HeyGen Video vs H3 Max
HeyGen Video and H3 Max are both MiniMax H3 post-trained by someone else: HeyGen Video by HeyGen, H3 Max by fal. Both ran the same nine prompts on fal at 768p and five seconds: H3 Max on 18 September 2026 with prompt expansion disabled, HeyGen Video on 22 October with fal's default prompt enhancement, turbo.
Anvisha Pai, Co-founder & CEO, Voyager
Which to use
Start with HeyGen Video. At fal's regular rates it costs a quarter of H3 Max, $0.02 a second at 768p against $0.08, so our nine clips cost $0.90, against $1.80 for H3 Max at its September launch price. H3 Max returned sooner, 6 to 26 seconds a clip against 21 to 41. On our prompts the two share H3's strengths and its habits. Both spelled the title, HeyGen's in full on both lines; both kept the kettle and dripper through the pour and made a dense, legible market. Both changed the products: H3 Max gave the turntable dripper a handle and filled the photographed one like a cup, HeyGen turned the turntable dripper into a spouted bowl and also filled the photo's dripper from inside. HeyGen also cuts within a one-shot prompt, as base H3 does: its spill cuts from the tipping glass to a macro of the ice cubes, so the spill itself is never on screen. H3 Max adds camera controls, lip sync and a live Director mode that HeyGen Video does not offer on fal. One run per prompt is a first look, not a ranking.
Side by side, measured
| HeyGen Video | H3 Max | |
|---|---|---|
| Vendor | HeyGen / MiniMax | fal / MiniMax |
| Released | Date not verified | Date not verified |
| Price | $0.02 per second at 768p via fal | $0.08 per second at 768p via fal |
| Seconds to make one clip | 21 to 41 | 6 to 26 |
| 9 clips cost | $0.90 | $1.80 |
| Length | 5 to 15 seconds, in whole seconds | 5 to 15 seconds |
Seconds and cost are from our own runs of the same 9 prompts through each model.
The same 9 prompts, HeyGen Video against H3 Max
One try each, nothing re-rolled or retouched, generated by us. HeyGen Video is on the left, H3 Max on the right. Every prompt has its own page with the whole roster.
Product turntable
Every model on this prompt →Both invent: H3 Max adds a handle, HeyGen turns the dripper into a faceted bowl with a spout.
›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.
Person speaking
Every model on this prompt →›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.
Animated title card
Every model on this prompt →HeyGen spells both lines in full. H3 Max's title resolves into readable lettering after the entrance.
›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.
Camera move
Every model on this prompt →›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.
Physics
Every model on this prompt →HeyGen cuts from the tipping glass to a macro of three ice cubes in a puddle; the spill is never shown.
›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.
Hands at work
Every model on this prompt →›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.
Busy scene
Every model on this prompt →›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.
Specific art style
Every model on this prompt →›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.
Image to video
Every model on this prompt →Both keep the photographed dripper's shape and fill it with coffee like a cup.
›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.
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.
Frequently asked questions
Are HeyGen Video and H3 Max the same model?
Both start from MiniMax H3 and are post-trained separately, HeyGen Video by HeyGen and H3 Max by fal. They behave alike on our prompts but are priced and served differently.
Which is cheaper?
HeyGen Video: $0.02 a second at 768p against H3 Max's regular $0.08 and H3 Max Turbo's $0.04, on fal, read October 22 and October 8, 2026.
Voyager
Run any of these inside Voyager
Voyager is an agent for creative work that runs every model on this page. Brief it, and it picks the model for the job, makes the thing and hands back something you can edit. Create an account to get started.