MiMo V2 Models by Xiaomi
2 models2026Up to 1.0M ctxFrom $0.4/1M input
About
MiMo V2 is a family of 2 AI models by Xiaomi, released in 2026.
Specifications(2 models)
| Model | Released | Context | Vision | Multimodal |
|---|---|---|---|---|
| MiMo-V2-Omni | 2026-03 | 262K | Yes | Yes |
| MiMo-V2-Pro | 2026-03 | 1M | No | No |
Available From(1 provider)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| MiMo-V2-Omni | OpenRouter | $0.4 | $2 | Serverless |
| MiMo-V2-Pro | OpenRouter | $1 | $3 | Serverless |
Frequently Asked Questions
- What is MiMo V2 used for?
- MiMo V2 is used for vision and multimodal work and math-heavy prompts. The family description and listed model capabilities point to those workloads as the best fit.
- How does MiMo V2 compare to MiMo?
- MiMo V2 by Xiaomi is strongest where you need vision and multimodal work, while MiMo by Xiaomi is the closest related family to check for audio. MiMo V2 has 2 listed variants and reaches up to 1.0M context, while MiMo reaches up to 1.0M context, so compare the specs and pricing tables before choosing a production model.
- Which MiMo V2 model should I use?
- For the lowest listed input price, start with MiMo-V2-Omni through OpenRouter at $0.4/1M input tokens. For the most capable/latest local choice, evaluate MiMo-V2-Omni with 262K context and multimodal inputs.
