connects their own Apiframe API key once, and Scalekit sends it with every call, so your agent never handles credentials. It comes with 22 tools.

**Authentication:** API Key
**Categories:** AI, Media
**Tools:** 22: 7 read, 14 write, 1 destructive
**Users sign in with:** API key
**Built by:** Scalekit connector
**Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=APIFRAME)

## Setup

1. ### Install the SDK

   **Node.js**

   ```bash
   npm install @scalekit-sdk/node dotenv
   ```

   **Python**

   ```bash
   pip install scalekit-sdk-python python-dotenv
   ```

2. ### Set your credentials

   Add your Scalekit credentials to your `.env` file. Find values in **[app.scalekit.com](https://app.scalekit.com)** > **Developers** > **API Credentials**.

   ```sh title=".env"
   SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
   SCALEKIT_CLIENT_ID=<your-client-id>
   SCALEKIT_CLIENT_SECRET=<your-client-secret>
   ```

3. ### Create the Apiframe connection

   In **AgentKit > Connections**, create an Apiframe connection. The name you give it is the `connection_name` your code passes. See [Configure connections](/agentkit/connections/).

4. ### Authorize a user and make your first call

   **Node.js** (`quickstart.mts`)

   ```typescript
   import { ScalekitClient } from '@scalekit-sdk/node'
   import 'dotenv/config'
   import { createInterface } from 'node:readline/promises'

   const scalekit = new ScalekitClient(
     process.env.SCALEKIT_ENVIRONMENT_URL,
     process.env.SCALEKIT_CLIENT_ID,
     process.env.SCALEKIT_CLIENT_SECRET,
   )
   const actions = scalekit.actions

   const connector = 'apiframe'
   const identifier = 'user_123'

   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize Apiframe:', link)
   const rl = createInterface({ input: process.stdin, output: process.stdout })
   await rl.question('Press Enter after authorizing...')
   rl.close()

   // Make your first call
   const result = await actions.executeTool({
     connector,
     identifier,
     toolName: 'apiframe_jobs_list',
     toolInput: {},
   })
   console.log(result)
   ```

   ```bash
   npx tsx quickstart.mts
   ```

   **Python** (`quickstart.py`)

   ```python
   import os
   from scalekit import ScalekitClient
   from dotenv import load_dotenv
   load_dotenv()

   scalekit_client = ScalekitClient(
       env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"),
       client_id=os.getenv("SCALEKIT_CLIENT_ID"),
       client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
   )
   actions = scalekit_client.actions

   connection_name = "apiframe"
   identifier = "user_123"

   # Generate an authorization link for the user
   link_response = actions.get_authorization_link(
       connection_name=connection_name,
       identifier=identifier,
   )
   print("Authorize Apiframe:", link_response.link)
   input("Press Enter after authorizing...")

   # Make your first call
   result = actions.execute_tool(
       tool_input={},
       tool_name="apiframe_jobs_list",
       connection_name=connection_name,
       identifier=identifier,
   )
   print(result)
   ```

   ```bash
   python quickstart.py
   ```

   Each user opens the link once and enters their Apiframe credentials there. See [Authorize a user](/agentkit/tools/authorize/) for the full flow and statuses.

## Tools

Pass the exact name to `execute_tool`, with an input like each tool's example. To ask for a tool that's missing, use the [request form](https://scalekitsupport.portal.usepylon.com/forms/request-a-connector-tool).

**Node.js**

```typescript
const result = await actions.executeTool({
  toolName: 'apiframe_asset_get',
  toolInput: {
    asset_id: '<asset_id>',
  },
  connector: 'apiframe',
  identifier: 'user_123',
})
```

**Python**

```python
result = actions.execute_tool(
    tool_name="apiframe_asset_get",
    tool_input={
        "asset_id": "<asset_id>",
    },
    connection_name="apiframe",
    identifier="user_123",
)
```

`result.data` is the app's response as JSON, and `result.execution_id` (`executionId` in Node.js) is the ID of the call.

