MiniMax-H3 AI Video API

MiniMax-H3 is MiniMax's multimodal video model. Official documentation lists text, image, video, and audio references, 768P or 2K output, and 4–15-second clips; Flatkey exposes the asynchronous /v1/videos flow.

Image to VideoReference-guided VideoAudio generationShort-form Video
Provider
MiniMax
Reference price
from $0.130 / second · 4s min768pfrom $0.080 / second · 4s min
Flatkey price
from $0.130 / second · 4s min768pfrom $0.080 / second · 4s min
Generator setup · Playground (edit before sign-up)

Input

PromptCheck more732 / 10000
Quick Prompts
Reference image0 / 9
Reference videos0 / 3
Reference Audios0 / 3
Start generating

Output

Preview

Generated with Seedance 2.0

Request summary

Endpoint
POST /v1/videos
Model ID
MiniMax-H3
Aspect ratio
9:16
Resolution
768P
Duration
6s
Reference media
None

Preview only. Sign in to submit this request to Flatkey.

Request preview
{
  "model": "MiniMax-H3",
  "content": [
    {
      "type": "text",
      "text": "Creative direction: A person in a yellow raincoat waits beside a bench at a rainy station, notices a torn letter, and picks it up to read. Move from the wet platform to a close view of the paper and hold on the reader's concerned expression.\n\nVisual treatment: Rainy character drama with subdued station colors and a yellow raincoat focal accent.\n\nShot sequence: 1. Establish the raincoat figure beside the station bench.; 2. Move closer as the torn letter is noticed and lifted.; 3. Hold the concerned face with the letter visible and rain continuing behind.\n\nContinuity: Keep the character's face, clothing and key prop consistent; preserve screen direction across cuts.\nExclude: extra people or props, text, logos and watermarks."
    }
  ],
  "resolution": "768P",
  "duration": 6,
  "ratio": "9:16",
  "aigc_watermark": false
}

Performance

MiniMax-H3 video API performance and availability

Live Flatkey request telemetry appears here when enough MiniMax-H3 traffic is available; no quality ranking is inferred.

Avg. provider uptime
—
last 30 days
Latency
—
last 30 days
Requests
653
30-day window
Successful inference trend

Activity

MiniMax-H3 video API usage and generation activity

This chart uses live Flatkey generation requests and stays unreported until enough traffic is collected.

Requests
653
30-day window
Latency
—
last 30 days
Uptime
—
last 30 days
Successful inference trendActivity

Pricing

MiniMax H3 video API pricing by resolution and duration

Prices below are calculated from Flatkey pricing data for this model and the visible groups currently returned by our pricing API.

Flatkey price

2k · Price / second

Live catalog model
from $0.130 / second · 4s min
2k · Price / second
from $0.130 / second · 4s minfrom $0.130 / second · 4s min
768p · Price / second
from $0.080 / second · 4s minfrom $0.080 / second · 4s min
Try a prompt
Shared balance

Add credits

Add credits

Use the same Flatkey balance and API key across image, video, audio, and text models.

Model catalog
Model Type
Text to Video
API
/v1/videos
Billing basis
second
Duration
4–15s
Aspect ratio
21:9 · 16:9 · 4:3 · 1:1 · 3:4 · 9:16 · adaptive

MiniMax H3 video generation and production capabilities

Use these documented capabilities to plan a production workflow; request fields remain in the API section below.

Text-to-video and image-to-video

Start a scene from a written brief or a designed frame and develop it into a short clip.

Reference-led motion

Use text, image, video, or audio references to keep the subject and creative direction coherent.

Camera and pacing direction

Shape how the camera, subject movement, duration, and framing progress through the shot.

Production-ready variants

Create product, UGC, and storyboard versions that can move from testing into an editing workflow.

Compare

MiniMax H3 hosted API vs open-weight or local deployment

Compare documented hosted request fields with open-weight or local assumptions; MiniMax upstream terms and Flatkey routing are separate.

CapabilityOpen-weight / local deploymentVerified hosted API
Resolution768P base; 2K via hosted regeneration768P or 2K
Duration4–15 seconds4–15 seconds
RatioText-to-video requires a fixed ratio; adaptive is for reference routesRoute-specific fixed/adaptive ratio rules
AIGC watermarkNot verifiedFlatkey route field; availability varies
ComfyUI or local weightsMiniMax documents open-source weights and ComfyUI options upstreamNative Flatkey local/ComfyUI delivery not verified
Upstream vs FlatkeyOpen-source/local use follows MiniMax upstream documentationFlatkey routes and bills hosted API access

Choose the right request before you integrate

Review the supported workflows, live cost for the current setup, and the exact parameter contract used by Flatkey.

Live cost estimate

Calculated from the current Playground settings and the live catalog rate when a fixed unit price is available.

