Model type
Video generation
Designed for fast text-to-video and image-to-video generation.
MiniMax H3 Max API
Access MiniMax H3 Max, officially launched by MiniMax, through EvoLink's unified video API. Test 768p and 480p text-to-video or first/last-frame image-to-video, see credits before you generate, and move the same model ID into production.
MiniMax H3 family-Video GenerationAvailable
From ~$0.050 / s for the 480p video rate
Text-to-VideoImage-to-VideoFast generation768p / 480p output5-15s VideoAsync API
Production routeLive
Model Highlights
Fast 480p / 768p video generation for high-volume iteration
Use Cases
High-volume ad creative, ecommerce, social clips, rapid iteration
Input
Text, or a first frame, last frame, or both
Output
768p / 480p video (MP4)
Try MiniMax H3 Max before you integrate the API.
Test MiniMax H3 Max output, estimate credits, and pick the model ID that matches your input type before wiring the API into your product.
Create a Sample
Pick a route, enter your prompt, and set the parameters.Duration5s
Quality
Aspect Ratio
Estimated: ~$0.4027.20 cr
Ready
History
Results are kept for 24 hours — download anything you want to keep.
Your generation history will appear here
MiniMax H3 Max pricing is per output second.
Both routes are billed per output second. 480p costs 5/8 of the 768p rate, and the playground shows the live price before you generate.
First Test Cost
Text-to-Video - 5s - 480pCredits17
One 5s 480p sample
Approx. Cost$0.25
About 40 tests with $10 in credits.
This is also the minimum charge: 5s at 480p is the cheapest valid request, so no MiniMax H3 Max task costs less. Omit the resolution and you get 768p, which costs proportionally more.
Testing Budget Guide
Pick an amount based on how many tests you expect.$10
About 40 tests
Good for a first validation.
$50
About 200 tests
Good for prompt and shot iteration.
$100
About 400 tests
Good before production integration.
Common Cost Examples
Short text-to-video testT2V 5s 768p
~$0.4027.2 cr
Full-length clipT2V 15s 768p
~$1.2081.6 cr
Image-to-video clipI2V 10s 768p
~$0.8054.4 cr
Estimates use the current per-second rate for your user group. Duration is rounded up to whole seconds, exactly as the task reports it.
MiniMax H3 Max Pricing
| Mode | 480P | 768P | Billing |
|---|---|---|---|
| Text-to-VideoStandard route | $0.050/s3.4 cr/s | $0.080/s5.44 cr/s | Output video seconds |
| Image-to-VideoStandard route | $0.050/s3.4 cr/s | $0.080/s5.44 cr/s | Output video seconds |
Text-to-Video
Standard route · Output video seconds
480P $0.050/s · 3.4 cr/s
768P $0.080/s · 5.44 cr/s
Image-to-Video
Standard route · Output video seconds
480P $0.050/s · 3.4 cr/s
768P $0.080/s · 5.44 cr/s
Billed per second of output video. Input frames are never charged separately — MiniMax H3 Max accepts at most a first and a last frame, which stay inside the included allowance.
Minimum charge per task equals the cheapest valid request (480p x 5s). Failed, expired, and rejected tasks are refunded in full.
What is MiniMax H3 Max best for?
MiniMax H3 Max is best for high-volume creative iteration: ad variations, ecommerce product clips, social shorts, and fast storyboard validation. Start from a text prompt, or provide first and last frames when the shot needs a defined opening and ending. Through EvoLink, teams can use 480p for lower-cost exploration or 768p for higher-definition output while keeping the same API key, shared balance, and asynchronous task workflow used by other video models.
Input
Text prompt, first frame, last frame, or both
Output
480p / 768p MP4 video
Duration
5-15 seconds per generation
Billing
Per output second; failures refunded
MiniMax H3 Max model information
Choose a route and output tier based on the input and delivery requirements of your workflow.
Supported inputs
Text, first frame, last frame
The current EvoLink H3 Max route accepts a first frame, a last frame, or both. Use MiniMax H3 on EvoLink when a brief needs broader reference media.
API model IDs
minimax-h3-max-text-to-video / -image-to-video
MiniMax documents the official model as MiniMax-H3-Max. EvoLink splits text and frame inputs into two route-specific IDs that share one video endpoint and credit balance.
Output and duration
768p / 480p, 5-15s, MP4
768p is the default when resolution is omitted. 2K is not available on H3 Max, and 4-second clips are not supported.
API pricing
Per output second, 480p and 768p tiers
EvoLink bills each output second through the shared credit balance. 480p costs 5/8 of the 768p rate.
