MiniMax H3
MiniMax H3 — multimodal video generation with native audio. Text-to-video, image-to-video with end_image, and reference-based generation. 2K resolution, 5-15s duration, 24fps. Prompt with timelines, audio cues, and negative lists.
api reference
about
minimax h3 — multimodal video generation with native audio. text-to-video, image-to-video with end_image, and reference-based generation. 2k resolution, 5-15s duration, 24fps. prompt with timelines, audio cues, and negative lists.
get an api key
create one in settings → api keys. the examples read it from INFERENCE_API_KEY.
1export INFERENCE_API_KEY="inf_your_key"1. calling the api
install the client
nothing to install. any http client works; the examples use curl, and jq to read responses. every response wraps its result in a data field.
run and get result
send "wait": true to hold the connection until the task finishes. without it the call returns right away with the task still running.
12# "wait": true holds the connection until the task finishes.3# the response is {"data": {"id", "status", "status_text", "output", ...}}4curl -X POST https://api.inference.sh/apps/run \5 -H "Authorization: Bearer $INFERENCE_API_KEY" \6 -H "Content-Type: application/json" \7 -d '{8 "app": "minimax/h3",9 "input": {10 "prompt": "[0s-3s] Static wide shot. A lone marble camera on a pedestal in darkness, single moonbeam. [3s-6s] The lens flares to life, film strips unfurl from the reels. [6s-8s] Film strips fill the frame. Camera: locked off, no cuts. Audio: low hum building to orchestral swell at 6s. Do not add subtitles."11 },12 "wait": true13 }'stream live updates
get real-time progress updates as the task runs. ideal for showing progress bars, partial results, or long-running tasks. send "stream": true and the response is a server-sent event stream that ends when the task does.
12# "stream": true answers with server-sent events until the task finishes3curl -N -X POST https://api.inference.sh/apps/run \4 -H "Authorization: Bearer $INFERENCE_API_KEY" \5 -H "Content-Type: application/json" \6 -d '{7 "app": "minimax/h3",8 "input": {9 "prompt": "[0s-3s] Static wide shot. A lone marble camera on a pedestal in darkness, single moonbeam. [3s-6s] The lens flares to life, film strips unfurl from the reels. [6s-8s] Film strips fill the frame. Camera: locked off, no cuts. Audio: low hum building to orchestral swell at 6s. Do not add subtitles."10 },11 "stream": true12 }'run in the background
start the task and get its id back right away, then check on it later. for long tasks, or when you'd rather be called back, see webhooks.
1# without "wait" the call returns the task right away (status 1, "received")2TASK_ID=$(curl -s -X POST https://api.inference.sh/apps/run \3 -H "Authorization: Bearer $INFERENCE_API_KEY" \4 -H "Content-Type: application/json" \5 -d '{6 "app": "minimax/h3",7 "input": {8 "prompt": "[0s-3s] Static wide shot. A lone marble camera on a pedestal in darkness, single moonbeam. [3s-6s] The lens flares to life, film strips unfurl from the reels. [6s-8s] Film strips fill the frame. Camera: locked off, no cuts. Audio: low hum building to orchestral swell at 6s. Do not add subtitles."9 }10 }' | jq -r '.data.id')1112# later: read its state. done when status is 10 (completed), 11 (failed) or 12 (cancelled)13curl -s https://api.inference.sh/tasks/$TASK_ID \14 -H "Authorization: Bearer $INFERENCE_API_KEY" | jq '.data | {status, status_text, output}'2. authentication
the api uses api keys for authentication. see the authentication docs for detailed setup instructions.
3. files
file inputs are automatically handled by the sdk. you can pass local paths, urls, or base64 data.
automatic upload
pass urls directly or use data uris for inline content.
1# pass URLs or data URIs as input values2curl -X POST https://api.inference.sh/apps/run \3 -H "Authorization: Bearer $INFERENCE_API_KEY" \4 -H "Content-Type: application/json" \5 -d '{6 "app": "minimax/h3",7 "input": {8 "image": "https://example.com/image.png",9 "audio": "data:audio/mp3;base64,..."10 },11 "wait": true12 }'manual upload
you can also upload files manually and use the returned url.
