Stronger MiMo Pro tier for multimodal reasoning and coding-agent executionMiMo-V2.6-Pro by xiaomi is offered by 32 providers on this page. Public prices are shown for 29 of them. Its official list price is $0.435 per 1M input tokens and $0.87 per 1M output tokens. The lowest paid channel is Neuralwatt at $0.283 / $0.566 per 1M, about 1.5× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. It also has 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 29.9 on the Intelligence Index, with 46.9 for Strategy & Ops, its strongest domain. Against its lowest blended price of $0.353 per 1M, that is roughly 85 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 53 tokens per second, with 3.44s to the first token. Running one task of the Artificial Analysis suite costs about $0.2572, which reflects how many tokens its reasoning consumes rather than the unit price alone.
The context window is 1,048,576 tokens at the reference host, but hosts report different limits, from 1,000,000 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.
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 (Singapore) | Gateway | Subscription | $0 | — | 1,048,576 | 131,072 | ||
| Xiaomi Token Plan (China) | Gateway | Subscription | $0 | — | 1,048,576 | 131,072 | ||
| Xiaomi Token Plan (Europe) | Gateway | Subscription | $0 | — | 1,048,576 | 131,072 | ||
| Neuralwatt mimo-v2.6-pro-flex | Gateway | $0.28 | $0.57 | $0.0023 | — | 1,048,560 ⚠ | 393,216 | |
| Vultr mimo-v2.6-pro-rl | Cloud | $0.40 | $0.80 | — | — | 1,048,576 | 131,072 | |
| Standard Compute | Gateway | $0.43 | $0.87 | $0.0036 | — | 1,048,576 | 50,000 | |
| Deep Infra XiaomiMiMo/MiMo-V2.6-Pro | Cloud | $0.43 | $0.87 | $0.0036 | — | 1,048,576 | 131,072 | |
| Requesty | Gateway | $0.43 | $0.87 | $0.0036 | — | 1,048,576 | 131,072 | |
| XiaomiOfficial | First-party | $0.44 | $0.87 | $0.0036 | — | 1,048,576 | 131,072 | |
| Kilo Gateway | Gateway | $0.44 | $0.87 | $0.004 | — | 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 12 of 32 providers.
2 / 32 providers expose no reasoning control (reasoning_options: []).
3 more channels offer $0 (Xiaomi Token Plan (Singapore), Xiaomi Token Plan (China), Xiaomi Token Plan (Europe)); free tiers usually have rate limits and no SLA, excluded from ranking.
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| DeepSWE | variant: MiMo-V2.6 Pro comparison column · v1.1 | 71.9 | score | Source ↗ |
| ProgramBench | variant: MiMo-V2.6 Pro comparison column | 26.5 | score | Source ↗ |
| MiMo Code Bench | variant: MiMo-V2.6 Pro comparison column | 63.2 | score | Source ↗ |
| AutomationBench | variant: MiMo-V2.6 Pro comparison column · v1.0.6 | 53.1 | score | Source ↗ |
| Toolathlon-Verified | variant: MiMo-V2.6 Pro comparison column | 76.9 | score | Source ↗ |
| GDPval-AA | variant: MiMo-V2.6 Pro comparison column · v2.1 | 1673 | Elo | Source ↗ |
| Agents' Last Exam | variant: MiMo-V2.6 Pro comparison column | 31.6 | score | Source ↗ |
| Terminal-Bench | variant: MiMo-V2.6 Pro comparison column · v4.0 | 34.9 | score | Source ↗ |
| Terminal-Bench | variant: MiMo-V2.6 Pro comparison column · v2.1 | 89.9 | score | Source ↗ |
| OSWorld-Verified | variant: MiMo-V2.6 Pro comparison column | 82 | score | Source ↗ |
| JobBench | variant: MiMo-V2.6 Pro comparison column | 62 | score | Source ↗ |
| CyberGym | variant: MiMo-V2.6 Pro comparison column | 94 | score | Source ↗ |
| MiMo Cyber Bench | variant: MiMo-V2.6 Pro comparison column | 80.2 | score | Source ↗ |
| ExploitGym | variant: MiMo-V2.6 Pro comparison column | 17.8 | score | Source ↗ |
| ExploitBench | variant: MiMo-V2.6 Pro comparison column | 47.9 | score | Source ↗ |
| SEC-Bench Pro | variant: MiMo-V2.6 Pro comparison column | 66.3 | score | Source ↗ |
| MiMo VisualCoding | variant: MiMo-V2.6 Pro comparison column | 72.3 | 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 scale (percent correct, points or an index), so rows are not comparable with one another.