MiMo-V2.6-Flash: 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) | 98.53% | 96.43% | 94.27% | 1.14s | 8.00s | 45 tps | 1.0M | $0.140 / $0.280 | |
| Healthy | 100%◆ (best) | 99.69% | 99.50%◆ (best) | 99.50%◆ (best) | 1.05s◆ (best) | 7.83s | 68 tps | 1.0M | $0.115 / $0.280 | |
| Healthy | 100%◆ (best) | 99.54% | 98.46% | 98.46% | 1.57s | 10.7s | 105 tps◆ (best) | 1.0M | $0.118 / $0.252 | |
| Healthy | 100%◆ (best) | 98.13% | 94.55% | 94.55% | 1.36s | 5.97s◆ (best) | 22 tps | 1.0M | $0.175 / $0.350 | |
| Healthy | 99.56% | 99.23% | 98.88% | 99.09% | 2.87s | 34.1s | 52 tps | 1.0M | $0.140 / $0.280 | |
| Healthy | 99.15% | 99.64% | 99.39% | 99.39% | 4.06s | 23.7s | 27 tps | 1.0M | $0.100 / $0.280 | |
| Healthy | 98.73% | 96.40% | 96.20% | 96.20% | 2.66s | 35.7s | 35 tps | 1.0M | $0.140 / $0.280 | |
| Degraded | 98.06% | 86.03% | 87.03% | 87.03% | 3.33s | 10.5s | 44 tps | 1.1M | $0.140 / $0.280 | |
| No data | — | — | 98.66% | 98.66% | — | — | — | 1.0M | $0.120 / $0.280 | |
| No data | — | — | 97.88% | 97.88% | — | — | — | 1.0M | $0.040 / $1.28◆ (best) |
- DeepInfra100%◆ (best)Healthy24h 98.53%
- 7d
- 96.43%
- 30d
- 94.27%
- p50
- 1.14s
- p99
- 8.00s
- Throughput
- 45 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
deepinfra/fp8fp8 - InferenceNet100%◆ (best)Healthy24h 99.69%
- 7d
- 99.50%◆ (best)
- 30d
- 99.50%◆ (best)
- p50
- 1.05s◆ (best)
- p99
- 7.83s
- Throughput
- 68 tps
- Context
- 1.0M
- $/Mtok
- $0.115 / $0.280
inference-net/fp8fp8 - Io Net100%◆ (best)Healthy24h 99.54%
- 7d
- 98.46%
- 30d
- 98.46%
- p50
- 1.57s
- p99
- 10.7s
- Throughput
- 105 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.118 / $0.252
io-net/fp8fp8 - Venice100%◆ (best)Healthy24h 98.13%
- 7d
- 94.55%
- 30d
- 94.55%
- p50
- 1.36s
- p99
- 5.97s◆ (best)
- Throughput
- 22 tps
- Context
- 1.0M
- $/Mtok
- $0.175 / $0.350
venice/fp8fp8 - Xiaomi99.56%Healthy24h 99.23%
- 7d
- 98.88%
- 30d
- 99.09%
- p50
- 2.87s
- p99
- 34.1s
- Throughput
- 52 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
xiaomi/fp8fp8 - Darkbloom99.15%Healthy24h 99.64%
- 7d
- 99.39%
- 30d
- 99.39%
- p50
- 4.06s
- p99
- 23.7s
- Throughput
- 27 tps
- Context
- 1.0M
- $/Mtok
- $0.100 / $0.280
darkbloom/fp4fp4 - Novita98.73%Healthy24h 96.40%
- 7d
- 96.20%
- 30d
- 96.20%
- p50
- 2.66s
- p99
- 35.7s
- Throughput
- 35 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
novita/fp8fp8 - GMICloud98.06%Degraded24h 86.03%
- 7d
- 87.03%
- 30d
- 87.03%
- p50
- 3.33s
- p99
- 10.5s
- Throughput
- 44 tps
- Context
- 1.1M
- $/Mtok
- $0.140 / $0.280
gmicloud/bf16bf16 - No data24h —
- 7d
- 98.66%
- 30d
- 98.66%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.120 / $0.280
inference-net/mxfp4mxfp4 - No data24h —
- 7d
- 97.88%
- 30d
- 97.88%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $0.040 / $1.28◆ (best)
relace/mxfp4mxfp4
Measured 1m 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.