Current setup
768P · 6s
Live rate
from $0.080 / second · 4s min
Estimated request
$0.480
$0.080 × 6s

The final charge follows the submitted request and your account group. Token-priced or tiered requests cannot be reduced to one fixed estimate.

Workflows and Model ID

Use only the workflows marked available. Flatkey keeps one public model ID while the request body selects the input workflow.

Available

Text to Video

Create a clip from a text prompt and supported output controls.

Model ID
MiniMax-H3
Endpoint
/v1/videos
Available

Image to Video

Animate one or more image references while preserving the requested subject and composition.

Model ID
MiniMax-H3
Endpoint
/v1/videos
Available

Reference to Video

Guide the result with the documented image, video, or audio reference inputs.

Model ID
MiniMax-H3
Endpoint
/v1/videos

Parameter compatibility

These values come from the same model configuration used by the Playground and request preview.

resolutionResolution
Accepted

768P · 2K

Default: 768P
durationDuration
Accepted

4–15

Default: 6
ratioAspect ratio
Accepted

21:9 · 16:9 · 4:3 · 1:1 · 3:4 · 9:16 · adaptive

Default: 16:9
aigc_watermarkAIGC watermark
Accepted

On · Off

Default: Off
imageReference limit
Accepted

9 files

Endpoint: /v1/videos
videoReference limit
Accepted

3 files

Endpoint: /v1/videos
audioReference limit
Accepted

3 files

Endpoint: /v1/videos

From first test to production

Use the same request contract in the Playground and API, then handle validation, balance, task state, and output retrieval explicitly.

Request lifecycle

  1. 1

    Validate the model, prompt, references, and output settings.

  2. 2

    POST the request and retain the returned task ID.

  3. 3

    Poll task status or process the configured callback.

  4. 4

    Fetch the generated file from the content endpoint and store it before expiry.

Production checks

Parameter validation

Reject unsupported sizes, durations, ratios, formats, or reference counts before submitting.

Authentication and balance

Handle invalid keys, insufficient balance, rate limits, and account-group pricing separately.

Input or policy rejection

Surface the rejected prompt or asset clearly so the user can replace only the failing input.

Task failure or timeout

Keep the task ID, use bounded retries, and never treat a timeout as a successful generation.

Prompt library

MiniMax-H3 prompting guide: product, UGC, and storyboard shots

Describe the subject, action, camera position, duration, and output ratio; keep the request fields separate from the scene prompt.

Micro-drama and comic creators

Generated with Seedance 2.0

Creative direction: A person in a yellow raincoat waits beside a bench at a rainy station, notices a torn letter, and picks it up to read. Move from the wet platform to a close view of the paper and hold on the reader's concerned expression. Visual treatment: Rainy character drama with subdued station colors and a yellow raincoat focal accent. Shot sequence: 1. Establish the raincoat figure beside the station bench.; 2. Move closer as the torn letter is noticed and lifted.; 3. Hold the concerned face with the letter visible and rain continuing behind. Continuity: Keep the character's face, clothing and key prop consistent; preserve screen direction across cuts. Exclude: extra people or props, text, logos and watermarks.

Create similar
Advertising and ecommerce teams

Generated with Seedance 2.0

Creative direction: A teal reusable bottle with water droplets stands on bright marble beside an open canvas tote. One hand grips the bottle, lifts it and slides it into the tote side pocket. End with the bottle still visible above the pocket and daylight catching its wet surface. Visual treatment: Photoreal lifestyle commercial with soft window daylight, teal enamel and tactile canvas and marble textures. Shot sequence: 1. Frame the bottle and the open tote together; 2. Follow the hand as it lifts the bottle into the side pocket; 3. Hold the packed tote with the bottle visible and upright Continuity: Keep the product silhouette, cap or hinge, materials and prop positions stable; hold the final hero frame. Exclude: extra people or props, text, logos and watermarks.

Create similar
Film concept and production teams

Generated with Seedance 2.0

Creative direction: A man walks from a dark interior into an empty glass-domed observatory at dawn. Follow him toward the telescope as cool sky light fills the dome, then settle behind the figure and instrument facing the bright horizon. Visual treatment: Live-action observatory reveal with cool dawn skylight and a dark foreground silhouette. Shot sequence: 1. Follow the man out of the dark interior into the glass dome.; 2. Continue toward the telescope as dawn sky fills the background.; 3. Settle behind the figure and telescope facing the bright horizon. Continuity: Maintain scene geography, subject scale and motivated light direction throughout the camera move. Exclude: extra people or props, text, logos and watermarks.

Create similar
Game art and animation teams

Generated with Seedance 2.0

Creative direction: A cyberpunk fighter crouches on a wet neon plaza, bursts into a sprint, and slides to a stop. A blue circular energy shield opens in front of the fighter as the low camera tracks the movement and holds on the glowing barrier. Visual treatment: Rendered cyberpunk action with neon reflections and localized blue shield emission. Shot sequence: 1. Start low on the crouched fighter in the wet plaza.; 2. Track the acceleration and slide, keeping foot contact legible.; 3. Stop with the fighter as the blue shield opens in front. Continuity: Maintain character design, equipment geometry and travel direction from first to final frame. Exclude: extra people or props, text, logos and watermarks.

