MiniMax H3 Max reference images: 2 free, then per image
MiniMax includes the first 2 images free on H3 Max (5 on H3) and charges per extra image. On Sume, check the catalog for accepted reference types.

MiniMax's pay-as-you-go page includes the first 2 reference images free on H3 Max and the first 5 on H3; every additional image is charged. On Sume the question is different: only models whose supported_input_references lists a type accept that type, so check the catalog first, then expect one reserved amount on submit.
How many reference images are free at MiniMax?
The image-input rows on the vendor page differ by model.
| Model | Free images | Each additional image |
|---|---|---|
| MiniMax-H3 | First 5 | $0.04 |
| MiniMax-H3-Max | First 2 | $0.074 |
| MiniMax-H3-Regeneration | First 5 | $0.025 |
Which reference types does Sume accept?
The video docs say: only models whose supported_input_references lists a type accept that type. Audio and video references are honored by the Seedance 2.x models, Wan 3.0, MiniMax H3 and MiniMax H3 Max. Read the list from /v1/catalog instead of assuming it.
Does Sume add a per-image surcharge?
The sources read here describe no separate per-image line. The docs say video billing is the workspace USD balance, reserved on submit at provider list x 1.25 (every model, minimax-h3-max included), and the pricing page says per-model rates are in the catalog. Read the reserved amount on the job. More on the vendor side: MiniMax H3 reference image surcharge.
Sources
Related posts
More in Pricing
- MiniMax H3 Max input video: billed per second, by resolution
MiniMax bills H3 Max input video by duration, at a rate set by output resolution. Sume lists video references for H3 Max and reserves list x 1.25.
- MiniMax H3 Max price per second: promo ends Sept 30, Sume bills list
fal lists MiniMax H3 Max at a 50% promo through September 30. Sume's rate is the standard list times 1.25, with 5 s and 15 s clip totals by resolution.
- MiniMax H3 regeneration to 2K re-bills the original inputs
MiniMax bills a 768P-to-2K H3 regeneration per output second and bills the original task's inputs again. Sume reserves list x 1.25 on submit.
- OmniHuman 1.5 price: $0.12/s BytePlus, $0.16/s fal
BytePlus lists OmniHuman 1.5 at 0.12 USD per second; fal shows 0.16 per second. Sume does not offer OmniHuman, but has two still-plus-audio routes.
Written by Sume