MiniMax H3 Max Turbo API

Generate 5–15 second clips from text or a first frame with an optional last frame. Use 480p for drafts and 768p for selected takes, with per-second pricing and one EvoLink API key across video models.

MiniMaxVideo GenerationAvailable

From ~$0.024 / s for the 480p video rate$0.025 official price-5%

Text-to-VideoImage-to-VideoFirst / Last FrameFast GenerationShort-Form ClipsAsync API

Production routeLive

Live

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 with an optional last frame

Output

768p / 480p video (MP4)

Playground Pricing Model Guide API

Try MiniMax H3 Max Turbo before you integrate the API.

Test MiniMax H3 Max Turbo 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.

Prompt

Create a 5-second horizontal 16:9 cinematic short film.

Keep the woman highly consistent: young woman with dark wavy hair and bangs, black shirt, calm but tense expression, sitting alone in the back seat of a car. Keep the rainy car window, red and cyan neon reflections, dark interior, realistic city night atmosphere, shallow depth of field, and intimate film-noir mood.

0-1s: Rain slides slowly down the car window. She sits still in the back seat, looking through the glass. Red neon light washes across her face like a warning.

1-2s: A phone on her lap vibrates and lights up, but the screen shows no readable text. She glances down, does not answer, and quietly tightens her hand around it.

2-3s: A bright pair of headlights appears behind the car, reflected in the wet window. Her eyes shift toward the reflection.

3-4s: She stays calm. No panic. She turns the phone face down on the seat, then reaches into her coat and touches an old photograph.

4-5s: She looks toward the driver without raising her voice. Red light flashes across the window. End on her close-up through the rain-covered glass - no tears, no fear, only a cold final decision.

Style: realistic cinematic thriller, urban rainy night, neon reflections, film noir mood, restrained acting, natural face movement, real skin texture, low-light cinematography, shallow depth of field.

Avoid: exaggerated car chase, explosions, guns, fighting, crying, screaming, plastic skin, changing identity, random text, subtitles, watermark, logo, distorted face, chaotic camera movement.

Duration5s

Quality

Aspect Ratio

Estimated: ~$0.19012.92 cr

Ready

History

Results are kept for 24 hours — download anything you want to keep.

Your generation history will appear here

MiniMax H3 Max Turbo 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 · 480P · 5s · no input media

-5%Minimum charge

Credits8.075

One 5s 480P sample

Approx. Cost~$0.119

About 80 tests with $10 in credits.

The first test uses the cheapest visible route at 480p for 5s, with a first frame if required. Omitting quality defaults to 768p.

Testing Budget Guide

At the first-test settings: 5s at 480P

Add Credits

$10

About 80 tests

Good for a first validation.

$50

About 421 tests

Good for prompt and shot iteration.

$100

About 842 tests

Good before production integration.

Common Cost Examples

Short text-to-video test

T2V 5s 768p

~$0.190-5%

~12.92 cr·~$0.200 official price

Full-length clip

T2V 15s 768p

~$0.570-5%

~38.76 cr·~$0.600 official price

Image-to-video clip

I2V 10s 768p

~$0.380-5%

~25.84 cr·~$0.400 official price

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 Turbo Pricing

Mode	480P	768P	Billing
Text-to-VideoStandard route	$0.024/s-5% 1.615 cr/s$0.025 official price	$0.038/s-5% 2.584 cr/s$0.040 official price	Output video seconds
Image-to-VideoStandard route	$0.024/s-5% 1.615 cr/s$0.025 official price	$0.038/s-5% 2.584 cr/s$0.040 official price	Output video seconds

Text-to-Video

Standard route · Output video seconds

480P $0.024/s · 1.615 cr/s $0.025/s-5%

768P $0.038/s · 2.584 cr/s $0.040/s-5%

Image-to-Video

Standard route · Output video seconds

480P $0.024/s · 1.615 cr/s $0.025/s-5%

768P $0.038/s · 2.584 cr/s $0.040/s-5%

Billed per second of output video. Input frames are never charged separately — MiniMax H3 Max Turbo 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 Turbo best for?

