H3 Max
fal post-trains MiniMax H3 for prompt adherence and faster video generation. Max supports text and image inputs, native audio and clips of 5 to 15 seconds.
Anvisha Pai, Co-founder & CEO, Voyager
fal / MiniMax
›What we asked for
A self-portrait of H3 Max: a sculptural paper bird glides through a sunlit workshop, slow tracking camera, paper rustling, warm natural light.
minimax/h3-max/text-to-video
prompt_expansion_mode: disabled, aspect_ratio: 16:9, resolution: 768P, duration: 5
returned 1344 by 768 pixels
At a glance
- Price
- $0.04 per second at 768p on fal, verified September 18, 2026.
- Length
- 5 to 15 seconds.
- Measured wait
- 6 to 26 seconds from queue submission to result, including polling. One batch, not a service guarantee.
- Camera Controls
- Separate image-to-video endpoint with keyframed orbit, elevation and distance; example below.
- Lip Sync
- Separate photo-plus-audio endpoint. Input audio must be at least five seconds; longer inputs are clipped to 14.8 seconds.
Other Hailuo models: H3 Max Turbo, MiniMax H3, Hailuo 2.3. Compare all 4.
Anvisha's take
H3 Max is a useful low-cost option on this run. The sampled frames keep the kettle and dripper visible during the pour, the market has distinct stalls and people, and the title resolves into readable lettering. It still improvises: the text-to-video dripper gains a handle, while the image-to-video result fills the dripper like a cup. All nine requests returned, with estimated fixture cost $1.80 at the September promotion. These are frame-based observations; native audio was not scored by ear.
H3 Max real output: the same 9 clips every model gets
Every video model on this site gets the same 9 clips, so you can compare like with like. These are the clips H3 Max returned, one try each, nothing re-rolled or retouched. Each tile shows one frame of the clip until you press play. Generated on . The 9 clips took 6 to 26 seconds each and cost $1.80 in total.
A clean product shot that holds its shape through a full slow rotation.
›What we asked for
A matte black ceramic pour-over coffee dripper rotating slowly on a white turntable, soft studio light, seamless white background, product video, no text.
minimax/h3-max/text-to-video
prompt_expansion_mode: disabled, aspect_ratio: 16:9, resolution: 768P, duration: 5
returned 1344 by 768 pixels
A face, lip sync and a spoken line, where the model makes audio.
›What we asked for
A woman in her 40s with short grey hair stands in a bright kitchen, looks at the camera and says 'Good morning, the coffee is ready', natural window light, handheld feel, she smiles at the end.
minimax/h3-max/text-to-video
prompt_expansion_mode: disabled, aspect_ratio: 16:9, resolution: 768P, duration: 5
returned 1344 by 768 pixels
Set text that stays spelled correctly while it moves.
›What we asked for
A title card reading 'MODA SUMMER SESSIONS' animates in over slow-motion footage of a festival crowd at dusk, then a smaller line 'Friday 12 June' fades in beneath it. Bold condensed type, tangerine on navy.
minimax/h3-max/text-to-video
prompt_expansion_mode: disabled, aspect_ratio: 16:9, resolution: 768P, duration: 5
returned 1344 by 768 pixels
A steady drone push-in with stable geometry.
›What we asked for
Drone shot pushing slowly forward over a coastal town at sunrise, terracotta roofs, fishing boats in the harbour, long shadows, cinematic and steady.
minimax/h3-max/text-to-video
prompt_expansion_mode: disabled, aspect_ratio: 16:9, resolution: 768P, duration: 5
returned 1344 by 768 pixels
A spill in slow motion: does water behave like water.
›What we asked for
A glass of water tips over on a wooden table and spills in slow motion, water and three ice cubes sliding across the wood, macro lens, morning light.
minimax/h3-max/text-to-video
prompt_expansion_mode: disabled, aspect_ratio: 16:9, resolution: 768P, duration: 5
returned 1344 by 768 pixels
Hands, a kettle and a steady pour without extra fingers or teleporting objects.
