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 | 99.90%◆ (best) | 99.89% | 99.81%◆ (best) | 98.28% | 1.54s◆ (best) | 15.5s◆ (best) | 30 tps | 1.0M | $0.430 / $0.870◆ (best) | |
| Healthy | 99.89% | 99.81% | 99.46% | 99.60%◆ (best) | 3.48s | 32.4s | 30 tps | 1.0M | $0.435 / $0.870 | |
| Healthy | 99.77% | 99.61% | 99.59% | 99.59% | 4.41s | 48.4s | 32 tps◆ (best) | 1.0M | $0.435 / $0.870 | |
| Healthy | 99.51% | 99.27% | 99.00% | 99.00% | 6.50s | 42.3s | 29 tps | 1.1M | $0.435 / $0.870 |
- DeepInfra99.90%◆ (best)Healthy24h 99.89%
- 7d
- 99.81%◆ (best)
- 30d
- 98.28%
- p50
- 1.54s◆ (best)
- p99
- 15.5s◆ (best)
- Throughput
- 30 tps
- Context
- 1.0M
- $/Mtok
- $0.430 / $0.870◆ (best)
deepinfra/fp8fp8 - Xiaomi99.89%Healthy24h 99.81%
- 7d
- 99.46%
- 30d
- 99.60%◆ (best)
- p50
- 3.48s
- p99
- 32.4s
- Throughput
- 30 tps
- Context
- 1.0M
- $/Mtok
- $0.435 / $0.870
xiaomi/fp8fp8 - Novita99.77%Healthy24h 99.61%
- 7d
- 99.59%
- 30d
- 99.59%
- p50
- 4.41s
- p99
- 48.4s
- Throughput
- 32 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.435 / $0.870
novita/fp8fp8 - GMICloud99.51%Healthy24h 99.27%
- 7d
- 99.00%
- 30d
- 99.00%
- p50
- 6.50s
- p99
- 42.3s
- Throughput
- 29 tps
- Context
- 1.1M
- $/Mtok
- $0.435 / $0.870
gmicloud/bf16bf16
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.
Throughput
Median tokens per second.