### `apiframe_asset_get`

Get Media Asset · Read-only

Get a stored media asset.
Returns its status, URL and metadata.
Only assets created by your team are accessible.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `asset_id` (`string`, required): ID of the asset, from apiframe_asset_create. Example: ast_01JC9B3C4D5E6F7G8H9J0K1L2M.

Example input: `{"asset_id":"<asset_id>"}`

### `apiframe_job_get`

Get Job · Read-only

Get the status, progress and, when complete, the result of one generation job.
Returns status (QUEUED, PROCESSING, COMPLETED, FAILED or CANCELLED), progress and result with the output image, video or audio URLs.
Poll this after any generate, edit, upscale or action tool until status is COMPLETED or FAILED.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `job_id` (`string`, required): ID of the job, returned by the tool that started it. Example: job_01JC8Z3QH5V7K9M2N4P6R8T0W2.

Example input: `{"job_id":"<job_id>"}`

### `apiframe_jobs_list`

List Jobs · Read-only

List generation jobs, newest first, filtered by status, model or text search.
Returns jobs with id, model, status, progress, created time and result, plus a cursor for the next page.
Use apiframe_job_get to poll one job.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cursor` (`string`, optional): Cursor from the previous page's response, for the next page. Example: eyJjcmVhdGVkQXQiOiIyMDI2LTExLTE2In0.
- `limit` (`integer`, optional): Jobs per page. Defaults to 20. Example: 20.
- `model` (`string`, optional): Only jobs for this model id. Example: flux-2-pro.
- `scope` (`string`, optional): user (default) lists your own jobs; team lists every job in the team (admins only). Example: user. One of: `user`, `team`.
- `search` (`string`, optional): Text to search for in job prompts. Example: snowy cabin.
- `status` (`string`, optional): Only jobs with this status. Example: COMPLETED. One of: `QUEUED`, `PROCESSING`, `COMPLETED`, `FAILED`, `CANCELLED`.

Example input: `{}`

### `apiframe_lora_get`

Get LoRA · Read-only

Get one LoRA, including its training status.
Returns the LoRA's id, name, subject kind, status and timestamps.
Use this to poll training until the LoRA is ready.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `lora_id` (`string`, required): ID of the LoRA, from apiframe_loras_list. Example: lora_01JC9A2B3C4D5E6F7G8H9J0K1L.

Example input: `{"lora_id":"<lora_id>"}`

### `apiframe_loras_list`

List LoRAs · Read-only

List the team's trained Flux LoRAs (AI photo models of a person, style or object).
Returns each LoRA's id, name, subject kind, status and created time, plus a cursor.
Use an id as loraId in apiframe_image_generate with model flux-lora.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `cursor` (`string`, optional): Cursor from the previous page's response. Example: eyJpZCI6ImxvcmFfMTIzIn0.
- `include_archived` (`string`, optional): true also lists archived LoRAs. Example: false. One of: `true`, `false`.
- `limit` (`integer`, optional): LoRAs per page. Defaults to 24. Example: 24.

Example input: `{}`

### `apiframe_me_get`

Get Account · Read-only

Get the authenticated user, their team with its credit balance and plan, and the API key in use.
Returns user, team (credits, plan) and apiKey details.
Use this to check the connection and remaining credits.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs: none.

Example input: `{}`

### `apiframe_models_list`

List Models · Read-only

List Apiframe's model catalog for image, video and music generation.
Returns each model's id, label, description, supported controls and credit cost range.
Use a model id as the model input of the generate tools.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `modality` (`string`, optional): Only models of this kind. Example: image. One of: `image`, `video`, `music`.

Example input: `{}`

### `apiframe_asset_create`

Create Media Asset · Write

Download media from a URL and store it in Apiframe storage as a reusable asset.
Returns the asset id, status and URL; reference it as asset://<id> in any media URL field of a generation request.
Use this for inputs you will reuse across many jobs.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `type` (`string`, required): Kind of media. Example: image. One of: `image`, `video`, `audio`.
- `url` (`string`, required): Public URL of the media to store. Example: https://example.com/brand-logo.png.

