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
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
DeepInfradeepinfra/fp8fp8 | Healthy | 100% | 97.23% | 318ms | 11.4s | 64 tps | 1.0M | $1.00 / $3.00 |
DigitalOceandigitalocean | Healthy | 100% | 98.71% | 737ms | 5.30s | 49 tps | 262K | $0.400 / $1.50 |
Novitanovita | Healthy | 100% | 99.40% | 3.41s | 9.78s | 25 tps | 1.0M | $0.480 / $0.960 |
Xiaomixiaomi/fp8fp8 | Healthy | 99.97% | 99.60% | 2.90s | 14.1s | 34 tps | 1.0M | $0.435 / $0.870 |
AtlasCloudatlas-cloud/fp8fp8 | Degraded | 99.40% | 98.52% | 2.14s | 55.5s | 26 tps | 1.0M | $0.435 / $0.870 |
GMICloudgmicloud/bf16bf16 | Healthy | 96.30% | 93.86% | 3.49s | 6.96s | 15 tps | 1.1M | $0.304 / $0.609 |
StreamLakestreamlake | No data | — | 94.06% | 2.25s | 5.50s | 7.0 tps | 1.0M | $0.522 / $1.04 |
- DeepInfra100%Healthy24h 97.23%
- p50
- 318ms
- p99
- 11.4s
- Throughput
- 64 tps
- Context
- 1.0M
- $/Mtok
- $1.00 / $3.00
deepinfra/fp8fp8 - DigitalOcean100%Healthy24h 98.71%
- p50
- 737ms
- p99
- 5.30s
- Throughput
- 49 tps
- Context
- 262K
- $/Mtok
- $0.400 / $1.50
digitalocean - Novita100%Healthy24h 99.40%
- p50
- 3.41s
- p99
- 9.78s
- Throughput
- 25 tps
- Context
- 1.0M
- $/Mtok
- $0.480 / $0.960
novita - Xiaomi99.97%Healthy24h 99.60%
- p50
- 2.90s
- p99
- 14.1s
- Throughput
- 34 tps
- Context
- 1.0M
- $/Mtok
- $0.435 / $0.870
xiaomi/fp8fp8 - AtlasCloud99.40%Degraded24h 98.52%
- p50
- 2.14s
- p99
- 55.5s
- Throughput
- 26 tps
- Context
- 1.0M
- $/Mtok
- $0.435 / $0.870
atlas-cloud/fp8fp8 - GMICloud96.30%Healthy24h 93.86%
- p50
- 3.49s
- p99
- 6.96s
- Throughput
- 15 tps
- Context
- 1.1M
- $/Mtok
- $0.304 / $0.609
gmicloud/bf16bf16 - StreamLake—No data24h 94.06%
- p50
- 2.25s
- p99
- 5.50s
- Throughput
- 7.0 tps
- Context
- 1.0M
- $/Mtok
- $0.522 / $1.04
streamlake
Measured 57s ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
1 endpoint reporting no data is 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 and p99 are OpenRouter's rolling 30-minute windows.
Throughput
Median tokens per second.