Video generation

Video is an asynchronous task API on the same bearer token, under /v1/videos. The shape follows OpenAI's video routes:

POST /v1/videos creates a job and returns its id immediately.
GET /v1/videos/{id} is polled until the job finishes.
Download the finished clip from GET /v1/videos/{id}/content.

The gateway serves two video families:

Group	Provider	Resolutions	Duration
`minimax-h3`	MiniMax	768P, 2K	4–15 s
`minimax-h3-max`	MiniMax	480P, 768P	5–15 s
`seedance`	BytePlus	480p, 720p, 1080p	4–30 s

A deployment serves a group only when its provider credential is configured. GET /v1/models lists the video groups your key can call.

See BytePlus Seedance for its image-to-video and billing details.

Try it

Generate a video

POST /v1/videos

Key

Model groupResolutionAspect ratio

Prompt

Seconds4–15 s for MiniMax H3.

MiniMax H3 · billed per second

Create a job

curl -sS "https://llms.party/v1/videos" \
  -H "Authorization: Bearer $LLMS_PARTY_KEY" \
  -H "content-type: application/json" \
  -d '{
    "model": "minimax-h3",
    "prompt": "A glass city at sunset, slow aerial push-in.",
    "seconds": 4,
    "resolution": "768P",
    "ratio": "16:9"
  }'

{
  "id": "video_...",
  "object": "video",
  "model": "minimax-h3",
  "status": "queued",
  "progress": 0,
  "created_at": 1760000000
}

Field	Values
`model`	A video group or one of its aliases.
`prompt`	Text description of the shot.
`seconds`	H3: 4–15. H3-Max: 5–15. Seedance: 4–30.
`resolution`	Group-specific; see the table above (Seedance is lowercase).
`ratio`	`16:9`, `9:16`, `1:1`, `4:3`, `3:4`, `21:9`.
`input_reference`	Optional image URL for image-to-video.

Poll

curl -sS "https://llms.party/v1/videos/$VIDEO_ID" \
  -H "Authorization: Bearer $LLMS_PARTY_KEY"

Statuses are normalized across providers: the gateway maps running to in_progress and succeeded to completed, but older payloads may still say succeeded. Terminal states are completed, failed and cancelled.

Status	Meaning
`queued`	Accepted, not started upstream yet.
`in_progress`	Rendering; `progress` may be populated.
`completed`	Ready to download.
`failed`	`error.message` explains why.
`cancelled`	Cancelled upstream.

Polling every 2–5 s is plenty; renders take tens of seconds to a few minutes.

Download

Download the finished clip through the OpenAI-compatible content route:

curl -sS "https://llms.party/v1/videos/$VIDEO_ID/content" \
  -H "Authorization: Bearer $LLMS_PARTY_KEY" \
  -o clip.mp4

The response is video/mp4. The gateway streams the clip from the provider as it downloads (Range requests are supported), so large 720p/1080p files are not buffered. Provider signed URLs are resolved internally and are not returned in the task object; on BytePlus they expire after 24 hours or 100 downloads, so always download through /content. Task records are kept for 7 days; after that a finished clip can no longer be downloaded.

What it costs

MiniMax is billed per second of output; Seedance is billed per million tokens.

MiniMax H3

Group	480P	768P	2K
`minimax-h3`	n/a	$0.08/s	$0.13/s
`minimax-h3-max`	$0.05/s	$0.08/s	n/a

BytePlus Seedance 2.5

Resolution	USD per 1M tokens	5 s, 16:9	30 s, 16:9
480p	$10.70	$0.514	$3.08
720p	$10.70	$1.156	$6.94
1080p	$11.70	$2.843	$17.06

Seedance cost is (input video seconds + output seconds) × width × height × fps / 1024 tokens, priced per million tokens; see BytePlus Seedance for the full formula and caveats. The largest Seedance job through the gateway, 30 s at 1080p, costs about $17.06.

Figures are vendor list prices; the gateway meters them as spend against the key's budget. Sources: MiniMax pricing and BytePlus ModelArk pricing.