Xiaomi · LLMs & Coding
MiMo-V2.6-Pro-UltraSpeed
Catalog data · checked Nov 16, 2026
MiMo-V2.6-Pro-UltraSpeed is a language model from Xiaomi, released in September 2026. It reads text, images, audio and video and writes text, with a context window of 1.05M tokens and up to 131.1K output tokens per answer. It costs $4.35 per million input tokens and $8.7 per million output tokens. That puts it in the upper price range: 85% of the 185 paid language models we track cost less.
What it can do
- Tool calling
- Structured output
- Reasoning mode
- Image input
- File input
- Audio input
- Video input
- Image output
- Audio output
- Prompt caching
More prices
| Cached input (read) | $0.036 /1M |
What it costs in practice
| 1,000 support replies1,000 chats with 800 input and 250 output tokens each | $5.66 |
| Summarize a 300-page reportabout 150,000 input tokens in one request, 2,000 tokens out | $0.67 |
| 10,000 product descriptions300 input and 200 output tokens per text | $30.45 |
| One day of agentic codingabout 3M input and 150K output tokens across many calls | $14.36 |
Calculated from the list prices above. Your bill depends on your real token counts. Use your own numbers →
Compare MiMo-V2.6-Pro-UltraSpeed with
Questions & answers
How much does MiMo-V2.6-Pro-UltraSpeed cost?
MiMo-V2.6-Pro-UltraSpeed costs $4.35 per 1 million input tokens and $8.7 per 1 million output tokens (USD, list price checked Nov 16, 2026).
How large is the context window of MiMo-V2.6-Pro-UltraSpeed?
MiMo-V2.6-Pro-UltraSpeed can process up to 1,048,576 tokens per request and return up to 131,072 tokens. As a rule of thumb, 1,000 tokens are about 750 English words.
Does MiMo-V2.6-Pro-UltraSpeed support tool calling?
Yes. The API accepts tool (function) definitions and also supports structured JSON output.
Can MiMo-V2.6-Pro-UltraSpeed read images?
Yes, image input is supported.