›What we asked for
Close-up of hands pouring hot water from a gooseneck kettle in slow circles into a pour-over coffee dripper, steam rising, shallow depth of field, warm cafe light.
minimax/h3-max/text-to-video
prompt_expansion_mode: disabled, aspect_ratio: 16:9, resolution: 768P, duration: 5
returned 1344 by 768 pixels
Many people and objects moving at once without merging.
›What we asked for
A crowded Saturday farmers market seen from slightly above, shoppers with tote bags, a dog on a leash, a busker with a guitar, bunting swaying, late morning light, gentle camera drift.
minimax/h3-max/text-to-video
prompt_expansion_mode: disabled, aspect_ratio: 16:9, resolution: 768P, duration: 5
returned 1344 by 768 pixels
A named style held across every frame rather than drifting to photoreal.
›What we asked for
A lighthouse on a rocky cliff in a storm, in the style of a Japanese ukiyo-e woodblock print, waves crashing in flat colour with visible wood grain, animated like moving paper cutouts.
minimax/h3-max/text-to-video
prompt_expansion_mode: disabled, aspect_ratio: 16:9, resolution: 768P, duration: 5
returned 1344 by 768 pixels
Bring a still product photo to life without changing the product.
›What we asked for
The coffee dripper slowly fills as coffee drips through it, steam rising, the camera drifting gently around it, the dripper itself unchanged. (starting from The Nano Banana Pro product shot from the image fixture set.)
minimax/h3-max/image-to-video
prompt_expansion_mode: disabled, resolution: 768P, duration: 5
returned 768 by 768 pixels
How the cost under each picture was worked out: fal h3-max 768p $0.04/second for 5 requested seconds; 50% launch promotion through September 30, 2026; source read 2026-09-18, not a receipt.
Additional workflow tests
Separate from the common benchmark above. These tests examine longer shots, successive edits or specialized controls. One attempt per test, including failures. Costs are estimates from published rates.
H3 Max Camera Controls: product orbit
View the generated starting image
H3 Max
Camera parallax with a stationary product; this endpoint returns video, not a 3D mesh.
›What we asked for
The coffee dripper is rigid and motionless. Only the camera moves. Preserve its shape and materials and the white background.
minimax/h3-max/camera-controls
prompt_expansion_mode: disabled, camera_trajectory: [{"time":0,"azimuth":0,"elevation":0,"distance":1},{"time":1,"azimuth":45,"elevation":10,"distance":1}], resolution: 768P, duration: 5
returned 768 by 768 pixels
Generated . Cost basis: fal h3-max 768p $0.04/second for 5 requested seconds; 50% launch promotion through September 30, 2026; source read 2026-09-18, not a receipt. Original output.
The product remains recognizable across sampled frames. Its near-symmetric shape makes orbit accuracy difficult to establish from this example alone; a video result is not a reconstructed 3D mesh.
H3 Max Lip Sync: supplied voice
View the generated starting image
H3 Max
A generated portrait plus our synthetic speech sample. This endpoint takes image and audio URLs, not a text prompt. Synchronization has not been scored by ear.
›What we asked for
Animate the generated portrait to the supplied synthetic ad-read audio.
minimax/h3-max/lip-sync/image-to-video
resolution: 480P
returned 832 by 480 pixels
Generated . Cost basis: fal pricing API base rate $0.05/second at the selected 480P, read 2026-09-18; estimated using clipped source-audio duration. Original output.
The generated portrait changes mouth shape while the kitchen and clothing remain recognizable. The output retains supplied audio; synchronization quality has not been scored by ear.
