H3 Max Extend Video API pricing on Fal
- id
- minimax/h3-max/extend-video
- minimax
- First seen 2026-11-07 14:04 UTC
- Open on fal.ai/models/minimax/h3-max/extend-video
RoutePlatform-hostedruns on fal
Basis: model page: endpointBilling.provider_type = "fal", is_partner_api = false Archived copy
Current prices
Per second of output4
| Variant | USD | Platform’s own wording | Since |
|---|---|---|---|
| 480p | $0.05/s | Billing is calculated per second of generated video, plus reference input charges beyond the included allowance. Video costs $0.05 per second at 480p, $0.08 per second at 768p, $0.16 per second at 1080p, and $0.32 per second at 2K. Each request includes 4,096 reference tokens at no additional charge. Reference usage above this allowance costs $0.02 per 1,000 tokens, prorated to the actual token co | |
| 768p | $0.08/s | Billing is calculated per second of generated video, plus reference input charges beyond the included allowance. Video costs $0.05 per second at 480p, $0.08 per second at 768p, $0.16 per second at 1080p, and $0.32 per second at 2K. Each request includes 4,096 reference tokens at no additional charge. Reference usage above this allowance costs $0.02 per 1,000 tokens, prorated to the actual token co | |
| 1080p | $0.16/s | Billing is calculated per second of generated video, plus reference input charges beyond the included allowance. Video costs $0.05 per second at 480p, $0.08 per second at 768p, $0.16 per second at 1080p, and $0.32 per second at 2K. Each request includes 4,096 reference tokens at no additional charge. Reference usage above this allowance costs $0.02 per 1,000 tokens, prorated to the actual token co | |
| 2K | $0.32/s | Billing is calculated per second of generated video, plus reference input charges beyond the included allowance. Video costs $0.05 per second at 480p, $0.08 per second at 768p, $0.16 per second at 1080p, and $0.32 per second at 2K. Each request includes 4,096 reference tokens at no additional charge. Reference usage above this allowance costs $0.02 per 1,000 tokens, prorated to the actual token co |
Change log
No changes yet. A platform’s first run sets the baseline; changes appear from the next one.
Earlier versions
| Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|
| $0.05/s | $0.05 / seconds | 2026-11-07 14:04 UTC → 2026-11-11 12:24 UTC |
Where these prices come from
Read from the platform’s public pages and APIs. Every read is archived, so any price here can be checked against what the platform showed at the time.
- fal.ai/models/minimax/h3-max/extend-videoLast read 2 h ago1 readsArchived copy
- api.fal.ai/v1/models/pricing?…Last read 4 days ago1 readsArchived copy