Text to Video

kimi-h3

Kimi H3 text-to-video and image-to-video generation via the configured gputw provider

POST /v1/videos/generationsAsync generationFixed Credit pricing

Quick start

Submit a request with this public model ID. The API immediately returns a normalized job; poll GET /v1/jobs/{jobId} while its status is queued or running.

curl -X POST "https://api.artany.ai/v1/videos/generations" \
  -H "Authorization: Bearer $ARTANY_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: unique-request-id" \
  -d '{"model":"kimi-h3","prompt":"A cinematic slow orbit around a mountain lake at sunrise","duration":5,"resolution":"768p","aspect_ratio":"16:9"}'

Request

Headers

Header	Required	Description
Authorization	Yes	Bearer token for an Artany API key.
Content-Type	Yes	Must be application/json.
Idempotency-Key	Recommended	8–128 characters. Reusing it with an identical request prevents duplicate jobs and charges.

Body

{
  "model": "kimi-h3",
  "prompt": "A cinematic slow orbit around a mountain lake at sunrise",
  "duration": 5,
  "resolution": "768p",
  "aspect_ratio": "16:9"
}

Request Parameters

Only fields in this model’s public request contract are shown. Defaults are applied before validation and quoting.

Note:Supports text-to-video and first-frame image-to-video through one public model. Resolution and aspect ratio deterministically select the output canvas.

modelstringrequireddefault: "kimi-h3"

Stable public model ID for this request.

promptstringrequired

Video instruction. Describe the subject, motion, scene, visual style, and camera behavior.

Length: 1–3500

image_urlsarray<string>

Optional first-frame image URL.

Items: 0–1

Provide at most one image. When present, the request uses image-to-video generation.
Image-to-video follows the source image canvas through the provider's image-size matching behavior.

Note:Do not send resolution or aspect_ratio together with image_urls.

durationintegerdefault: 5

Generated video duration in seconds.

Allowed: 5, 6, 7, 8, 9, 10

Field description

5–10: Choose a whole-second duration from 5 through 10.

5678910

resolutionstring

Text-to-video output canvas resolution tier.

Allowed: 480p, 768p

Field description

480p: 480-pixel short-edge tier.
768p: 768-pixel short-edge tier.

480p768p

The final width and height are aligned to 32 pixels.

Note:This field is not accepted for image-to-video requests.

aspect_ratiostring

Text-to-video output video aspect ratio.

Allowed: 1:1, 2:3, 3:2, 4:3, 3:4, 4:5, 5:4, 16:9, 9:16

Field description

1:1: Square
2:3 / 3:2: Portrait or landscape photo ratio
4:3 / 3:4: Landscape or portrait standard ratio
4:5 / 5:4: Portrait or landscape social ratio
16:9 / 9:16: Widescreen or vertical video

1:12:33:24:33:44:55:416:99:16

Note:This field is not accepted for image-to-video requests.

seedinteger

Optional non-negative generation seed.

Range: 0–2147483647

When omitted, the provider uses seed 42.

Use Cases

Choose the request shape that matches the source media you provide. The examples use the public model ID and accepted public fields.

Text-to-video

Generate a video directly from a text instruction.

{
  "model": "kimi-h3",
  "prompt": "A cinematic slow orbit around a mountain lake at sunrise",
  "duration": 5,
  "resolution": "768p",
  "aspect_ratio": "16:9"
}

Image-to-video

Use one image as the first frame; the provider matches the output canvas to that image.

{
  "model": "kimi-h3",
  "prompt": "The subject turns toward the camera as the wind moves through the scene",
  "image_urls": [
    "https://example.com/first-frame.jpg"
  ],
  "duration": 5
}

Response and task status

A successful asynchronous submission returns HTTP 202 with a supplier-neutral job.

{
  "id": "job_…",
  "object": "generation.job",
  "model": "kimi-h3",
  "status": "queued",
  "progress": 0,
  "output": null,
  "error": null,
  "billing": {
    "estimated_credits": "…",
    "frozen_credits": "…",
    "charged_credits": "0",
    "state": "frozen",
    "price_version": "2026-07-18.picverse-parity"
  },
  "created_at": "2026-07-21T00:00:00.000Z",
  "completed_at": null
}

queued / running: continue polling.
succeeded: retrieve media URLs from output; billing has settled.
failed / canceled: inspect error; frozen Credits are released.

Pricing

The price shown for a matching configuration is the fixed amount settled on successful completion. Price version: 2026-07-18.picverse-parity.

duration	Credits
5	200
6	240
7	280
8	320
9	360
10	400