Task lifecycle
Async submit, poll or callback, no cancel
Tasks report pending / processing / completed / failed. Cancellation is not available, so failures refund instead.
Official MiniMax H3 Max model listing
MiniMax officially launched MiniMax-H3-Max as its high-speed H3 generation model. It supports 480p / 768p text-to-video and first/last-frame image-to-video with 5-15 second output; EvoLink exposes those inputs as two route-specific model IDs.
Read the official MiniMax model catalogWhere MiniMax H3 Max fits in a video workflow
Use text prompts or controlled first and last frames across creative, commerce, and production workflows.
Text-to-video creation
Prompt adherence, camera direction, motion, and physical plausibility for storyboards, social clips, and creative concepts.
Image-to-video animation
Animate a first frame, land on a last frame, or drive a transition between both while keeping product shape and character identity.
Advertising creative
Batch throughput, retries, brand consistency, and cost per accepted ad rather than one showcase clip.
Ecommerce product video
Product fidelity, controllable movement, aspect-ratio delivery, and logo handling before customer-facing use.
Narrative and short-form series
Shot continuity across a sequence by driving each clip from a first and last frame.
Multi-model video products
Run MiniMax H3 Max as one route beside H3, Seedance, Kling, and Wan, and keep a tested fallback instead of coupling to one provider.
How to integrate MiniMax H3 Max in production
Choose the route by input type
Send prompt-only requests to minimax-h3-max-text-to-video. Use minimax-h3-max-image-to-video when you need a first frame, a last frame, or both. Both routes use EvoLink's unified video endpoint.
Submit and track an asynchronous task
Create the task once, then poll its status or receive a callback until the MP4 is ready. Result URLs remain available for 24 hours, so copy completed videos to your own storage as part of the delivery flow.
Control cost and keep a fallback
Use 480p for lower-cost drafts and 768p for higher-definition output. Failed, expired, and rejected tasks are refunded; the same API key and balance let you route 2K or broader reference jobs to MiniMax H3.
Is MiniMax H3 Max worth adding to your video stack?
Choose H3 Max for fast 480p / 768p iteration; switch routes when you need higher resolution or broader reference inputs.
Good fit when
- You need 768p or 480p clips from 5 to 15 seconds.
- Your product needs text-to-video and first/last-frame image-to-video.
- You are iterating in volume and want the cheapest Hailuo second.
- Your application already supports async polling or callbacks.
- You evaluate accepted-output cost across multiple video models.
Consider another route when
- You need 2K output — use MiniMax H3, which has the 2K tier.
- Your EvoLink workflow needs reference images, video, or audio — use the MiniMax H3 route currently available here.
- You need 4-second clips; H3 Max starts at 5 seconds.
- The task must return synchronously or remain cancellable after submission.
- You cannot save the completed MP4 within the 24-hour result window.
How to decide whether MiniMax H3 Max fits production
Use real workloads and acceptance criteria — not selected showcase clips — to measure usable output, consistency, total cost, and operating reliability.
Does it produce more usable clips?
Measure prompt adherence, temporal consistency, visible artifacts, and accepted outputs across the full attempt set.
Does it preserve identity and products?
Compare character, face, clothing, logo, product shape, composition, and style retention from the same source assets.
Does it improve the full workflow?
Include queue limits, failed-task refunds, moderation, retries, reviewer correction, delivery format, and downstream editing — not only generation speed.
Is it worth adding to production?
Calculate cost per final accepted clip, and confirm callbacks, retention rules, monitoring, rollback, and multi-model fallback fit your product.
How MiniMax H3 Max fits your video stack
| Feature | MiniMax H3 Max | MiniMax H3 | Other video routes |
|---|---|---|---|
| Primary role | Fast Hailuo route for volume | Full-featured Hailuo route | Cross-vendor comparison and fallback |
| Generation modes | T2V + I2V (first/last frame) | T2V + I2V + R2V | Model-dependent |
| Reference input | Not on current EvoLink routes | Image + video + audio | Model-dependent |
| Resolution | 768p / 480p | 2K / 768p | 480p to 4K |
| Duration | 5-15s | 4-15s | 3-15s |
| Billing | Per output second | Per output second (+ reference video seconds) | Per second or per video |
Primary role
MiniMax H3 MaxFast Hailuo route for volume
MiniMax H3Full-featured Hailuo route
Other video routesCross-vendor comparison and fallback
Generation modes
MiniMax H3 MaxT2V + I2V (first/last frame)
MiniMax H3T2V + I2V + R2V
Other video routesModel-dependent
Reference input
MiniMax H3 MaxNot on current EvoLink routes
MiniMax H3Image + video + audio
Other video routesModel-dependent
Resolution
MiniMax H3 Max768p / 480p
MiniMax H32K / 768p
Other video routes480p to 4K
Duration
MiniMax H3 Max5-15s
MiniMax H34-15s
Other video routes3-15s
Billing
MiniMax H3 MaxPer output second
MiniMax H3Per output second (+ reference video seconds)
Other video routesPer second or per video
Why use the MiniMax H3 Max API through EvoLink
Cost Clarity
See credits and per-second cost before each generation.
