MiniMax H3 API
MiniMax Hailuo H3 is a general-purpose multimodal video model: it reads text, images, video and audio in the same request and returns one clip with picture, motion and sound already in agreement (native synchronized audio) — no separate dubbing, lip-sync or motion-transfer step afterwards. A prompt alone is text-to-video; attach up to 9 reference images, 3 reference videos and 3 reference audio clips to pin down character, camera movement and voice. Any whole-second length from 5 to 15, billed per second: 768P at $0.097/s, native 2K at $0.145/s.
Resolution tiers and pricing
| Tier | resolution | Per second | 5s | 10s | 15s |
|---|---|---|---|---|---|
| Native 2K (default) | 2k | $0.145 | $0.725 | $1.45 | $2.175 |
| 768P | 768p | $0.097 | $0.485 | $0.97 | $1.455 |
Both tiers carry native synchronized audio; resolution is the only difference. 768P saves a third for drafts, feeds and small players; native 2K ships without any upscaling step. Charged only on success, refunded on failure.
Aliases: hailuo-h3 and minimax-h3 point at the same model — Hailuo is the product name of the MiniMax video line.
Input asset pricing
Reference assets are priced separately, on top of the output seconds — a reference video bills by its own length, reference audio is free, and the first 5 reference images are free.
| Asset | Limit | Price |
|---|---|---|
| images | 9 images | first 5 free, $0.054 each from the 6th |
| video_list | 3 clips, each 15s at most | by the reference clip’s own length: $0.135/s at 2K, $0.081/s at 768P |
| audio_list | 3 clips | free |
Example: a 10-second 2K output with a 7-second reference video → 10 × $0.145 + 7 × $0.135 = $2.395. Another: a 5-second 2K output with 8 reference images → 5 × $0.145 + 3 × $0.054 = $0.887.
A reference video longer than 15 seconds is rejected at create time: we probe each reference clip’s real duration and return a clear 400 before any task is created or credits frozen.
Authentication
All requests carry the API key in the header:
Authorization: Bearer YOUR_API_KEYVideo Generation
/api/v1/video/generations·GET/api/v1/video/generations?task_id=# Text-to-video (model: minimax-h3 — the alias hailuo-h3 also works)
curl -X POST https://api.apimodels.app/v1/video/generations \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "minimax-h3",
"prompt": "a lighthouse keeper climbs a spiral staircase at dusk, warm lamplight, waves crashing outside",
"resolution": "768p",
"ratio": "16:9",
"duration": 10
}'
# Poll until completed (result files are kept 30 days)
curl "https://api.apimodels.app/v1/video/generations?task_id=TASK_ID" \
-H "Authorization: Bearer YOUR_API_KEY"
# All reference inputs are optional — prompt alone is text-to-video.
# Attach images / video_list / audio_list to steer character, motion and voice
# in the same request (see the multimodal example in the Python / Node tabs).Parameters
| Field | Required | Type | Description |
|---|---|---|---|
| model | Yes | string | minimax-h3 (alias hailuo-h3) |
| prompt | Yes | string | The prompt. Describe the scene in plain language, and say what each reference asset should supply (looks, camera movement, rhythm, voice). |
| duration | Yes | number | A whole number of seconds, 5-15. Required, and whole seconds only. |
| resolution | No | string | 768p or 2k, default 2k. |
| ratio | No | string | adaptive (default) / 21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16. The field name aspect_ratio is also accepted. |
| images | No | string[] | Reference images, up to 9 (public URL or base64). First 5 free, $0.054 each from the 6th. reference_image_urls is also accepted. |
| video_list | No | string[] | Reference videos, up to 3, each 15s at most (public URL or base64), billed by their own length ($0.135/s at 2K, $0.081/s at 768P). video_urls / reference_video_urls are also accepted. |
| audio_list | No | string[] | Reference audios, up to 3 (public URL or base64), free. audio_urls / reference_audio_urls are also accepted. |
| callback_url | No | string | We POST the result to this URL on completion; omit it and poll the GET endpoint instead. |
Billing
total = duration × per-second price
+ reference video seconds × input-video price
+ max(0, images − 5) × $0.054- Per-second price: $0.145 at 2K, $0.097 at 768P; input-video price: $0.135/s at 2K, $0.081/s at 768P; reference audio is free.
- Charged only on success: a failed generation is fully refunded automatically, input-asset charges included.
Notes
- Async: create returns a taskId; poll GET /v1/video/generations?task_id= until completed, or pass callback_url and we call you back on completion. Result files are deleted after 30 days — download or re-host promptly.
- Every reference input is optional and they combine freely — images only, audio only, or images + video + audio together. Nothing attached means plain text-to-video.
- Parameter errors (duration out of range, ratio outside the enum, too many assets) return a synchronous 400 at create time — no task is created and no credits are frozen.
- Prompts and outputs go through content moderation; a moderation rejection is treated as a failure and refunded.
Try it in the Playground
FAQ
How much does the MiniMax H3 API cost?
On apimodels.app, 768P is $0.097 per second and native 2K is $0.145 per second (a 5s clip is $0.485 / $0.725). Reference assets price separately: a reference video bills by its own length at $0.135/s (2K) or $0.081/s (768P), reference audio is free, and the first 5 reference images are free with $0.054 for each one after. Only successful generations are charged; failures are refunded in full.
What inputs does MiniMax H3 take?
Text, images, video and audio in the same request: up to 9 reference images, 3 reference videos (each 15s at most) and 3 reference audio clips, every one of them optional and freely combined. A prompt alone behaves as text-to-video. Each asset accepts a public URL or base64.
How do I call the MiniMax H3 API?
POST /api/v1/video/generations with model set to minimax-h3 (the alias hailuo-h3 also works), a prompt and duration (a whole number of seconds, 5-15). Optionally add resolution (768p or 2k, default 2k), ratio, images, video_list and audio_list. The call returns a taskId — poll GET /api/v1/video/generations?task_id=xxx, or pass callback_url to be called back on completion. One API key covers every model on apimodels.app.
What resolutions, lengths and aspect ratios does MiniMax H3 support?
Two resolution tiers, 768p and native 2k, both with synchronized audio. Any whole-second duration from 5 to 15. Aspect ratios: adaptive (default), 21:9, 16:9, 4:3, 1:1, 3:4 and 9:16.