1# 1. create the file: the response has an upload_url and the file's uri2FILE=$(curl -s -X POST https://api.inference.sh/files \3 -H "Authorization: Bearer $INFERENCE_API_KEY" \4 -H "Content-Type: application/json" \5 -d '{"files": [{"filename": "image.png", "content_type": "image/png"}]}')67# 2. PUT the bytes to upload_url8curl -X PUT "$(echo "$FILE" | jq -r '.data[0].upload_url')" \9 -H "Content-Type: image/png" \10 --data-binary @image.png1112# 3. pass the uri as an input value13echo "$FILE" | jq -r '.data[0].uri'4. webhooks
get notified when a task completes by providing a webhook url. when the task reaches a terminal state (completed, failed, or cancelled), a POST request is sent to your url with the task result.
1curl -X POST https://api.inference.sh/apps/run \2 -H "Authorization: Bearer $INFERENCE_API_KEY" \3 -H "Content-Type: application/json" \4 -d '{5 "app": "minimax/h3",6 "input": {7 "prompt": "[0s-3s] Static wide shot. A lone marble camera on a pedestal in darkness, single moonbeam. [3s-6s] The lens flares to life, film strips unfurl from the reels. [6s-8s] Film strips fill the frame. Camera: locked off, no cuts. Audio: low hum building to orchestral swell at 6s. Do not add subtitles."8 },9 "webhook": "https://your-server.com/webhook"10 }'webhook payload
your endpoint receives a JSON POST with the task result:
1{2 "event": "task.completed",3 "timestamp": "2024-01-15T10:30:05Z",4 "data": {5 "id": "task_abc123",6 "short_id": "abc123",7 "status": 10,8 "status_text": "completed",9 "output": { ... },10 "created_at": "2024-01-15T10:30:00Z",11 "updated_at": "2024-01-15T10:30:05Z"12 }13}5. schema
input
video prompt. use six-block structure: style contract, timeline with [0s-2s] markers, camera, audio cues, spelled-out text, negative list. max 7000 chars.
first frame image for image-to-video. formats: jpg, png, webp, heic. max 30mb.
last frame image. requires image to be set as first frame.
reference images for style/content guidance. cannot combine with first/last frame.
reference video for motion/style guidance. mp4/mov, max 50mb, 2-15s.
reference audio for synchronized generation. wav/mp3, max 15mb, 2-15s.
output resolution. 2k is the only resolution currently accepted.
video duration in seconds. 5-10 for text/image-to-video, 5-15 for reference-to-video.
aspect ratio. text-to-video requires explicit value (not adaptive). image/reference modes default to adaptive.
VACE
pruna/vace
$0.40/video
P-Video-Animate
pruna/p-video-animate
$0.03/sec 720p, $0.06/sec 1080p
P-Video-Upscale
pruna/p-video-upscale
Std: $0.01/sec 720p, $0.02 1080p, $0.04 2k, $0.08 4k; high fps 2x
P-Video-2-Pro-Avatar
pruna/p-video-2-pro-avatar
$0.02/sec 480p, $0.04/sec 768p, $0.06/sec 1080p, $0.08/sec 2k, $0.12/sec 4k
P-Video-2-Pro-Reference
pruna/p-video-2-pro-reference
Output: cost $0.015-$0.105/sec, speed $0.02-$0.115/sec. Ref video: $0.03-$0.06/sec. Ref img: $0.005/img. Ref audio: $0.0015-$0.0025/sec
new models
Tripo Auto Rig
tripo/tripo-rig
3d$0.01/credit (rig check free, auto rig 25 credits, retarget 10 credits/animation)
Hunyuan 3D Auto Rigging
tencent/hunyuan-3d-auto-rigging
3d$0.02/credit, 10 credits/call ($0.20/call)
TokenRig
infsh/tokenrig
3dGPU time, billed per millisecond
Hunyuan 3D 3.1
tencent/hunyuan-3d-3-1
3d$0.02/credit; Geometry 15cr, Normal 25cr, +10cr views/PBR/face-count
Rodin Gen-2.5
hyper3d/rodin-gen-2-5
3d$0.58/credit; Extreme-High tier +0.5 credits, texture extreme-high +2 credits
ready to run MiniMax H3?
we use cookies
we use cookies to ensure you get the best experience on our website. for more information on how we use cookies, please see our cookie policy.
by clicking "accept", you agree to our use of cookies.
learn more.