Create similar
Creator and explainer channels

Generated with Seedance 2.0

Creative direction: Miniature island and map pieces assemble on a blue tabletop around a white lighthouse. The land sections lock together, the lighthouse rises upright, and its lamp turns on while the overhead view reveals the completed coastal model. Visual treatment: Miniature map animation with distinct island layers and a blue tabletop. Shot sequence: 1. Establish separated island pieces and the lighthouse from overhead.; 2. Slide the land sections together and raise the lighthouse upright.; 3. Turn on the lamp and hold the completed coastal model. Continuity: Keep demonstration props, layout and hand contact consistent so the action remains legible. Exclude: extra people or props, text, logos and watermarks.

Create similar
Music producers and visual artists

Generated with Seedance 2.0

Creative direction: A chrome ring-and-ribbon sculpture rotates above a reflective black floor under blue and red light. The metal loops bend and morph into a new interlocking shape while the camera holds a symmetrical gallery-style composition. Visual treatment: Reflective abstract sculpture animation with chrome, black and controlled blue-red light. Shot sequence: 1. Center the chrome loops above the black reflective floor.; 2. Rotate the sculpture while ribbons bend into the next interlocking shape.; 3. Slow the rotation and hold the new silhouette with its reflection aligned. Continuity: Keep the main subject, palette and light behavior consistent as the visual pattern develops. Exclude: extra people or props, text, logos and watermarks.

Create similar

Why use Flatkey for MiniMax-H3?

A practical MiniMax H3 video API workflow

Keep video settings, asynchronous task handling, and pricing boundaries visible while you move from a prompt draft to a real request.

Video fields are explicit

Choose 768P or 2K, 4–15 seconds, a supported ratio, and the AIGC watermark boolean.

Prompting guide included

Product, UGC, and storyboard examples describe subject, action, camera, and ending rather than repeating a generic cinematic prompt.

Async result path

Save the task ID returned by POST /v1/videos and retrieve the generated content when the task is ready.

ComfyUI/local boundary

MiniMax documents open-source H3 weights and ComfyUI/local options upstream; this page only promises Flatkey hosted delivery, not native local packaging.

API

Use the MiniMax H3 video API with an async task

MiniMax's upstream API and Flatkey's hosted route use different paths; save the returned task ID and retrieve the result when ready.

POST /v2/video_generation
POST /v1/videos
MiniMax-H3
content[] with a non-empty text item, resolution, duration, and ratio; aigc_watermark is a Flatkey route field whose availability is route-specific.
Use the returned task ID with the content endpoint.
curl https://router.flatkey.ai/v1/videos \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-***" \
  -d '{"model":"MiniMax-H3","content":[{"type":"text","text":"A paper boat crosses a rain puddle at street level, cinematic macro shot, soft reflections, 6 seconds."}],"resolution":"768P","duration":6,"ratio":"16:9","aigc_watermark":false}'

# Poll for the result (replace TASK_ID with the returned task id)
curl "https://router.flatkey.ai/v1/videos/TASK_ID" \
  -H "Authorization: Bearer sk-***"
Docs

FAQ

MiniMax H3 video API
pricing and ComfyUI questions

Answers about MiniMax-H3 video API fields, prompting, per-second pricing, asynchronous tasks, ComfyUI/local boundaries, and moderation claims.

Which MiniMax-H3 fields can I configure here?
Configure resolution, duration, ratio, and AIGC watermark before opening the console.
What is MiniMax-H3?
MiniMax-H3 is MiniMax's multimodal video model, with documented text, image, video, and audio references and 768P or 2K output up to 15 seconds.
How much does MiniMax-H3 cost?
Use the pricing section above for current Flatkey prices from our pricing API.
How do I use the MiniMax-H3 video API?
Configure the fields, create a Flatkey API key, send POST /v1/videos with model MiniMax-H3, then keep the asynchronous task ID for the content lookup.
Does MiniMax-H3 have a prompting guide?
Use the page examples as a starting point: name the subject, action, camera movement, duration, and ending, then set ratio and resolution as request fields.
Does Flatkey provide native MiniMax-H3 ComfyUI or local installation?
MiniMax documents open-source H3 weights and ComfyUI/local options upstream. Flatkey's hosted route is available here; native Flatkey ComfyUI delivery and local hardware packaging are not promised.
Is MiniMax-H3 censored or unrestricted?
The current catalog does not publish a moderation policy for this model, so the page makes no unrestricted-use claim.
Are MiniMax-H3 prompt drafts executed on this public page?
The public page saves the video settings and prompt draft first. Sign up or open the console to run POST /v1/videos with an API key.