Example input: `{"type":"image","url":"<url>"}`

### `apiframe_image_background_remove`

Remove Image Background · Write

Start a background removal job that returns a transparent PNG.
Returns the job id; the cut-out image is in the job's result.
Poll apiframe_job_get. bria-bg-remove is highest quality; 851-bg-remove is cheaper. Spends credits.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `model` (`string`, required): Background removal model: bria-bg-remove or 851-bg-remove. Example: bria-bg-remove.
- `parameters` (`object`, required): The model's params block with the image URL, merged into the body: {"briaBgRemoveParams": {"image": <url>}} or {"lab851BgRemoveParams": {"image": <url>, "background_type": "rgba"}}. Required. Example: {"briaBgRemoveParams": {"image": "https://example.com/product.jpg"}}
- `webhook_events` (`array`, optional): Which events to send to webhook_url: progress, completed and/or failed. Example: ["completed", "failed"]
- `webhook_url` (`string`, optional): HTTPS URL Apiframe calls when the job reports progress, completes or fails. Leave empty to poll apiframe_job_get instead. Example: https://example.com/webhooks/apiframe.

Example input: `{"model":"<model>","parameters":{}}`

### `apiframe_image_edit`

Edit Image (Inpaint or Outpaint) · Write

Start an inpaint or outpaint job on an existing image with Flux Fill Pro.
Returns the job id; the edited image is in the job's result.
Poll apiframe_job_get. Spends credits.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `params` (`object`, required): Flux Fill options: image (URL), prompt, mode inpaint (with a mask image URL) or outpaint (with an outpaint preset: Zoom out 1.5x, Zoom out 2x, Make square, Left outpaint, Right outpaint, Top outpaint or Bottom outpaint), and optional steps, guidance, output_format (jpg or png) and seed. Example: {"image": "https://example.com/room.jpg", "prompt": "a large window with a sea view", "mode": "inpaint", "mask": "https://example.com/mask.png"}
- `webhook_events` (`array`, optional): Which events to send to webhook_url: progress, completed and/or failed. Example: ["completed", "failed"]
- `webhook_url` (`string`, optional): HTTPS URL Apiframe calls when the job reports progress, completes or fails. Leave empty to poll apiframe_job_get instead. Example: https://example.com/webhooks/apiframe.

Example input: `{"params":{"image":"https://example.com/room.jpg","prompt":"a large window with a sea view","mode":"inpaint","mask":"https://example.com/mask.png"}}`

### `apiframe_image_generate`

Generate Image · Write

Start an image generation job with any supported model: Midjourney, Flux, Nano Banana, Seedream, Ideogram, Imagen, GPT Image, DALL-E, Stable Diffusion, Kling, Qwen, Wan, Grok, Reve or a trained Flux LoRA.
Returns the job id and status; the images are in the job's result.
Poll apiframe_job_get or set webhook_url. Spends credits. Use apiframe_models_list for model ids.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `model` (`string`, required): Image model id from apiframe_models_list (modality image), such as midjourney, flux-2-pro, nano-banana-pro, seedream-4.5, ideogram-v3-quality, imagen-4, gpt-image-2 or flux-lora. Example: flux-2-pro.
- `prompt` (`string`, required): Text prompt describing what to generate. Example: A cozy cabin in a snowy pine forest at dusk, warm light in the windows, cinematic.
- `parameters` (`object`, optional): Model-specific options, merged into the request body as the model's params block, such as {"fluxParams": {...}} for Flux models, {"midjourneyParams": {...}} for Midjourney, {"nanoBananaParams": {...}}, {"seedreamParams": {...}}, {"ideogramParams": {...}} (required for ideogram-character) or {"fluxLoraParams": {"loraId": ...}} (required for flux-lora). Typical options are aspect_ratio, output_format, seed and reference images. Example: {"fluxParams": {"aspect_ratio": "16:9", "output_format": "png"}}
- `webhook_events` (`array`, optional): Which events to send to webhook_url: progress, completed and/or failed. Example: ["completed", "failed"]
- `webhook_url` (`string`, optional): HTTPS URL Apiframe calls when the job reports progress, completes or fails. Leave empty to poll apiframe_job_get instead. Example: https://example.com/webhooks/apiframe.

