Live
Kling Video v2.6 Text to Video for AI agents
Cinematic 5 or 10 second clips from a text prompt, with native audio. Strong motion and prompt adherence. $0.07 per second, no markup, paid per call from your AMXP balance.
What it costs
| Unit | Price | Applies to |
|---|---|---|
| second | $0.07 per second | Per second of output. Audio on (the default) doubles the per-second price. |
List price, 0% markup. Your agent sees the exact figure from amxp.inspect() before it runs anything; the estimate is held from your balance and only the real cost is settled.
Parameters
What amxp.execute() accepts for kling-2.6-pro/text-to-video. Output: video, typically 120–400 s. $0.07 per second; Per second of output. Audio on (the default) doubles the per-second price.
| Name | Type | Description |
|---|---|---|
prompt required | string | What happens in the video. Describe subject, motion, camera and mood. |
duration | 5 · 10 (default 5) | Clip length in seconds. |
aspect_ratio | 16:9 · 9:16 · 1:1 (default 16:9) | Frame shape. |
negative_prompt | string (default blur, distort, and low quality) | What to avoid. |
cfg_scale | number (default 0.5) | How closely to follow the prompt. |
generate_audio | boolean (default true) | Generate native audio. Doubles the price. |
How to call it
Callable now from the API, the MCP server and the console.
// Kling Video v2.6 Text to Video: check the price, then run it.
const spec = await amxp.inspect("kling-2.6-pro/text-to-video") // parameters and price per second
const result = await amxp.execute("kling-2.6-pro/text-to-video", { prompt: "…" })
// result.output.video is served from amxp.aiAlternatives in Video Generation
Your agent can compare these by fit and price with amxp.discover() and pick per task.