Compare H3 Max
H3 Max pricing
| Where | Unit | Price | Source |
|---|---|---|---|
| fal | Second at 768p Promotional rate through September 30, 2026. Regular 768p rate is $0.08/second. Prices below distinguish promotion and regular billing. | $0.04 | fal model page, read |
| fal | Second at 480p through September 30, 2026 | $0.025 | fal model page, read |
| fal | Second at 480p after September 30, 2026 | $0.05 | fal model page, read |
| fal | Second at 768p after September 30, 2026 | $0.08 | fal model page, read |
| fal | Second at 1080p through September 30, 2026 | $0.08 | fal model page, read |
| fal | Second at 1080p after September 30, 2026 | $0.16 | fal model page, read |
| fal Lip Sync | Second at the tested 480P setting Separate endpoint and rate. Do not apply the Max text-to-video launch discount to this endpoint. | $0.05 | fal lip-sync pricing, read |
Is H3 Max free?
The fal endpoint is paid per generation. We have not verified a recurring free allowance for this specific model.
- •Provider promotions and consumer-app credits are separate from the API prices shown here.
fal model page, read
Where to use H3 Max
- fal · Hosted API and playground; the endpoint used for the samples below.
Voyager
Run H3 Max inside Voyager
Voyager is an agent for creative work that runs every model in this reference, H3 Max included. Brief it, and it picks the model, makes the thing and hands back something you can edit. Create an account to get started.
What we noticed running H3 Max
- •The sampled frames keep a continuous-looking pour, with kettle, hand and filter all visible. See the hands at work clip.
- •The source silhouette is recognizable, but the dripper fills with coffee like a cup. See the image to video clip.
- •The text-only dripper includes an unrequested handle; compare the image-conditioned result when product identity matters. See the product turntable clip.
H3 Max limits and API parameters
| Limit | Value |
|---|---|
| Duration | 5 to 15 seconds; 480P, 768P or 1080P. fal API schema, read |
| Lip-sync duration | Audio must be at least 5 seconds; inputs above 14.8 seconds are clipped. Output follows the clipped audio duration. fal lip-sync schema, read |
›Every setting, for developers
fal (minimax/h3-max/text-to-video)
fal API schema, read
| Parameter | Type | Values | Default |
|---|---|---|---|
| prompt | string | 1 to 50000 characters Required. | |
| aspect_ratio | string | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | 16:9 |
| duration | integer | 5 to 15 | 5 |
| resolution | string | 480P, 768P, 1080P | 768P |
| prompt_expansion_mode | string | disabled, balanced, quality Required. | balanced |
H3 Max Camera Controls
fal camera-control schema, read
| Parameter | Type | Values | Default |
|---|---|---|---|
| image_url | URL | Starting image Required. | |
| camera_trajectory | array | 2 to 12 camera keyframes: time, azimuth, elevation and distance | |
| duration | integer | 5 to 15 seconds | 5 |
| prompt_expansion_mode | string | disabled, balanced, quality Required. |
H3 Max Lip Sync
fal lip-sync schema, read
| Parameter | Type | Values | Default |
|---|---|---|---|
| image_url | URL | Image with aspect ratio from 0.4 to 2.5 Required. | |
| audio_url | URL | At least five seconds of audio; clipped at 14.8 seconds Required. | |
| resolution | enum | 480P, 768P, 1080P, 2K | 768P |
What H3 Max will not make
The hosted endpoint applies provider content checks. A refusal is retained as a failed sample rather than retried with a different prompt. Commercial-use availability is marked on the linked endpoint; review provider terms for your intended use.
fal model page, read
Alternatives to H3 Max
Frequently asked questions
How much does H3 Max cost?
The tested fal setting is $0.04 per second at 768p, read September 18, 2026. See the pricing table for conditions and other tiers.
Where can I use H3 Max?
The linked fal playground and API expose the endpoints used for our samples. Every returned file below includes the exact request settings.
How this page is made
Prices, limits and settings are read from the linked vendor and host pages on the dates shown. Every picture was generated by us through fal with the request shown under it, and the original files are kept unedited. A generation that failed is shown as a failure. Model and vendor names are used to identify the products; no vendor imagery appears on this page.