Example input: `{"model":"<model>","prompt":"<prompt>"}`

### `apiframe_image_upscale`

Upscale Image · Write

Start an image upscale job with Topaz (realistic photos) or Clarity (creative, invents detail).
Returns the job id; the upscaled image is in the job's result.
Poll apiframe_job_get. Spends credits (Topaz is priced by output megapixels).

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `model` (`string`, required): Upscale model: topaz-image-upscale or clarity-upscale. Example: topaz-image-upscale.
- `parameters` (`object`, required): The model's params block with the image URL, merged into the body: {"topazUpscaleParams": {"image": <url>, "upscale_factor": 2, "model_type": "standard-v2"}} or {"clarityUpscaleParams": {"image": <url>, "scale_factor": 2, "prompt": ...}}. Required. Example: {"topazUpscaleParams": {"image": "https://example.com/photo.jpg", "upscale_factor": 2}}
- `webhook_events` (`array`, optional): Which events to send to webhook_url: progress, completed and/or failed. Example: ["completed", "failed"]
- `webhook_url` (`string`, optional): HTTPS URL Apiframe calls when the job reports progress, completes or fails. Leave empty to poll apiframe_job_get instead. Example: https://example.com/webhooks/apiframe.

Example input: `{"model":"<model>","parameters":{}}`

### `apiframe_midjourney_action`

Run Midjourney Action · Write

Run a follow-up action on a completed Midjourney image job: upsample or variation of one grid image, or inpaint, outpaint (zoom) or pan.
Returns a new job id; the result is in that job.
Poll apiframe_job_get. Spends credits.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `action` (`string`, required): upsample or variation (pick a grid image with index), inpaint (needs mask and prompt), outpaint (needs zoom_ratio) or pan (needs direction). Example: upsample. One of: `upsample`, `variation`, `inpaint`, `outpaint`, `pan`.
- `parent_job_id` (`string`, required): ID of the completed Midjourney job to act on, from apiframe_jobs_list or the generation call. Example: job_01JC8Z3QH5V7K9M2N4P6R8T0W2.
- `direction` (`string`, optional): For pan: which way to extend the image. Example: left. One of: `up`, `down`, `left`, `right`.
- `index` (`integer`, optional): Which of the parent's grid images, for upsample and variation to use, 1 to 4. Example: 1.
- `mask` (`string`, optional): For inpaint: URL of a mask image (white marks the area to repaint). Example: https://example.com/mask.png.
- `prompt` (`string`, optional): For inpaint: what to paint in the masked area. Example: a red umbrella.
- `webhook_events` (`array`, optional): Which events to send to webhook_url: progress, completed and/or failed. Example: ["completed", "failed"]
- `webhook_url` (`string`, optional): HTTPS URL Apiframe calls when the job reports progress, completes or fails. Leave empty to poll apiframe_job_get instead. Example: https://example.com/webhooks/apiframe.
- `zoom_ratio` (`number`, optional): For outpaint: how far to zoom out, such as 1.5 or 2. Example: 1.5.

