MiMo-V2.5-Pro-UltraSpeed
Summary
MiMo-V2.5-Pro-UltraSpeed is an open-weight language model from Xiaomi (MiMo), released on 8 Jun 2026. It accepts text and generates text, with a 1M-token context window and up to 131K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $1.30 per million input tokens and $2.61 per million output tokens (Xiaomi MiMo API), across 1 provider we track.
MiMo pro model for strong multimodal reasoning and agent execution
Last verified 4 Oct 2026. Every figure on this page links to its source.
Specifications
| Developer | Xiaomi (MiMo) |
|---|---|
| Release date | 8 Jun 2026 [models.dev] |
| Status | Preview [models.dev] |
| Weights | Open weights [models.dev] |
| Context window | 1M (1,048,576 tokens) [models.dev] |
| Max output | 131K tokens [models.dev] |
| Knowledge cutoff | Dec 2024 [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | Yes [models.dev] |
| Tool calling | Yes [models.dev] |
MiMo-V2.5-Pro-UltraSpeed API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| Xiaomi MiMo API mimo-v2.5-pro-ultraspeed | $1.30 | $2.61 | $0.01 | 1M | models.dev, 4 Oct 2026 |
Frequently asked questions
What is the context window of MiMo-V2.5-Pro-UltraSpeed?
MiMo-V2.5-Pro-UltraSpeed has a context window of 1,048,576 tokens (1M) and can generate up to 131,072 tokens in a single response, according to models.dev.
How much does the MiMo-V2.5-Pro-UltraSpeed API cost?
Through Xiaomi MiMo API, MiMo-V2.5-Pro-UltraSpeed costs $1.30 per million input tokens and $2.61 per million output tokens. Prices last verified 4 Oct 2026.
Is MiMo-V2.5-Pro-UltraSpeed open source?
MiMo-V2.5-Pro-UltraSpeed is an open-weight model. Check the license terms before commercial use.
When was MiMo-V2.5-Pro-UltraSpeed released?
Xiaomi (MiMo) released MiMo-V2.5-Pro-UltraSpeed on 8 Jun 2026, according to models.dev.
Change history
No changes detected since we started tracking this model. We re-check every source daily.