MiMo-V2.5-Pro
xiaomi/mimo-v2.5-pro
Compare with MiMo-V2.5, GLM 5.2, DeepSeek V4 Flash 0731
CompareMiMo-V2.5-Pro
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 97.04% | 98.33% | 98.33% | 4.38s | 15.2s | 28 tps | 1.0M | $0.435 / $0.870 | |
DigitalOceandigitalocean | Healthy | 100% | 99.21% | 98.33% | 98.33% | 1.11s | 7.82s | 25 tps | 262K | $0.400 / $1.50 |
Novitanovita | Healthy | 100% | 96.32% | 98.74% | 98.74% | 3.34s | 42.2s | 24 tps | 1.0M | $0.480 / $0.960 |
| Healthy | 99.92% | 98.24% | 98.88% | 98.88% | 3.16s | 26.8s | 28 tps | 1.0M | $0.435 / $0.870 | |
| No data | — | 94.09% | 97.34% | 97.34% | 465ms | 37.4s | 57 tps | 1.0M | $1.00 / $3.00 | |
| No data | — | 75.18% | 87.80% | 87.80% | 3.59s | 6.99s | 26 tps | 1.1M | $0.304 / $0.609 | |
StreamLakestreamlake | No data | — | 81.98% | 83.25% | 83.25% | 3.54s | 5.83s | 30 tps | 1.0M | $0.522 / $1.04 |
- AtlasCloud100%Healthy24h 97.04%
- 7d
- 98.33%
- 30d
- 98.33%
- p50
- 4.38s
- p99
- 15.2s
- Throughput
- 28 tps
- Context
- 1.0M
- $/Mtok
- $0.435 / $0.870
atlas-cloud/fp8fp8 - DigitalOcean100%Healthy24h 99.21%
- 7d
- 98.33%
- 30d
- 98.33%
- p50
- 1.11s
- p99
- 7.82s
- Throughput
- 25 tps
- Context
- 262K
- $/Mtok
- $0.400 / $1.50
digitalocean - Novita100%Healthy24h 96.32%
- 7d
- 98.74%
- 30d
- 98.74%
- p50
- 3.34s
- p99
- 42.2s
- Throughput
- 24 tps
- Context
- 1.0M
- $/Mtok
- $0.480 / $0.960
novita - Xiaomi99.92%Healthy24h 98.24%
- 7d
- 98.88%
- 30d
- 98.88%
- p50
- 3.16s
- p99
- 26.8s
- Throughput
- 28 tps
- Context
- 1.0M
- $/Mtok
- $0.435 / $0.870
xiaomi/fp8fp8 - No data24h 94.09%
- 7d
- 97.34%
- 30d
- 97.34%
- p50
- 465ms
- p99
- 37.4s
- Throughput
- 57 tps
- Context
- 1.0M
- $/Mtok
- $1.00 / $3.00
deepinfra/fp8fp8 - No data24h 75.18%
- 7d
- 87.80%
- 30d
- 87.80%
- p50
- 3.59s
- p99
- 6.99s
- Throughput
- 26 tps
- Context
- 1.1M
- $/Mtok
- $0.304 / $0.609
gmicloud/bf16bf16 - No data24h 81.98%
- 7d
- 83.25%
- 30d
- 83.25%
- p50
- 3.54s
- p99
- 5.83s
- Throughput
- 30 tps
- Context
- 1.0M
- $/Mtok
- $0.522 / $1.04
streamlake
Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
3 endpoints reporting no data are omitted from the charts.
Availability
Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.
Time to first token
Logarithmic axis — the fleet spans two orders of magnitude. P50 is OpenRouter's rolling 30-minute window.
Throughput
Median tokens per second.