MiMo-V2.6-Pro: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100%◆ (best) | 99.88% | 99.82%◆ (best) | 98.29% | 1.78s◆ (best) | 26.1s◆ (best) | 39 tps◆ (best) | 1.0M | $0.430 / $0.870◆ (best) | |
| Healthy | 96.33% | 99.79% | 99.46% | 99.60%◆ (best) | 3.90s | 33.3s | 32 tps | 1.0M | $0.435 / $0.870 | |
| Degraded | 93.64% | 99.58% | 99.58% | 99.58% | 4.61s | 56.8s | 32 tps | 1.0M | $0.435 / $0.870 | |
| Degraded | 90.11% | 99.23% | 99.00% | 98.99% | 5.95s | 41.0s | 32 tps | 1.1M | $0.435 / $0.870 |
- DeepInfra100%◆ (best)Healthy24h 99.88%
- 7d
- 99.82%◆ (best)
- 30d
- 98.29%
- p50
- 1.78s◆ (best)
- p99
- 26.1s◆ (best)
- Throughput
- 39 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.430 / $0.870◆ (best)
deepinfra/fp8fp8 - Xiaomi96.33%Healthy24h 99.79%
- 7d
- 99.46%
- 30d
- 99.60%◆ (best)
- p50
- 3.90s
- p99
- 33.3s
- Throughput
- 32 tps
- Context
- 1.0M
- $/Mtok
- $0.435 / $0.870
xiaomi/fp8fp8 - Novita93.64%Degraded24h 99.58%
- 7d
- 99.58%
- 30d
- 99.58%
- p50
- 4.61s
- p99
- 56.8s
- Throughput
- 32 tps
- Context
- 1.0M
- $/Mtok
- $0.435 / $0.870
novita/fp8fp8 - GMICloud90.11%Degraded24h 99.23%
- 7d
- 99.00%
- 30d
- 98.99%
- p50
- 5.95s
- p99
- 41.0s
- Throughput
- 32 tps
- Context
- 1.1M
- $/Mtok
- $0.435 / $0.870
gmicloud/bf16bf16
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.
Price vs latency
One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag
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, averaged over the hour.
Throughput
Median tokens per second.