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% | 97.32% | 417ms | 9.76s | 67 tps | 1.0M | $1.00 / $3.00 |
DigitalOceandigitalocean | Healthy | 100% | 98.94% | 947ms | 4.86s | 33 tps | 262K | $0.400 / $1.50 |
GMICloudgmicloud/bf16bf16 | Healthy | 100% | 93.68% | 3.35s | 6.98s | 22 tps | 1.1M | $0.304 / $0.609 |
Novitanovita | Healthy | 100% | 99.40% | 3.13s | 25.2s | 29 tps | 1.0M | $0.480 / $0.960 |
Xiaomixiaomi/fp8fp8 | Healthy | 99.92% | 99.60% | 2.71s | 23.9s | 37 tps | 1.0M | $0.435 / $0.870 |
AtlasCloudatlas-cloud/fp8fp8 | Healthy | 98.15% | 98.37% | 2.56s | 30.2s | 31 tps | 1.0M | $0.435 / $0.870 |
StreamLakestreamlake | No data | — | 93.78% | 2.18s | 5.09s | 38 tps | 1.0M | $0.522 / $1.04 |
- DeepInfra100%Healthy24h 97.32%
- p50
- 417ms
- p99
- 9.76s
- Throughput
- 67 tps
- Context
- 1.0M
- $/Mtok
- $1.00 / $3.00
deepinfra/fp8fp8 - DigitalOcean100%Healthy24h 98.94%
- p50
- 947ms
- p99
- 4.86s
- Throughput
- 33 tps
- Context
- 262K
- $/Mtok
- $0.400 / $1.50
digitalocean - GMICloud100%Healthy24h 93.68%
- p50
- 3.35s
- p99
- 6.98s
- Throughput
- 22 tps
- Context
- 1.1M
- $/Mtok
- $0.304 / $0.609
gmicloud/bf16bf16 - Novita100%Healthy24h 99.40%
- p50
- 3.13s
- p99
- 25.2s
- Throughput
- 29 tps
- Context
- 1.0M
- $/Mtok
- $0.480 / $0.960
novita - Xiaomi99.92%Healthy24h 99.60%
- p50
- 2.71s
- p99
- 23.9s
- Throughput
- 37 tps
- Context
- 1.0M
- $/Mtok
- $0.435 / $0.870
xiaomi/fp8fp8 - AtlasCloud98.15%Healthy24h 98.37%
- p50
- 2.56s
- p99
- 30.2s
- Throughput
- 31 tps
- Context
- 1.0M
- $/Mtok
- $0.435 / $0.870
atlas-cloud/fp8fp8 - StreamLake—No data24h 93.78%
- p50
- 2.18s
- p99
- 5.09s
- Throughput
- 38 tps
- Context
- 1.0M
- $/Mtok
- $0.522 / $1.04
streamlake
Measured 4m 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, averaged over the hour.
Throughput
Median tokens per second.