Choose MiniMax H3 Max Turbo on EvoLink for 480p or 768p clips from text or a first frame, with an optional last frame. Choose H3 Max when the shot needs image, video or audio references, and H3 when it needs 2K. All three use the same EvoLink API key and balance; their model IDs and input limits differ.

Input

Text prompt, first frame with an optional last frame

Output

MP4 video

Duration

5-15 seconds per generation

Resolution

480p / 768p

References

First and last frame only; no reference media

Choose between H3 Max Turbo, H3 Max and H3

Capabilities below describe the routes currently available on EvoLink. Other providers may expose different resolutions or inputs. Use each model’s pricing section for current rates.

Feature	MiniMax H3 Max Turbo	MiniMax H3 Max	MiniMax H3
Primary role	Text and first/last-frame clips	Clips guided by reference media	2K output and reference workflows
Generation modes	T2V + I2V (first/last frame)	T2V + I2V + R2V	T2V + I2V + R2V
Reference input	Not on current EvoLink routes	Image + video + audio	Image + video + audio
Resolution	768p / 480p	480p / 768p	2K / 768p
Duration	5-15s	5–15s	4-15s
Billing	Per output second	Output seconds + applicable reference input fees	Per output second (+ reference video seconds)

Primary role

MiniMax H3 Max TurboText and first/last-frame clips

MiniMax H3 MaxClips guided by reference media

MiniMax H32K output and reference workflows

Generation modes

MiniMax H3 Max TurboT2V + I2V (first/last frame)

MiniMax H3 MaxT2V + I2V + R2V

MiniMax H3T2V + I2V + R2V

Reference input

MiniMax H3 Max TurboNot on current EvoLink routes

MiniMax H3 MaxImage + video + audio

MiniMax H3Image + video + audio

Resolution

MiniMax H3 Max Turbo768p / 480p

MiniMax H3 Max480p / 768p

MiniMax H32K / 768p

Duration

MiniMax H3 Max Turbo5-15s

MiniMax H3 Max5–15s

MiniMax H34-15s

Billing

MiniMax H3 Max TurboPer output second

MiniMax H3 MaxOutput seconds + applicable reference input fees

MiniMax H3Per output second (+ reference video seconds)

MiniMax H3 Max Turbo: two routes, two model IDs

Each generation mode is its own model ID behind the same API key and credit balance - pick the route that matches your input.

MiniMax H3 Max Turbo Text-to-Video

minimax-h3-max-turbo-text-to-video

Generate 768p or 480p video from a text prompt.

MiniMax H3 Max Turbo Image-to-Video

minimax-h3-max-turbo-image-to-video

Animate a required first frame with an optional last frame.

MiniMax H3 Max Turbo model information

Choose a route and output tier based on the input and delivery requirements of your workflow.

Model type

Video generation

Designed for fast text-to-video and image-to-video generation.

Supported inputs

Text, first frame, last frame

Turbo supports text and first-frame image input, with an optional last frame. For reference media, use MiniMax H3 Max: minimax-h3-max-reference-to-video.

API model IDs

minimax-h3-max-turbo-text-to-video / -image-to-video

MiniMax-H3-Max-Turbo is the upstream model name in the supplied API contract. EvoLink exposes two complete route-specific IDs for text and frame inputs through one video endpoint and credit balance.

Output and duration

768p / 480p, 5-15s, MP4

On EvoLink, omitting quality defaults to 768p. The current Turbo routes accept 480p or 768p and 5–15 seconds; other providers’ settings do not apply to these model IDs.

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.

Key MiniMax H3 Max Turbo API parameters

These fields cover the main integration decisions. Open the API Reference for route-specific request and response examples.

modelstring

Choose the text or image EvoLink model ID that matches your input.

Default: route-specific

promptstring

Describe the scene, motion, and camera behavior in up to 7000 characters.

