MiMo-V2.5 is a efficient-tier language model from Xiaomi MiMo. MiMo-V2.5 is a proprietary model available exclusively through Xiaomi MiMo's API. The MiMo-V2.5 family is Xiaomi MiMo's model series for this capability tier.
MiMo-V2.5 is priced at $0.14/1M input tokens and $0.28/1M output tokens. Output tokens are 2× more expensive than input tokens — this ratio reflects the sequential nature of autoregressive generation, which requires a separate forward pass per output token versus parallel processing of all input tokens simultaneously. At a typical usage pattern of 1,000 input tokens and 500 output tokens per call, MiMo-V2.5 costs approximately $0.28 per 1,000 API calls. Xiaomi MiMo does not publish a prompt caching rate for this model, so repeated long contexts are billed at the standard $0.14/1M input rate.
Its 33K-token context window is sufficient for most production use cases, handling documents up to ~25,000 words or multi-turn conversations spanning dozens of exchanges.
MiMo-V2.5 is best suited to cost, chat, reasoning. Supported capabilities include function calling / tool use for agentic workflows, streaming token output for real-time UIs. Function calling support makes it suitable for building AI agents, structured data extraction pipelines, and any workflow requiring the model to invoke external APIs or return typed JSON. When evaluating this model for a specific workload, the most important factors are: context window (does your input fit?), output price (how long are your generations?), and latency (is this interactive or batch?). The pricing table above shows how MiMo-V2.5 compares to similar models across these dimensions.
MiMo-V2.5 sits in the efficient tier — optimized for speed and cost while maintaining solid quality, ideal for high-volume or latency-sensitive workloads. Unlike open-weights alternatives, MiMo-V2.5 is only available via Xiaomi MiMo's API — there is no self-hosted option, which simplifies deployment but creates vendor dependency. When comparing MiMo-V2.5 to alternatives, use the similar models section on this page to find models at comparable price points with different capability tradeoffs. The intelligence score (N/A/100) reflects aggregate benchmark performance — a useful proxy for general capability, though real-world performance varies significantly by task type. Always test with your specific prompts and use case before committing to a model for production.
Input price vs 217 efficient models tracked. Avg: $0.321/1M.
| Model ID | MiMo-V2.5 |
| Provider | Xiaomi MiMo |
| Model Family | MiMo-V2.5 |
| Tier | Efficient |
| Context Window | 32,768 tokens (33K) |
| Max Output Tokens | — |
| Input Price | $0.14 / 1M tokens |
| Output Price | $0.28 / 1M tokens |
| Cached Input Price | Not available |
| Throughput | — |
| Latency (P50) | — |
| Intelligence Score | — |
| LiveBench Score | — |
| Cost per Task (LiveBench) | — |
| Data Confidence | — |
| HLE Score | — |
| GPQA Diamond | — |
| SWE-bench Score | — |
| OSWorld Score | — |
| BrowseComp Score | — |
| Terminal-Bench Score | — |
| AutoBench Score | — |
| Parameters | — |
| Vision Support | No |
| Function Calling | Yes |
| Streaming | Yes |
| Reasoning Model | No |
| Open Weights | No |
| Data Source | Static (verified) |
| Last Updated | 2026-10-18 |
Self-hosting MiMo-V2.5? These GPUs are well-matched for this model's compute and memory requirements.