Skip to content
Model infoModelsSnapshot: 15 Oct 2026

fal / H3 Max

MiniMax H3 Max Turbo

fal Research’s faster named H3 derivative for text and keyframe video generation, with native audio and resolution-dependent pricing.

availableClosed weightsVideo generation
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
7 of 21 specification fields collected
Output resolution480P, 768P, 1080PSee specification notes below
Clip duration0.92–15 seconds; fractional durations acceptedSee specification notes below
Input billingSee ratesfal API · text-to-video
Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum input tokens
Not collected
Maximum output
Not collected
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected

A JSON response containing a video file is not constrained JSON Schema generation.

Streaming
Not collected

Queue status/log streaming is not incremental video output.

Batch processing
Not collected

Queued requests do not establish a Batch Inference API.

Fine-tuning
Not collected

Public base weights and a public realism LoRA do not establish fine-tuning support for Max or Max Turbo.

Knowledge cutoff
Not collected
Release date
2026-08-26Source for Release date (opens in a new tab)

Announcement of the named Max and Max Turbo variants, not a later hosted route launch date.

Parameters
Not collected
Architecture
Not collected
Languages
Not collected
Context caching
Not collected

No documented prompt-cache controls, rates, minimum input or lifetime for these endpoints.

Maximum prompt characters
50,000Source for Maximum prompt characters (opens in a new tab)

fal API prompt limit; MiniMax native Max has a separate 7,000-character limit.

Output modalities
Video, AudioSource for Output modalities (opens in a new tab)

Synchronized video audio does not establish a standalone speech or music API.

Output resolutions
480P, 768P, 1080PSource for Output resolutions (opens in a new tab)

480P/768P native; 1080P latent refinement of a 768P source. MiniMax native Max supports only 480P/768P.

Video duration
0.92–15 seconds; fractional durations acceptedSource for Video duration (opens in a new tab)

fal request duration defaults to 5 seconds; actual output may be about 0.7 seconds longer. Use at least two seconds with target_audio_url.

Base model
MiniMax H3 open-weight base; post-trained by fal ResearchSource for Base model (opens in a new tab)
Input modalities
Text, Image, AudioSource for Input modalities (opens in a new tab)

Available inputs depend on the selected route; target audio on text/image routes replaces the soundtrack, while reference audio conditions generation.

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

fal API · text-to-video

Provider source (opens in a new tab)
API model ID
minimax/h3-max-turbo/text-to-video
Access
POST https://queue.fal.run/minimax/h3-max-turbo/text-to-video with Authorization: Key <FAL_KEY>. GET returned status_url/response_url; PUT cancel_url to request cancellation. No authenticated generation performed.
Regions
Hosted API; inference residency unverified
Context / input limit
Not collected
Maximum input tokens
Not collected
Maximum output
Not collected
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected

A JSON response containing a video file is not constrained JSON Schema generation.

Streaming
Not collected

Queue status/log streaming is not incremental video output.

Batch processing
Not collected

Queued requests do not establish a Batch Inference API.

Fine-tuning
Not collected

Public base weights and a public realism LoRA do not establish fine-tuning support for Max or Max Turbo.

Knowledge cutoff
Not collected
Release date
2026-08-26Source for Release date (opens in a new tab)

Announcement of the named Max and Max Turbo variants, not a later hosted route launch date.

Parameters
Not collected
Architecture
Not collected
Languages
Not collected
Context caching
Not collected

No documented prompt-cache controls, rates, minimum input or lifetime for these endpoints.

Maximum prompt characters
50,000Source for Maximum prompt characters (opens in a new tab)

fal API prompt limit; MiniMax native Max has a separate 7,000-character limit.

Output modalities
Video, AudioSource for Output modalities (opens in a new tab)

Synchronized video audio does not establish a standalone speech or music API.

Output resolutions
480P, 768P, 1080PSource for Output resolutions (opens in a new tab)

480P/768P native; 1080P latent refinement of a 768P source. MiniMax native Max supports only 480P/768P.

Video duration
0.92–15 seconds; fractional durations acceptedSource for Video duration (opens in a new tab)

fal request duration defaults to 5 seconds; actual output may be about 0.7 seconds longer. Use at least two seconds with target_audio_url.

Base model
MiniMax H3 open-weight base; post-trained by fal ResearchSource for Base model (opens in a new tab)
Required request fields
Non-empty prompt and prompt_expansion_mode are marked required. Expansion defaults to balanced in property metadata, but callers should provide it explicitly.Source for Required request fields (opens in a new tab)
Prompt expansion
disabled, balanced or quality; balanced is the declared default. Approximate expansion times are about one second or up to thirty seconds, not an end-to-end SLA.Source for Prompt expansion (opens in a new tab)
Random seed
Optional integer; omitted means random. Bounds are not specified.Source for Random seed (opens in a new tab)
Safety checker
enable_safety_checker defaults to true.Source for Safety checker (opens in a new tab)
Output transport
sync_mode=false returns a CDN URL; true returns Base64. This changes file transport, not whether inference is synchronous.Source for Output transport (opens in a new tab)
Timing measurements
timings.inference measures DiT denoising only, excluding the rest of the request. expanded_prompt may be null if unchanged, disabled or handled by the MiniMax hosted API.Source for Timing measurements (opens in a new tab)
Asynchronous generation
SupportedSource for Asynchronous generation (opens in a new tab)

Submit via queue.fal.run and poll the returned status/result URLs.

