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% | 98.36% | 98.36% | 2.71s | 13.9s | 30 tps | 1.0M | $0.435 / $0.870 | |
Novitanovita | Healthy | 100% | 96.31% | 98.77% | 98.77% | 2.59s | 13.0s | 30 tps | 1.0M | $0.480 / $0.960 |
| Healthy | 99.90% | 98.25% | 98.90% | 98.90% | 2.67s | 22.1s | 35 tps | 1.0M | $0.435 / $0.870 | |
| Healthy | 98.89% | 94.13% | 97.38% | 97.38% | 590ms | 8.68s | 58 tps | 1.0M | $1.00 / $3.00 | |
| Healthy | 98.80% | 75.13% | 88.00% | 88.00% | 3.31s | 6.42s | 20 tps | 1.1M | $0.304 / $0.609 | |
StreamLakestreamlake | Degraded | 94.26% | 82.37% | 83.31% | 83.31% | 2.44s | 5.97s | 31 tps | 1.0M | $0.522 / $1.04 |
DigitalOceandigitalocean | Down | — | 98.88% | 98.36% | 98.36% | 1.10s | 4.87s | 33 tps | 262K | $0.400 / $1.50 |
- AtlasCloud100%Healthy24h 97.04%
- 7d
- 98.36%
- 30d
- 98.36%
- p50
- 2.71s
- p99
- 13.9s
- Throughput
- 30 tps
- Context
- 1.0M
- $/Mtok
- $0.435 / $0.870
atlas-cloud/fp8fp8 - Novita100%Healthy24h 96.31%
- 7d
- 98.77%
- 30d
- 98.77%
- p50
- 2.59s
- p99
- 13.0s
- Throughput
- 30 tps
- Context
- 1.0M
- $/Mtok
- $0.480 / $0.960
novita - Xiaomi99.90%Healthy24h 98.25%
- 7d
- 98.90%
- 30d
- 98.90%
- p50
- 2.67s
- p99
- 22.1s
- Throughput
- 35 tps
- Context
- 1.0M
- $/Mtok
- $0.435 / $0.870
xiaomi/fp8fp8 - DeepInfra98.89%Healthy24h 94.13%
- 7d
- 97.38%
- 30d
- 97.38%
- p50
- 590ms
- p99
- 8.68s
- Throughput
- 58 tps
- Context
- 1.0M
- $/Mtok
- $1.00 / $3.00
deepinfra/fp8fp8 - GMICloud98.80%Healthy24h 75.13%
- 7d
- 88.00%
- 30d
- 88.00%
- p50
- 3.31s
- p99
- 6.42s
- Throughput
- 20 tps
- Context
- 1.1M
- $/Mtok
- $0.304 / $0.609
gmicloud/bf16bf16 - StreamLake94.26%Degraded24h 82.37%
- 7d
- 83.31%
- 30d
- 83.31%
- p50
- 2.44s
- p99
- 5.97s
- Throughput
- 31 tps
- Context
- 1.0M
- $/Mtok
- $0.522 / $1.04
streamlake - Down24h 98.88%
- 7d
- 98.36%
- 30d
- 98.36%
- p50
- 1.10s
- p99
- 4.87s
- Throughput
- 33 tps
- Context
- 262K
- $/Mtok
- $0.400 / $1.50
digitalocean
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
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.