Kling 3 first and last frame API: request, limits and a gotcha

To make a Kling 3 clip that starts and ends on your images, send model: "kling-3" and frame_images with a first_frame and a last_frame to POST /v1/videos, and set duration from 4 to 15 seconds. The gotcha: in current code aspect_ratio reaches the model only for text-to-video, so crop your first frame to the shape you want before you send it.

Sume facts are from Video generation and the catalog and provider code, read 2026-09-29; Kling's support for first/last frame is from its capability map.

What does the request look like?

One entry per frame, each with type: "image_url", an image_url.url and a frame_type. Send a first_frame along with the last_frame.

curl -X POST https://api.sume.com/v1/videos \
  -H "Authorization: Bearer $SUME_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: kling-fl-002" \
  -d '{
    "model": "kling-3",
    "prompt": "Camera pushes in as she turns toward the window.",
    "frame_images": [
      {"type":"image_url","image_url":{"url":"https://example.com/a.png"},"frame_type":"first_frame"},
      {"type":"image_url","image_url":{"url":"https://example.com/b.png"},"frame_type":"last_frame"}
    ],
    "duration": 8,
    "generate_audio": false
  }'

What are the limits?

Why did my aspect ratio change?

For image-to-video the request builder passes the frames, prompt, duration and audio flag, not aspect_ratio. The output follows your first frame's shape. For a 9:16 clip, send a 9:16 first frame.

What does a clip cost?

Sume bills provider list × 1.25 reserved on submit. Audio is on unless you send generate_audio: false: an 8-second clip reserves $1.12 silent or $1.68 with audio, before the agent fee.