Unified API
Switch between Hailuo, Seedance, Kling, and other video routes without rebuilding auth or billing.
Unified Balance
Track credits, spending, and model usage for every route in one console.
Task Status Tracking
See whether a task is pending, processing, completed, or failed, with refunds on failure.
Model Choice
Keep MiniMax H3 Max as one tested route and fall back to H3 or another family when a workload needs it.
Hailuo Model Family
Compare all Hailuo models
MiniMax H3 Max
CurrentThe fast Hailuo route: 768p / 480p output, 5-15s, text or first/last-frame driven generation.
MiniMax H3
The full-featured Hailuo route: 2K / 768p output, 4-15s, and text, frame, or reference driven generation.
View
Hailuo 2.3
The documented Hailuo generation for text-to-video and image-to-video through Standard and Fast routes.
ViewOther video models on EvoLink
Seedance 2.0
A multimodal route for text, image, video, and audio reference workflows from 480p to 4K.
View
Kling O3
A production video route with multimodal controls and a different capability and cost profile.
View
Wan 2.7
A video fallback for text-to-video and image-to-video workflows with different duration and pricing options.
ViewCompare MiniMax H3 Max before you adopt it
Use the family page and the dated comparisons for the decision that brought you here.
Read the MiniMax H3 API guide
cURL, Python, and TypeScript examples for the Hailuo routes, async submission, polling, callbacks, and error handling.
ViewMiniMax H3 release timeline
Confirmed evidence, reported timing, and the verification checklist EvoLink used before opening the Hailuo routes.
ViewMiniMax H3 vs Hailuo 2.3
Decide when the next generation has enough evidence to justify an upgrade inside the same family.
ViewMiniMax H3 vs Seedance 2.0
Compare the Hailuo routes with an available multimodal audio-video workflow.
ViewMiniMax H3 vs Seedance 2.5
Decide whether to ship on Hailuo or move to the Seedance 2.5 API, live on EvoLink since August 7, 2026.
ViewMiniMax H3 Max FAQ
What is MiniMax H3 Max?
MiniMax H3 Max is MiniMax's officially launched high-speed H3 video generation model. It supports text-to-video and first/last-frame image-to-video at 480p or 768p with 5-15 second output. EvoLink exposes the two input modes as separate route-specific model IDs.
How is MiniMax H3 Max different from MiniMax H3?
For the routes available on EvoLink, H3 Max targets faster 480p / 768p iteration through text-to-video and first/last-frame image-to-video, while MiniMax H3 remains the 2K option with broader reference workflows. H3 Max starts at 5 seconds; H3 starts at 4 seconds.
What can MiniMax H3 Max be used for?
Text-to-video, image-to-video with first and last frame control, high-volume advertising creative, ecommerce product video, social clips, and any workflow where iteration speed matters more than the 2K tier.
Is MiniMax H3 Max available through EvoLink?
Yes. EvoLink exposes MiniMax H3 Max as two routes through the unified video endpoint, with API keys, credit balance, async task tracking, and refunds on failed tasks.
What are the MiniMax H3 Max API model IDs?
minimax-h3-max-text-to-video and minimax-h3-max-image-to-video. Pick the ID that matches your input type; each route validates its own parameter set. These are the two H3 Max model IDs currently exposed by EvoLink.
How much does the MiniMax H3 Max API cost?
MiniMax H3 Max is billed per second of output video through your shared EvoLink credit balance. 768p is the default tier; 480p is billed at 5/8 of the 768p rate. Use the pricing section and playground estimator for your user group's live rate before you generate.
Does MiniMax H3 Max support reference images, video, or audio?
Not on the two H3 Max routes currently exposed by EvoLink. They generate from text plus an optional first and last frame. When a brief needs reference images, video, or audio, use minimax-h3-reference-to-video on EvoLink.