Example input: `{"action":"upsample","parent_job_id":"<parent_job_id>"}`

### `apiframe_music_generate`

Generate Music · Write

Start a music generation job with Suno, Udio, Producer, Lyria 3, ElevenLabs Music or Mureka.
Returns the job id; the tracks (two per call for Suno, Udio, Producer and Mureka) are in the job's result.
Poll apiframe_job_get. Spends credits. Use apiframe_suno_action or apiframe_udio_action to extend or remix a result.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `model` (`string`, required): Music model: suno, udio, producer, lyria-3-clip, lyria-3-pro, elevenlabs-music or mureka. Example: suno.
- `parameters` (`object`, optional): Model-specific options, merged into the request body as the model's params block, such as {"sunoParams": {"custom_mode": true, "title": ..., "style": ..., "instrumental": false, "model_version": "V5"}} or {"udioParams": {...}}, {"lyriaParams": {...}}, {"elevenlabsParams": {...}}. Example: {"sunoParams": {"instrumental": true, "model_version": "V5"}}
- `prompt` (`string`, optional): Description of the song, or its lyrics in Suno custom mode. Example: A cozy cabin in a snowy pine forest at dusk, warm light in the windows, cinematic.
- `webhook_events` (`array`, optional): Which events to send to webhook_url: progress, completed and/or failed. Example: ["completed", "failed"]
- `webhook_url` (`string`, optional): HTTPS URL Apiframe calls when the job reports progress, completes or fails. Leave empty to poll apiframe_job_get instead. Example: https://example.com/webhooks/apiframe.

Example input: `{"model":"<model>"}`

### `apiframe_suno_action`

Run Suno Action · Write

Run a follow-up action on a completed Suno job: extend a track, cover it in a new style, add vocals, or split it into stems.
Returns a new job id; the result is in that job.
Poll apiframe_job_get. Spends credits.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `action` (`string`, required): extend (continue from continue_at), cover (new style, same melody), add_vocals (needs prompt) or stems (split vocals and instrumental). Example: extend. One of: `extend`, `cover`, `add_vocals`, `stems`.
- `parent_job_id` (`string`, required): ID of the completed Suno job to act on, from apiframe_jobs_list or the generation call. Example: job_01JC8Z3QH5V7K9M2N4P6R8T0W2.
- `audio_weight` (`number`, optional): For cover: how closely to follow the original audio, 0 to 1. Example: 0.6.
- `continue_at` (`number`, optional): For extend: the second in the track to continue from. Example: 60.
- `index` (`integer`, optional): Which of the parent's tracks to use, 1 to 2. Example: 1.
- `negative_tags` (`string`, optional): Styles to avoid. Example: heavy metal.
- `prompt` (`string`, optional): Lyrics or description for the new part (required for add_vocals). Example: [Verse] Walking home under city lights.
- `style` (`string`, optional): Music style tags for the new track. Example: synthwave, dreamy, female vocals.
- `title` (`string`, optional): Title for the new track. Example: City Lights (Extended)
- `track_id` (`string`, optional): ID of the parent's track to use, from its result.tracks[].id. Use instead of index. Example: trk_9f8e7d6c.
- `webhook_events` (`array`, optional): Which events to send to webhook_url: progress, completed and/or failed. Example: ["completed", "failed"]
- `webhook_url` (`string`, optional): HTTPS URL Apiframe calls when the job reports progress, completes or fails. Leave empty to poll apiframe_job_get instead. Example: https://example.com/webhooks/apiframe.

Example input: `{"action":"extend","parent_job_id":"<parent_job_id>"}`

### `apiframe_udio_action`

Run Udio Action · Write

Run a follow-up action on a completed Udio job: extend a song by up to 32 seconds before or after, or remix it.
Returns a new job id; the result is in that job.
Poll apiframe_job_get. Spends credits.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `action` (`string`, required): extend or remix. Example: extend. One of: `extend`, `remix`.
- `parent_job_id` (`string`, required): ID of the completed Udio job to act on, from apiframe_jobs_list or the generation call. Example: job_01JC8Z3QH5V7K9M2N4P6R8T0W2.
- `index` (`integer`, optional): Which of the parent's songs to use, 1 to 2. Example: 1.
- `lyrics` (`string`, optional): Lyrics for the new section. Example: We run until the morning comes.
- `model` (`string`, optional): Udio model version. Example: udio32-v1.5. One of: `udio32-v1.5`, `udio32-v1`, `udio32-v2`, `udio130-v1.5`, `udio130-v1`.
- `output_length` (`number`, optional): For extend: seconds to add, 1 to 32. Example: 32.
- `placement` (`string`, optional): For extend: where to add audio. Example: after-add-section. One of: `after-add-section`, `after-add-outro`, `before-add-section`, `before-add-intro`.
- `prompt` (`string`, optional): Style description for the new audio. Example: upbeat indie pop with bright guitars.
- `remix_strength` (`number`, optional): For remix: how far from the original, 0.1 to 1. Example: 0.5.
- `seed` (`integer`, optional): Random seed for reproducible results. Example: 42.
- `track_id` (`string`, optional): ID of the parent's track to use, from its result.tracks[].id. Use instead of index. Example: trk_9f8e7d6c.
- `webhook_events` (`array`, optional): Which events to send to webhook_url: progress, completed and/or failed. Example: ["completed", "failed"]
- `webhook_url` (`string`, optional): HTTPS URL Apiframe calls when the job reports progress, completes or fails. Leave empty to poll apiframe_job_get instead. Example: https://example.com/webhooks/apiframe.

