MiMo-V2.5
xiaomi/mimo-v2.5
Compare with MiMo-V2.5-Pro, GLM 5.2, DeepSeek V4 Flash 0731
CompareMiMo-V2.5
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Parasailparasail/fp8fp8 | Healthy | 100% | 98.16% | 755ms | 13.1s | 44 tps | 1.0M | $0.140 / $0.280 |
Novitanovita/fp8fp8 | Healthy | 99.56% | 98.00% | 1.51s | 18.0s | 60 tps | 1.0M | $0.168 / $0.336 |
Xiaomixiaomi/fp8fp8 | Degraded | 98.09% | 97.41% | 3.25s | 28.9s | 33 tps | 1.0M | $0.140 / $0.280 |
DeepInfradeepinfra/bf16bf16 | Healthy | 97.75% | 98.04% | 668ms | 9.95s | 18 tps | 262K | $0.400 / $2.00 |
GMICloudgmicloud/fp8fp8 | Healthy | 96.18% | 91.57% | 2.69s | 11.5s | 44 tps | 1.1M | $0.119 / $0.238 |
- Parasail100%Healthy24h 98.16%
- p50
- 755ms
- p99
- 13.1s
- Throughput
- 44 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
parasail/fp8fp8 - Novita99.56%Healthy24h 98.00%
- p50
- 1.51s
- p99
- 18.0s
- Throughput
- 60 tps
- Context
- 1.0M
- $/Mtok
- $0.168 / $0.336
novita/fp8fp8 - Xiaomi98.09%Degraded24h 97.41%
- p50
- 3.25s
- p99
- 28.9s
- Throughput
- 33 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
xiaomi/fp8fp8 - DeepInfra97.75%Healthy24h 98.04%
- p50
- 668ms
- p99
- 9.95s
- Throughput
- 18 tps
- Context
- 262K
- $/Mtok
- $0.400 / $2.00
deepinfra/bf16bf16 - GMICloud96.18%Healthy24h 91.57%
- p50
- 2.69s
- p99
- 11.5s
- Throughput
- 44 tps
- Context
- 1.1M
- $/Mtok
- $0.119 / $0.238
gmicloud/fp8fp8
Measured 5m 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 and p99 are OpenRouter's rolling 30-minute windows.
Throughput
Median tokens per second.