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% | 96.84% | 98.30% | 98.30% | 4.86s | 19.6s | 21 tps | 1.0M | $0.435 / $0.870 | |
DigitalOceandigitalocean | Healthy | 100% | 99.15% | 98.30% | 98.30% | 1.03s | 7.92s | 24 tps | 262K | $0.400 / $1.50 |
Novitanovita | Healthy | 100% | 96.37% | 98.72% | 98.72% | 4.85s | 73.6s | 17 tps | 1.0M | $0.480 / $0.960 |
| Healthy | 99.96% | 98.21% | 98.87% | 98.87% | 4.37s | 28.5s | 27 tps | 1.0M | $0.435 / $0.870 | |
| No data | — | 94.43% | 97.34% | 97.34% | 499ms | 39.0s | 79 tps | 1.0M | $1.00 / $3.00 | |
| Degraded | — | 74.75% | 87.69% | 87.69% | 4.25s | 6.98s | 24 tps | 1.1M | $0.304 / $0.609 | |
StreamLakestreamlake | No data | — | 81.71% | 83.25% | 83.25% | 3.19s | 5.31s | 26 tps | 1.0M | $0.522 / $1.04 |
- AtlasCloud100%Healthy24h 96.84%
- 7d
- 98.30%
- 30d
- 98.30%
- p50
- 4.86s
- p99
- 19.6s
- Throughput
- 21 tps
- Context
- 1.0M
- $/Mtok
- $0.435 / $0.870
atlas-cloud/fp8fp8 - DigitalOcean100%Healthy24h 99.15%
- 7d
- 98.30%
- 30d
- 98.30%
- p50
- 1.03s
- p99
- 7.92s
- Throughput
- 24 tps
- Context
- 262K
- $/Mtok
- $0.400 / $1.50
digitalocean - Novita100%Healthy24h 96.37%
- 7d
- 98.72%
- 30d
- 98.72%
- p50
- 4.85s
- p99
- 73.6s
- Throughput
- 17 tps
- Context
- 1.0M
- $/Mtok
- $0.480 / $0.960
novita - Xiaomi99.96%Healthy24h 98.21%
- 7d
- 98.87%
- 30d
- 98.87%
- p50
- 4.37s
- p99
- 28.5s
- Throughput
- 27 tps
- Context
- 1.0M
- $/Mtok
- $0.435 / $0.870
xiaomi/fp8fp8 - No data24h 94.43%
- 7d
- 97.34%
- 30d
- 97.34%
- p50
- 499ms
- p99
- 39.0s
- Throughput
- 79 tps
- Context
- 1.0M
- $/Mtok
- $1.00 / $3.00
deepinfra/fp8fp8 - Degraded24h 74.75%
- 7d
- 87.69%
- 30d
- 87.69%
- p50
- 4.25s
- p99
- 6.98s
- Throughput
- 24 tps
- Context
- 1.1M
- $/Mtok
- $0.304 / $0.609
gmicloud/bf16bf16 - No data24h 81.71%
- 7d
- 83.25%
- 30d
- 83.25%
- p50
- 3.19s
- p99
- 5.31s
- Throughput
- 26 tps
- Context
- 1.0M
- $/Mtok
- $0.522 / $1.04
streamlake
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
2 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.