Default: required

durationinteger

Set 5 through 15 output seconds (4-second clips are not supported); billing follows the output duration.

Default: 5

qualityenum

Select 480p or 768p. 480p is billed at 5/8 of the 768p per-second rate; there is no 2K tier.

Default: 768p

aspect_ratioenum

Text-to-Video only: 16:9, 21:9, 4:3, 1:1, 3:4, or 9:16. Image-to-Video follows the input frames.

Default: 16:9

image_startstring

Image-to-Video: required HTTP(S) URL of the first frame.

Default: required (I2V)

image_endstring

Image-to-Video: optional last-frame URL; a first frame is required.

Default: optional

callback_urlstring

Public HTTPS URL that receives the final task state; keep the task ID as a polling fallback.

Default: optional

Two ways to use MiniMax H3 Max Turbo: EvoLink API or Agent

Use the EvoLink API for product integration and batch jobs, or call it from Codex, Claude, or Gemini for fast creative and development workflows. Both paths share the same EvoLink API key, balance, model routes, and task history.

Option 1

Integrate with the EvoLink API

Best for: product backends, batch jobs, automated workflows

Call EvoLink’s unified video API from your server and control the model ID, parameters, task queue, callbacks, and result storage.

1Validate output and cost with a real brief in Playground
2Create an EvoLink API key in the console
3Pick the model ID that matches your task from the route cards above
4Submit the task and retrieve the result by polling or HTTPS callback

Create EvoLink API Key

Option 2

Call it with an Agent

Best for: creative and development tasks in Codex, Claude, and Gemini

Give the Agent your output goal, assets, and acceptance criteria. It can choose the route, assemble the request, track the task, and return the result without requiring you to hand-code every step.

1Set EVOLINK_API_KEY in your local environment; never put it in code or a prompt
2Describe the output goal, references, and the key parameters
3Ask the Agent to call a MiniMax H3 Max Turbo route and save the task ID
4Let the Agent poll the final state, download the result, and report failure reasons

Starting settings for three Turbo workflows

Choose the input first, then set duration and quality. These are suggested workflows, not measured speed or quality results.

Storyboard a camera move

Start with text-to-video at 480p for 5 seconds. Describe one subject, one action and one camera move; choose 16:9 for a landscape storyboard or 9:16 for a vertical concept.

Animate a product image

Use image-to-video with your product photo as image_start. Start at 768p for 5 seconds and describe a slow pan or orbit. The output aspect ratio follows the input image.

Connect an opening and closing frame

Send image_start and image_end together, then describe the transition between them. Use 5–15 seconds; a last frame alone is not accepted. For broader media references, use H3 Max.

Try these settings in the Turbo playground

MiniMax H3 Max Turbo API code example and error handling

This example shows the shortest runnable flow: create a task, save the returned task ID, then poll or wait for an HTTPS callback. Open the API tab for the complete parameter and response reference.

View complete API docs

cURL

curl -X POST https://api.evolink.ai/v1/videos/generations \
  -H "Authorization: Bearer $EVOLINK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax-h3-max-turbo-text-to-video",
    "prompt": "A female captain before a vast observation window as the fleet jumps away, cinematic slow dolly-in",
    "duration": 5,
    "quality": "768p",
    "aspect_ratio": "16:9",
    "callback_url": "https://your-domain.com/webhooks/video-task-completed"
  }'

# Save the returned task ID, then query:
curl https://api.evolink.ai/v1/tasks/{task_id} \
  -H "Authorization: Bearer $EVOLINK_API_KEY"

Parameter validation failed

Check every value against the parameter cards above: ranges, allowed options, asset counts, and file types must match the selected route.

Authentication or balance issue

Check the Authorization bearer token and confirm the available balance and task billing in the console.

Content or asset rejected

Review likeness rights, brand assets, readable text, sensitive content, and input-asset compliance.