Cancellation and task deletion
Queued cancellation removes a request; in-progress cancellation signals the runner and may not stop execution.Source for Cancellation and task deletion (opens in a new tab)
Concurrent requests
Account-wide across endpoints: new accounts start at two concurrent running requests; self-serve capacity scales to forty with paid-invoice history. Per-model limits and enterprise allocations can differ. Inspect the account dashboard for actual capacity.Source for Concurrent requests (opens in a new tab)
Input media transport
Public URLs without required cookies/auth, presigned URLs, Base64 data URIs or SDK uploads. File uploads are public by default unless access controls are configured.Source for Input media transport (opens in a new tab)
Output link expiry
CDN lifecycle can be set at account or request level, including X-Fal-Object-Lifecycle-Preference. No universal output URL lifetime is assumed.Source for Output link expiry (opens in a new tab)
Soundtrack replacement
Optional HTTP(S)/Base64 audio, at least two seconds and at most 15 MB; requested output must be at least two seconds. Replaces the soundtrack, trims from the end or pads silence without changing playback speed. Exceptionally high input sample rates may be resampled to 96 kHz.Source for Soundtrack replacement (opens in a new tab)
Aspect ratios
21:9, 16:9, 4:3, 1:1, 3:4, 9:16Source for Aspect ratios (opens in a new tab)

Defaults to 16:9.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
Video generation480P output · standard1$0.025second of output video
Video generation768P output · standard1$0.04second of output video
Video generation1080P output · standard1$0.08second of output video
Dated promotion480P output · promotion ends Oct 15, 20262$0.015second of output video
Dated promotion768P output · promotion ends Oct 15, 20262$0.024second of output video
Dated promotion1080P output · promotion ends Oct 15, 20262$0.048second of output video

Rate conditions

  1. Published standard rate after the October 15 promotion. Dated promotional rates are listed separately.
  2. 40% promotion observed October 14, 2026; provider says ends October 15, with no exact cutoff time or timezone. Do not treat as a permanent price or apply to other routes.
Pricing source (opens in a new tab)

Data & enterprise terms

Public CDN file access and configurable object lifecycle are documented. These do not establish training use, full request-data retention or inference residency.

Read the service policy (opens in a new tab)

fal API · image-to-video

Provider source (opens in a new tab)
API model ID
minimax/h3-max-turbo/image-to-video
Access
POST https://queue.fal.run/minimax/h3-max-turbo/image-to-video with Authorization: Key <FAL_KEY>. GET returned status_url/response_url; PUT cancel_url to request cancellation. No authenticated generation performed.
Regions
Hosted API; inference residency unverified
Context / input limit
Not collected
Maximum input tokens
Not collected
Maximum output
Not collected
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected

A JSON response containing a video file is not constrained JSON Schema generation.

Streaming
Not collected

Queue status/log streaming is not incremental video output.

Batch processing
Not collected

Queued requests do not establish a Batch Inference API.

Fine-tuning
Not collected

Public base weights and a public realism LoRA do not establish fine-tuning support for Max or Max Turbo.

Knowledge cutoff
Not collected
Release date
2026-08-26Source for Release date (opens in a new tab)

Announcement of the named Max and Max Turbo variants, not a later hosted route launch date.

Parameters
Not collected
Architecture
Not collected
Languages
Not collected
Context caching
Not collected

No documented prompt-cache controls, rates, minimum input or lifetime for these endpoints.

Maximum prompt characters
50,000Source for Maximum prompt characters (opens in a new tab)

fal API prompt limit; MiniMax native Max has a separate 7,000-character limit.

Output modalities
Video, AudioSource for Output modalities (opens in a new tab)

Synchronized video audio does not establish a standalone speech or music API.

Output resolutions
480P, 768P, 1080PSource for Output resolutions (opens in a new tab)

480P/768P native; 1080P latent refinement of a 768P source. MiniMax native Max supports only 480P/768P.

Video duration
0.92–15 seconds; fractional durations acceptedSource for Video duration (opens in a new tab)

fal request duration defaults to 5 seconds; actual output may be about 0.7 seconds longer. Use at least two seconds with target_audio_url.