Example input: `{"action":"extend","parent_job_id":"<parent_job_id>"}`

### `apiframe_udio_audio_upload`

Upload Audio to Udio · Write

Copy audio from a public URL to Udio's storage so Udio generations can use it as a style reference or voice.
Returns a job id; its result.url is the handle to pass as udioParams.style_ref.file or udioParams.voice.file.
Poll apiframe_job_get for the URL.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `audio_url` (`string`, required): Public URL of the audio file to upload. Example: https://example.com/reference.mp3.
- `webhook_events` (`array`, optional): Which events to send to webhook_url: progress, completed and/or failed. Example: ["completed", "failed"]
- `webhook_url` (`string`, optional): HTTPS URL Apiframe calls when the job reports progress, completes or fails. Leave empty to poll apiframe_job_get instead. Example: https://example.com/webhooks/apiframe.

Example input: `{"audio_url":"<audio_url>"}`

### `apiframe_udio_lyrics_write`

Write Lyrics with Udio · Write

Have Udio write song lyrics from a description, without generating audio.
Returns a job id; within seconds its result holds lyrics, instrumental and optional tempo.
Poll apiframe_job_get, then pass the lyrics to apiframe_music_generate with model udio.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `prompt` (`string`, required): What the song is about and its mood. Example: A hopeful song about moving to a new city.
- `duration` (`integer`, optional): Length of the song you plan to generate, in seconds, so the lyrics fit (about 8 lines at 32 seconds, 30 at 130). Example: 130.
- `lyrics` (`string`, optional): Partial lyrics to continue or refine. Example: New streets, new lights.
- `webhook_events` (`array`, optional): Which events to send to webhook_url: progress, completed and/or failed. Example: ["completed", "failed"]
- `webhook_url` (`string`, optional): HTTPS URL Apiframe calls when the job reports progress, completes or fails. Leave empty to poll apiframe_job_get instead. Example: https://example.com/webhooks/apiframe.

Example input: `{"prompt":"<prompt>"}`

### `apiframe_video_edit`

Edit Video · Write

Start an instruction-based video edit job (restyle, replace or transform a clip) with Wan 2.7 VideoEdit.
Returns the job id; the edited video is in the job's result.
Poll apiframe_job_get. Spends credits per second; set duration to cap billing.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `params` (`object`, required): Wan VideoEdit options: video (URL), and optional reference_image, negative_prompt, resolution (720p or 1080p), aspect_ratio, audio_setting (auto or origin), duration in seconds and seed. Example: {"video": "https://example.com/clip.mp4", "resolution": "720p", "duration": 5}
- `prompt` (`string`, required): Instruction describing the change to make. Example: Turn the scene into a watercolor painting.
- `webhook_events` (`array`, optional): Which events to send to webhook_url: progress, completed and/or failed. Example: ["completed", "failed"]
- `webhook_url` (`string`, optional): HTTPS URL Apiframe calls when the job reports progress, completes or fails. Leave empty to poll apiframe_job_get instead. Example: https://example.com/webhooks/apiframe.