Task failed or timed out

A MiniMax H3 Max Turbo task that reaches a final failed state is not charged. Keep the task ID, inspect the final state, and identify whether the cause is validation, review, or execution before retrying.

Callback not received

callback_url must be a public HTTPS URL, not localhost or a private network address. Always keep the task ID as a polling fallback.

Is MiniMax H3 Max Turbo worth adding to your video stack?

Choose H3 Max Turbo 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 want to compare the cost of 480p drafts and 768p selected takes before scaling up.
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.
You need reference images, video or audio: choose the MiniMax H3 Max reference route, or MiniMax H3 when 2K is also required.
You need 4-second clips; H3 Max Turbo 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.

Run a 5-second test

How to integrate MiniMax H3 Max Turbo in production

Choose the route by input type

Text-to-Video: minimax-h3-max-turbo-text-to-video. Image-to-Video: minimax-h3-max-turbo-image-to-video. Animate a required first frame with an optional last frame.

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.

Why use the MiniMax H3 Max Turbo 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 Turbo as one tested route and fall back to H3 or another family when a workload needs it.

Hailuo Model Family

Compare Hailuo generations under one EvoLink account and API key, then choose by resolution, duration, reference workflow, and cost.

Compare all Hailuo models

MiniMax H3 Max

Text, first-frame and reference-driven video at 480p / 768p, with 5–15s output.

View

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.

View

Choose the right H3 route for your next shot

Check Turbo’s launch details and the family comparison before moving workloads between routes.

MiniMax H3 Max Turbo launch details

See the two model IDs, output limits and first-frame requirements in the Turbo changelog.

MiniMax H3 vs Seedance 2.0

Compare the Hailuo routes with an available multimodal audio-video workflow.

MiniMax 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.

MiniMax H3 Max Turbo FAQ

What is MiniMax H3 Max Turbo?

MiniMax H3 Max Turbo is a speed-oriented variant in the MiniMax H3 family. On EvoLink, it generates 5–15 second videos at 480p or 768p from text or a required first frame with an optional last frame. The two input modes use separate model IDs.

How is MiniMax H3 Max Turbo different from MiniMax H3?

For the routes available on EvoLink, H3 Max Turbo 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 Turbo starts at 5 seconds; H3 starts at 4 seconds.

What can MiniMax H3 Max Turbo 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 Turbo available through EvoLink?

Yes. EvoLink exposes MiniMax H3 Max Turbo 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 Turbo API model IDs?

minimax-h3-max-turbo-text-to-video and minimax-h3-max-turbo-image-to-video. Pick the ID that matches your input type; each route validates its own parameter set. These are the two H3 Max Turbo model IDs currently exposed by EvoLink.

How much does the MiniMax H3 Max Turbo API cost?

MiniMax H3 Max Turbo 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 Turbo support reference images, video, or audio?

Turbo supports text and first-frame image input, with an optional last frame. For reference media, use MiniMax H3 Max: minimax-h3-max-reference-to-video.

Does MiniMax H3 Max Turbo support 2K output?

No on EvoLink's current H3 Max Turbo routes. They accept 480p and 768p, and reject 2K. Use MiniMax H3 when you need the 2K tier.

What is the shortest MiniMax H3 Max Turbo clip?

Five seconds. EvoLink's H3 Max Turbo contract accepts 5-15 seconds and rejects 4-second clips. The minimum charge follows the same floor: 480p at 5 seconds.

Does MiniMax H3 Max Turbo support 4K, longer clips, or a cancel endpoint?

No. Output is 768p or 480p with durations of 5 to 15 seconds, and there is no cancel endpoint, so tasks report can_cancel false and failures are refunded in full.

How do I get the completed MiniMax H3 Max Turbo video?

Submit the task, then poll the task endpoint or register a callback. When the status turns completed the response carries the MP4 URL. Download it and store it yourself.

How long is a MiniMax H3 Max Turbo result URL available?

Results are kept for 24 hours. Save anything you want to keep within that window — the URL stops resolving afterwards.

