# MiniMax H3 (MiniMax) — API pricing and providers

> 2K video generation. Model id `minimax/hailuo-03`. Video model by MiniMax.

- Page: https://infro.io/models/minimax/hailuo-03
- Vendor: MiniMax (https://infro.io/models/minimax)
- Modality: Video
- Endpoint through INFRO: `POST /v1/videos` at https://api.infro.io/v1
- List rate: $0.08 per second of video
- Rates checked: 2026-10-05

Rates are MiniMax's published list price: what the customer's own provider account bills, not an INFRO charge. INFRO is a BYOK control plane; it charges a software subscription and adds 0% to model spend.

## Providers that serve it

| Provider | Model id sent |
| --- | --- |
| OpenRouter | `minimax/hailuo-3` |
| Runway | `hailuo3` |
| MiniMax | `MiniMax-H3` |

## Questions

### How much does the MiniMax H3 API cost?

MiniMax's published list rate for MiniMax H3 is $0.08 per second of video (checked 2026-10-05). The provider account you connect bills you at the rate on that account, so a negotiated rate replaces the list rate. INFRO adds 0% to model spend.

### Which providers serve MiniMax H3?

In INFRO's provider registry, MiniMax H3 can be served by OpenRouter, Runway and MiniMax. You connect your own account with any of them, and INFRO routes and fails over between the ones you connect.

### What is the MiniMax H3 model ID?

Request it from INFRO as "minimax/hailuo-03". INFRO sends each provider its own id: OpenRouter "minimax/hailuo-3", Runway "hailuo3", MiniMax "MiniMax-H3".

### How do I call MiniMax H3 through an OpenAI-compatible API?

Point an OpenAI SDK, or any HTTP client, at https://api.infro.io/v1 with an INFRO gateway key and send model "minimax/hailuo-03" to POST /v1/videos. INFRO runs the request on a provider account you connected and returns the provider's response with an estimated cost.

### Does INFRO mark up MiniMax H3 usage?

No. MiniMax or the provider you connect bills model usage to your own account. INFRO charges a software subscription for routing, failover, observability, budgets and policy, and takes 0% of model spend.