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) | 99.65% | 99.39% | 99.39% | 3.53s | 14.2s | 28 tps | 1.0M | $0.100 / $0.280 | |
| Healthy | 100%◆ (best) | 98.44% | 96.41% | 94.25% | 832ms◆ (best) | 9.37s | 60 tps | 1.0M | $0.140 / $0.280 | |
| Healthy | 100%◆ (best) | 99.68% | 99.49%◆ (best) | 99.49%◆ (best) | 1.19s | 10.1s | 57 tps | 1.0M | $0.115 / $0.280 | |
| Healthy | 100%◆ (best) | 98.04% | 94.51% | 94.51% | 976ms | 5.15s◆ (best) | 30 tps | 1.0M | $0.175 / $0.350 | |
| Healthy | 99.92% | 99.51% | 98.44% | 98.44% | 1.37s | 6.24s | 102 tps◆ (best) | 1.0M | $0.118 / $0.252 | |
| Healthy | 99.77% | 99.24% | 98.88% | 99.09% | 2.78s | 29.4s | 48 tps | 1.0M | $0.140 / $0.280 | |
| Healthy | 98.99% | 96.67% | 96.20% | 96.20% | 2.30s | 59.6s | 32 tps | 1.0M | $0.140 / $0.280 | |
| Healthy | 97.33% | 85.87% | 86.95% | 86.95% | 3.33s | 8.08s | 47 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) |
- Darkbloom100%◆ (best)Healthy24h 99.65%
- 7d
- 99.39%
- 30d
- 99.39%
- p50
- 3.53s
- p99
- 14.2s
- Throughput
- 28 tps
- Context
- 1.0M
- $/Mtok
- $0.100 / $0.280
darkbloom/fp4fp4 - DeepInfra100%◆ (best)Healthy24h 98.44%
- 7d
- 96.41%
- 30d
- 94.25%
- p50
- 832ms◆ (best)
- p99
- 9.37s
- Throughput
- 60 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
deepinfra/fp8fp8 - InferenceNet100%◆ (best)Healthy24h 99.68%
- 7d
- 99.49%◆ (best)
- 30d
- 99.49%◆ (best)
- p50
- 1.19s
- p99
- 10.1s
- Throughput
- 57 tps
- Context
- 1.0M
- $/Mtok
- $0.115 / $0.280
inference-net/fp8fp8 - Venice100%◆ (best)Healthy24h 98.04%
- 7d
- 94.51%
- 30d
- 94.51%
- p50
- 976ms
- p99
- 5.15s◆ (best)
- Throughput
- 30 tps
- Context
- 1.0M
- $/Mtok
- $0.175 / $0.350
venice/fp8fp8 - Io Net99.92%Healthy24h 99.51%
- 7d
- 98.44%
- 30d
- 98.44%
- p50
- 1.37s
- p99
- 6.24s
- Throughput
- 102 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.118 / $0.252
io-net/fp8fp8 - Xiaomi99.77%Healthy24h 99.24%
- 7d
- 98.88%
- 30d
- 99.09%
- p50
- 2.78s
- p99
- 29.4s
- Throughput
- 48 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
xiaomi/fp8fp8 - Novita98.99%Healthy24h 96.67%
- 7d
- 96.20%
- 30d
- 96.20%
- p50
- 2.30s
- p99
- 59.6s
- Throughput
- 32 tps
- Context
- 1.0M
- $/Mtok
- $0.140 / $0.280
novita/fp8fp8 - GMICloud97.33%Healthy24h 85.87%
- 7d
- 86.95%
- 30d
- 86.95%
- p50
- 3.33s
- p99
- 8.08s
- Throughput
- 47 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 3m 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.