Example input: `{"params":{"video":"https://example.com/clip.mp4","resolution":"720p","duration":5},"prompt":"<prompt>"}`

### `apiframe_video_generate`

Generate Video · Write

Start a video generation job with any supported model: Kling, Veo, Sora, Seedance, Hailuo, Luma, Wan, Runway, Midjourney Video, Grok or Flux.
Returns the job id; the video URL is in the job's result.
Poll apiframe_job_get or set webhook_url. Spends credits, often per second of video. Use apiframe_models_list for model ids.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `model` (`string`, required): Video model id from apiframe_models_list (modality video), such as kling-3.0, veo-3.1, sora-2, seedance-2, hailuo-2.3, luma-ray-2, wan-2.7 or runway-gen4-turbo. Example: kling-3.0.
- `parameters` (`object`, optional): Model-specific options, merged into the request body as the model's params block, such as {"klingParams": {"duration": 5, "start_image": <url>}}, {"veoParams": {...}}, {"soraParams": {...}} or {"seedanceParams": {...}}. Typical options are duration, aspect_ratio, resolution and a start image for image-to-video. Example: {"klingParams": {"duration": 5, "mode": "standard"}}
- `prompt` (`string`, optional): Text prompt describing what to generate. Example: A cozy cabin in a snowy pine forest at dusk, warm light in the windows, cinematic.
- `webhook_events` (`array`, optional): Which events to send to webhook_url: progress, completed and/or failed. Example: ["completed", "failed"]
- `webhook_url` (`string`, optional): HTTPS URL Apiframe calls when the job reports progress, completes or fails. Leave empty to poll apiframe_job_get instead. Example: https://example.com/webhooks/apiframe.

Example input: `{"model":"<model>"}`

### `apiframe_video_upscale`

Upscale Video · Write

Start a Topaz video upscale and frame-interpolation job, up to 4K.
Returns the job id; the upscaled video is in the job's result.
Poll apiframe_job_get. Spends credits per second of video.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `params` (`object`, required): Topaz Video options: video (URL), target_resolution (720p, 1080p or 4k), target_fps (such as 30 or 60), and optional enhance_model and subject_detection. Example: {"video": "https://example.com/clip.mp4", "target_resolution": "1080p", "target_fps": 30}
- `webhook_events` (`array`, optional): Which events to send to webhook_url: progress, completed and/or failed. Example: ["completed", "failed"]
- `webhook_url` (`string`, optional): HTTPS URL Apiframe calls when the job reports progress, completes or fails. Leave empty to poll apiframe_job_get instead. Example: https://example.com/webhooks/apiframe.

Example input: `{"params":{"video":"https://example.com/clip.mp4","target_resolution":"1080p","target_fps":30}}`

### `apiframe_lora_delete`

Archive LoRA · Destructive

Archive a LoRA so it stops appearing in listings and can no longer be used.
Returns no content (204), also when it was already archived.
Use apiframe_loras_list with include_archived true to see archived LoRAs.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `lora_id` (`string`, required): ID of the LoRA to archive, from apiframe_loras_list. Example: lora_01JC9A2B3C4D5E6F7G8H9J0K1L.

Example input: `{"lora_id":"<lora_id>"}`

## Related

Other AI connectors ([all 216](/agentkit/connectors/?category=ai)):

- [Chorus](/agentkit/connectors/chorus/): Scalekit connector, Username and password, 9 tools
- [Gong](/agentkit/connectors/gong/): Scalekit connector, OAuth, 69 tools
- [Jiminny](/agentkit/connectors/jiminny/): Scalekit connector, Access token, 27 tools


---

## More Scalekit documentation

| Resource | What it contains | When to use it |
|----------|-----------------|----------------|
| [/llms.txt](/llms.txt) | Structured index with routing hints per product area | Start here — find which documentation set covers your topic before loading full content |
| [/llms-full.txt](/llms-full.txt) | Complete documentation for all Scalekit products in one file | Use when you need exhaustive context across multiple products or when the topic spans several areas |
| [sitemap-0.xml](https://docs.scalekit.com/sitemap-0.xml) | Full URL list of every documentation page | Use to discover specific page URLs you can fetch for targeted, page-level answers |
