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 | 99.77%◆ (best) | 99.89% | 99.82%◆ (best) | 98.29% | 1.91s◆ (best) | 23.2s◆ (best) | 31 tps◆ (best) | 1.0M | $0.430 / $0.870◆ (best) | |
| Healthy | 99.64% | 99.24% | 99.00% | 99.00% | 6.87s | 44.6s | 31 tps◆ (best) | 1.1M | $0.435 / $0.870 | |
| Healthy | 99.45% | 99.80% | 99.46% | 99.60%◆ (best) | 4.05s | 34.9s | 30 tps | 1.0M | $0.435 / $0.870 | |
| Healthy | 98.44% | 99.60% | 99.60% | 99.60% | 5.18s | 51.2s | 30 tps | 1.0M | $0.435 / $0.870 |
- DeepInfra99.77%◆ (best)Healthy24h 99.89%
- 7d
- 99.82%◆ (best)
- 30d
- 98.29%
- p50
- 1.91s◆ (best)
- p99
- 23.2s◆ (best)
- Throughput
- 31 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.430 / $0.870◆ (best)
deepinfra/fp8fp8 - GMICloud99.64%Healthy24h 99.24%
- 7d
- 99.00%
- 30d
- 99.00%
- p50
- 6.87s
- p99
- 44.6s
- Throughput
- 31 tps◆ (best)
- Context
- 1.1M
- $/Mtok
- $0.435 / $0.870
gmicloud/bf16bf16 - Xiaomi99.45%Healthy24h 99.80%
- 7d
- 99.46%
- 30d
- 99.60%◆ (best)
- p50
- 4.05s
- p99
- 34.9s
- Throughput
- 30 tps
- Context
- 1.0M
- $/Mtok
- $0.435 / $0.870
xiaomi/fp8fp8 - Novita98.44%Healthy24h 99.60%
- 7d
- 99.60%
- 30d
- 99.60%
- p50
- 5.18s
- p99
- 51.2s
- Throughput
- 30 tps
- Context
- 1.0M
- $/Mtok
- $0.435 / $0.870
novita/fp8fp8
Measured 4m 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.