Xiaomi: MiMo-V2.5xiaomi
Bottom Line
Xiaomi: MiMo-V2.5: $0.12/1M input, $0.24/1M output, 1.1M context. MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...
API Pricing (per 1M tokens)
| Input | $0.12 |
| Output | $0.24 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $0.15 |
Specs & Performance
| Context Length | 1.1M |
| Max Output | 945K |
| Intelligence | — |
| Coding | — |
| Math | — |
| Speed | — |
| TTFT | — |
| CPS Grade | — |
| Input / Output Modalities | text, audio, image, video → text |
More from xiaomi
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the Xiaomi: MiMo-V2.5 API cost?
Xiaomi: MiMo-V2.5 costs $0.12/1M input tokens and $0.24/1M output tokens. Blended cost at a 3:1 ratio is about $0.15/1M tokens.
What is the context window of Xiaomi: MiMo-V2.5?
Xiaomi: MiMo-V2.5 supports a 1.1M token context window with up to 945K output tokens.
Is Xiaomi: MiMo-V2.5 worth it?
Xiaomi: MiMo-V2.5 has a CPS grade of — (score —), intelligence index —, coding index —. Use the compare page to benchmark against rivals.