Interpolate first and last frames

Primary agent path

Use beatra.videos.interpolate only when both a first and last image define the transition. Preserve their order.

1. Upload both local frames and optional driving audio.
2. Call beatra.models.list with capability: "frames_to_video" for current media combinations, duration, resolution, audio support, and prices.
3. Describe the movement between the endpoints, not two disconnected scenes.
4. Submit once with one client_request_id; poll with beatra.tasks.get.

AI guide

Tool arguments

{
  "prompt": "The product rises and rotates smoothly between the two views",
  "first_frame": { "type": "artifact", "artifact_id": "artifact_start" },
  "last_frame": { "type": "artifact", "artifact_id": "artifact_end" },
  "driving_audio": { "type": "artifact", "artifact_id": "artifact_optional_audio" },
  "resolution": "720p",
  "duration": 6,
  "client_request_id": "vid-frames-opaque-1"
}

Omit driving_audio when it is unsupported or unnecessary. Image-driven aspect-ratio rules come from model discovery.

Models, controls, and cost

Common controls are prompt, negative_prompt, resolution, duration, aspect_ratio, seed, enhance_prompt, and watermark. Use each only according to the selected model's metadata.

Use beatra.models.list instead of a static model table. It returns selectable models, accepted frame/audio combinations, constraints, defaults, ignored fields, and customer prices. Resolution and duration normally affect cost; do not silently change them.

MiniMax H3

Set model: "minimax-h3" to interpolate with MiniMax H3. Both frames and a prompt are required. Output is 2K, duration is 4–15 seconds, and the first frame determines the output ratio. H3 accepts watermark but not driving audio or the other optional controls. Both input images are free and generated output costs 590 credits per second.

Task status and recovery

Poll the same task through queued and running. A lost create response may be retried only with identical arguments and the same client_request_id. Swapping either frame or changing audio, prompt, or output settings requires a new ID.

REST API

Direct protocol integrations may use POST /v1/videos/frames-to-video. Follow the generated API operation. Skill + MCP is the recommended integration; REST serves custom applications.