Open MiMo model for multimodal coding agents and long-context automation
MiMo-V2.5 by xiaomi is offered by 27 providers on this page. Public prices are shown for 22 of them. Its official list price is $0.14 per 1M input tokens and $0.28 per 1M output tokens. The lowest paid channel is Deep Infra at $0.14 / $0.28 per 1M, about 5.0× below the list price. It also has 2 free ($0) channels and 3 covered by a paid subscription; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.
Artificial Analysis rates it 25.2 on the Intelligence Index, with 56.8 for coding and 15.8 for agentic tasks. Against its lowest blended price of $0.175 per 1M, that is roughly 144 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 55 tokens per second, with 2.55s to the first token.
The context window is 1,048,576 tokens at the reference host, but hosts report different limits, from 262,144 to 1,050,000, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, Audio, and Video. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2024-12.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Xiaomi Token Plan (China) | Gateway | Subscription | $0 | — | 1,048,576 | 131,072 | ||
| Xiaomi Token Plan (Europe) | Gateway | Subscription | $0 | — | 1,048,576 | 131,072 | ||
| Xiaomi Token Plan (Singapore) | Gateway | Subscription | $0 | — | 1,048,576 | 131,072 | ||
| InferX mimo-v25 | Gateway | Free | — | — | 1,000,000 ⚠ | 100,000 | ||
| Kenari mimo-v2-5 | Gateway | Free | — | — | 1,048,576 | 131,072 | ||
| Deep Infra XiaomiMiMo/MiMo-V2.5 | Cloud | $0.14 | $0.28 | $0.0028 | — | 262,144 ⚠ | 16,384 | deprecated |
| NanoGPT | Gateway | $0.14 | $0.28 | $0.0028 | $0 | 1,048,576 | 131,072 | |
| Kilo Gateway | Gateway | $0.14 tiered >256K: $0.80 | $0.28 | $0.003 | — | 1,048,576 | 131,072 | |
| OpenRouter | Gateway | $0.14 | $0.28 | $0.0028 | — | 1,050,000 ⚠ | 131,072 | |
| ClinePass | Gateway | $0.14 | $0.28 | $0.0028 | — | 1,048,576 | 131,072 | |
| XiaomiOfficial | First-party | $0.14 | $0.28 | $0.0028 | — | 1,048,576 | 131,072 | |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Interleaved thinking (reasoning between tool calls) is declared by 14 of 27 providers.
5 / 27 providers expose no reasoning control (reasoning_options: []).
5 more channels offer $0 (Xiaomi Token Plan (China), Xiaomi Token Plan (Europe), Xiaomi Token Plan (Singapore) etc.); free tiers usually have rate limits and no SLA, excluded from ranking.
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| MiMo Coding Bench | — | 71.8 | score | Source ↗ |
| Claw-Eval | variant: text | 62.3 | score | Source ↗ |
| Terminal-Bench | v2.0 | 65.8 | score | Source ↗ |
| SWE-Bench Pro | — | 56.1 | score | Source ↗ |
| CharXiv Reasoning | — | 81 | score | Source ↗ |
| MMMU-Pro | — | 77.9 | score | Source ↗ |
| HR-Bench | variant: 4K | 88.5 | score | Source ↗ |
| OmniDocBench | — | 87.2 | score | Source ↗ |
| Claw-Eval | variant: multimodal | 23.8 | score | Source ↗ |
| Video-MME | — | 87.7 | score | Source ↗ |
| DailyOmni | — | 83.5 | score | Source ↗ |
| VideoHolmes | — | 64 | score | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.