# MiniMax H3 Usage, Cost & Rank | OpenCode Data

MiniMax general-purpose video model with multimodal references and synchronized stereo audio. Open H3-Base checkpoints; Context-IR and 2K regeneration are not included in the initial weights release.

- Page: https://opencode.ai/data/minimax/minimax-h3
- JSON: https://opencode.ai/data/minimax/minimax-h3.json
- Model ID: minimax/MiniMax-H3
- Lab: MiniMax

## Model facts

| Fact | Value |
| --- | --- |
| Context window | 0 |
| Max output | 0 |
| Knowledge cutoff | - |
| Release date | 2026-07-31 |
| Input modalities | text, image, video, audio |
| Output modalities | video, audio |
| Reasoning | No |
| Tool calling | No |
| Open weights | Yes |
| Weights | [Hugging Face: H3-Base FL2VA / Ref2VA](https://huggingface.co/MiniMaxAI/MiniMax-H3) |

## Methodology

- Updates: Aggregated every hour. Days and weeks use UTC.
- Tokens: Input, output, reasoning, and cached tokens for each request.
- Users and sessions: Approximate counts of distinct users and OpenCode sessions.
- Cost: Session cost is the average cost per OpenCode session. Token prices are list prices from the OpenCode model catalog.
- Retention: The share of a model's users in one week who use it again the next week.
- Citation: Cite OpenCode Data (opencode.ai/data) with the update time shown at the top of the page.