How does H3 Max Turbo differ from H3 Max on EvoLink?

Both offer 480p / 768p text-to-video and first-frame image-to-video, with an optional last frame and 5–15 second output. H3 Max also has a separate reference-to-video route; Turbo does not. Compare each page’s current pricing, then measure accepted-output cost and end-to-end time on your own workload.

Can I send only a last frame to H3 Max Turbo?

No. The image-to-video route requires image_start. Add image_end only together with the first frame; a last-frame-only request is rejected.

Does H3 Max Turbo guarantee real-time generation?

No completion time is guaranteed here. Provider speed demonstrations are specific to their test conditions; your elapsed time also includes queueing, prompt processing and result delivery. Measure submission-to-completion time on your workload.

Is H3 Max Turbo the same as a community H3 Turbo LoRA?

No. This page covers the hosted MiniMax H3 Max Turbo API on EvoLink. Community H3 Turbo LoRA projects use separate local inference workflows; their weights, hardware requirements and performance results do not define this API.

MiniMax H3 Max Turbo API

Try MiniMax H3 Max Turbo before you integrate the API.

MiniMax H3 Max Turbo pricing is per output second.

First Test Cost

Testing Budget Guide

Common Cost Examples

Short text-to-video test

Full-length clip

Image-to-video clip

MiniMax H3 Max Turbo Pricing

What is MiniMax H3 Max Turbo best for?

Choose between H3 Max Turbo, H3 Max and H3

MiniMax H3 Max Turbo: two routes, two model IDs

MiniMax H3 Max Turbo Text-to-Video

MiniMax H3 Max Turbo Image-to-Video

MiniMax H3 Max Turbo model information

Model type

Supported inputs

API model IDs

Output and duration

API pricing

Task lifecycle

Key MiniMax H3 Max Turbo API parameters

Two ways to use MiniMax H3 Max Turbo: EvoLink API or Agent

Integrate with the EvoLink API

Call it with an Agent

Starting settings for three Turbo workflows

Storyboard a camera move

Animate a product image

Connect an opening and closing frame

MiniMax H3 Max Turbo API code example and error handling

Parameter validation failed

Authentication or balance issue

Content or asset rejected

Task failed or timed out

Callback not received

Is MiniMax H3 Max Turbo worth adding to your video stack?

Good fit when

Consider another route when

How to integrate MiniMax H3 Max Turbo in production

Choose the route by input type

Submit and track an asynchronous task

Control cost and keep a fallback

Why use the MiniMax H3 Max Turbo API through EvoLink

Cost Clarity

Unified API

Unified Balance

Task Status Tracking

Model Choice

Hailuo Model Family

Other video models on EvoLink

Choose the right H3 route for your next shot

MiniMax H3 Max Turbo launch details

MiniMax H3 vs Seedance 2.0

MiniMax H3 vs Seedance 2.5

MiniMax H3 Max Turbo FAQ

What is MiniMax H3 Max Turbo?

How is MiniMax H3 Max Turbo different from MiniMax H3?

What can MiniMax H3 Max Turbo be used for?

Is MiniMax H3 Max Turbo available through EvoLink?

What are the MiniMax H3 Max Turbo API model IDs?

How much does the MiniMax H3 Max Turbo API cost?

Does MiniMax H3 Max Turbo support reference images, video, or audio?

Does MiniMax H3 Max Turbo support 2K output?

What is the shortest MiniMax H3 Max Turbo clip?

Does MiniMax H3 Max Turbo support 4K, longer clips, or a cancel endpoint?

How do I get the completed MiniMax H3 Max Turbo video?

How long is a MiniMax H3 Max Turbo result URL available?

How does H3 Max Turbo differ from H3 Max on EvoLink?

Can I send only a last frame to H3 Max Turbo?

Does H3 Max Turbo guarantee real-time generation?

Is H3 Max Turbo the same as a community H3 Turbo LoRA?