Deepinfra
99.79%Context262.1K
Max output131.1K
p50 latency6,213 ms
Throughput19.0 t/s
Input price$0.4
Output price$2
Zero retentionNo trainingCaching
Model directory
Baseer model profileLanguage model
xiaomi/mimo-v2.5
MiMo M2.5
A native full-modal model supporting text, image, video, and audio understanding, with powerful Agent capabilities.
Input / 1M tokens$0.119
Output / 1M tokens$0.238
Maximum context1.1M
Inference providers3
Price comparison
USD per one million tokens, using current provider data.
Provider latency
Last-hour p50 in milliseconds; lower is better.
Provider uptime
Reported availability over the last 24 hours; not a contractual SLA.
Inference providers
Compare current pricing, performance, and privacy across every available provider.
Gmicloud
98.22%Context1.1M
Max output131.1K
p50 latency2,955 ms
Throughput38.5 t/s
Input price$0.119
Output price$0.238
Caching
Xiaomi
99.81%Context1.1M
Max output131.1K
p50 latency4,707 ms
Throughput42.0 t/s
Input price$0.14
Output price$0.28
Caching
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Deepinfra | 262.1K | 131.1K | 6,213 ms | 19.0 t/s | 99.790% | $0.4 | $2 | |
Gmicloud | 1.1M | 131.1K | 2,955 ms | 38.5 t/s | 98.221% | $0.119 | $0.238 | |
Xiaomi | 1.1M | 131.1K | 4,707 ms | 42.0 t/s | 99.812% | $0.14 | $0.28 |
What can this model do?
Available modalities and capabilities across inference providers.
TextImageAdvanced reasoningTool useAutomatic cachingVisionTools
Technical profile
- Model type
- Language model
- Release date
- Apr 22, 2026
- Knowledge cutoff
- 2024-12
- Regions
- —
- API specifications
- V2, V3, V4
- Temperature control
- Supported
Model identifier
xiaomi/mimo-v2.5Model profile updated: Sep 12, 2026, 1:46 PM
Related models
More options from the same creator or model category.