Deepinfra
99.90%Context1M
Max output1M
p50 latency613 ms
Throughput40.0 t/s
Input price$1
Output price$3
Zero retentionNo trainingCaching
xiaomi/mimo-v2.5-pro
MiMo V2.5 Pro delivers significant improvements over its predecessor, MiMo-V2-Pro, in general agentic capabilities, complex software engineering, and long-horizon tasks. MiMo-V2.5-Pro is a 1.02T-parameter Mixture-of-Experts model with 42B active parameters, built on a hybrid-attention architecture with a 1M-token context window.
USD per one million tokens, using current provider data.
Last-hour p50 in milliseconds; lower is better.
Reported availability over the last 24 hours; not a contractual SLA.
Compare current pricing, performance, and privacy across every available provider.
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Deepinfra | 1M | 1M | 613 ms | 40.0 t/s | 99.902% | $1 | $3 | |
Gmicloud | 1.1M | 131K | 3,690 ms | 27.0 t/s | 98.468% | $0.305 | $0.609 | |
Xiaomi | 1.1M | 131K | 4,355 ms | 44.0 t/s | 99.903% | $0.435 | $0.87 |
Available modalities and capabilities across inference providers.
xiaomi/mimo-v2.5-proMore options from the same creator or model category.