Base model
MiniMax H3 open-weight base; post-trained by fal ResearchSource for Base model (opens in a new tab)
Input modalities
Text, Image, AudioSource for Input modalities (opens in a new tab)
Required request fields
Non-empty prompt and prompt_expansion_mode are marked required. Expansion defaults to balanced in property metadata, but callers should provide it explicitly.Source for Required request fields (opens in a new tab)
Prompt expansion
disabled, balanced or quality; balanced is the declared default. Approximate expansion times are about one second or up to thirty seconds, not an end-to-end SLA.Source for Prompt expansion (opens in a new tab)
Random seed
Optional integer; omitted means random. Bounds are not specified.Source for Random seed (opens in a new tab)
Safety checker
enable_safety_checker defaults to true.Source for Safety checker (opens in a new tab)
Output transport
sync_mode=false returns a CDN URL; true returns Base64. This changes file transport, not whether inference is synchronous.Source for Output transport (opens in a new tab)
Timing measurements
timings.inference measures DiT denoising only, excluding the rest of the request. expanded_prompt may be null if unchanged, disabled or handled by the MiniMax hosted API.Source for Timing measurements (opens in a new tab)
Asynchronous generation
SupportedSource for Asynchronous generation (opens in a new tab)

Submit via queue.fal.run and poll the returned status/result URLs.

Cancellation and task deletion
Queued cancellation removes a request; in-progress cancellation signals the runner and may not stop execution.Source for Cancellation and task deletion (opens in a new tab)
Concurrent requests
Account-wide across endpoints: new accounts start at two concurrent running requests; self-serve capacity scales to forty with paid-invoice history. Per-model limits and enterprise allocations can differ. Inspect the account dashboard for actual capacity.Source for Concurrent requests (opens in a new tab)
Input media transport
Public URLs without required cookies/auth, presigned URLs, Base64 data URIs or SDK uploads. File uploads are public by default unless access controls are configured.Source for Input media transport (opens in a new tab)
Output link expiry
CDN lifecycle can be set at account or request level, including X-Fal-Object-Lifecycle-Preference. No universal output URL lifetime is assumed.Source for Output link expiry (opens in a new tab)
Soundtrack replacement
Optional HTTP(S)/Base64 audio, at least two seconds and at most 15 MB; requested output must be at least two seconds. Replaces the soundtrack, trims from the end or pads silence without changing playback speed. Exceptionally high input sample rates may be resampled to 96 kHz.Source for Soundtrack replacement (opens in a new tab)
Frame controls
First frame, last frame, both or neither. Canvas follows first, else last. Omitting both falls back to text-to-video at 16:9. No aspect_ratio field is exposed on this route.Source for Frame controls (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
Video generation480P output · standard1$0.025second of output video
Video generation768P output · standard1$0.04second of output video
Video generation1080P output · standard1$0.08second of output video
Dated promotion480P output · promotion ends Oct 15, 20262$0.015second of output video
Dated promotion768P output · promotion ends Oct 15, 20262$0.024second of output video
Dated promotion1080P output · promotion ends Oct 15, 20262$0.048second of output video

Rate conditions

  1. Published standard rate after the October 15 promotion. Dated promotional rates are listed separately.
  2. 40% promotion observed October 14, 2026; provider says ends October 15, with no exact cutoff time or timezone. Do not treat as a permanent price or apply to other routes.
Pricing source (opens in a new tab)

Data & enterprise terms

Public CDN file access and configurable object lifecycle are documented. These do not establish training use, full request-data retention or inference residency.

Read the service policy (opens in a new tab)

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

fal API · text-to-video

minimax/h3-max-turbo/text-to-video
Not verified

No endpoint prompt-caching contract collected.

How it works
Not collected

No endpoint prompt-caching contract collected.

Minimum reusable input
Not collected

No endpoint prompt-caching contract collected.

Lifetime & refresh
Not collected

No endpoint prompt-caching contract collected.

How to enable it
Not collected

No endpoint prompt-caching contract collected.

Usage fields
Not collected

No endpoint prompt-caching contract collected.

Billing rules
Not collected

No endpoint prompt-caching contract collected.

Limits & data boundaries
Not collected

No endpoint prompt-caching contract collected.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Caching reviewed 14 Oct 2026

fal API · image-to-video

minimax/h3-max-turbo/image-to-video
Not verified

No endpoint prompt-caching contract collected.

How it works
Not collected

No endpoint prompt-caching contract collected.

Minimum reusable input
Not collected

No endpoint prompt-caching contract collected.

Lifetime & refresh
Not collected

No endpoint prompt-caching contract collected.

How to enable it
Not collected

No endpoint prompt-caching contract collected.

Usage fields
Not collected

No endpoint prompt-caching contract collected.

Billing rules
Not collected

No endpoint prompt-caching contract collected.

Limits & data boundaries
Not collected

No endpoint prompt-caching contract collected.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Caching reviewed 14 Oct 2026

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Qualified closed-weight inference: fal explicitly identifies its post-trained Max derivatives and states no separate Max weights release is listed. The reviewed official fal Hugging Face inventory contains only an H3 realism LoRA, not Max/Turbo weights; its GitHub inventory has no H3 repository. This is a dated public-release review, not proof of private checkpoint hashes or all unpublished distributions. The open MiniMax H3 base and public LoRA are excluded.

Classification evidence (opens in a new tab)

Lifecycle dates

Max and Max Turbo announced by fal Research26 Aug 2026Source (opens in a new tab)

Sources reviewed