# MiMo-V2-Omni

> MiMo-V2-Omni is a proprietary language model from Xiaomi (MiMo), released on 18 Mar 2026. It accepts text, images, audio, video and PDFs and generates text, with a 262K-token context window and up to 131K output tokens per response. Xiaomi (MiMo) has deprecated this model.

Source page: https://www.aimodel.directory/models/mimo-v2-omni
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Xiaomi (MiMo)
- **Release date:** 18 Mar 2026 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/xiaomi/models/mimo-v2-omni.toml)
- **Status:** Deprecated (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/xiaomi/models/mimo-v2-omni.toml)
- **Weights:** Proprietary (API only) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/xiaomi/models/mimo-v2-omni.toml)
- **Context window:** 262K (262,144 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/xiaomi/models/mimo-v2-omni.toml)
- **Max output:** 131K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/xiaomi/models/mimo-v2-omni.toml)
- **Knowledge cutoff:** Dec 2024 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/xiaomi/models/mimo-v2-omni.toml)
- **Input:** Text, images, audio, video and PDFs (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/xiaomi/models/mimo-v2-omni.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/xiaomi/models/mimo-v2-omni.toml)
- **Reasoning mode:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/xiaomi/models/mimo-v2-omni.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/xiaomi/models/mimo-v2-omni.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|

## FAQ

### What is the context window of MiMo-V2-Omni?

MiMo-V2-Omni has a context window of 262,144 tokens (262K) and can generate up to 131,072 tokens in a single response, according to models.dev.

### Is MiMo-V2-Omni open source?

No. MiMo-V2-Omni is a proprietary model; Xiaomi (MiMo) has not released its weights.

### When was MiMo-V2-Omni released?

Xiaomi (MiMo) released MiMo-V2-Omni on 18 Mar 2026, according to models.dev.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "MiMo-V2-Omni", https://www.aimodel.directory/models/mimo-v2-omni