Qwen3.5-122B-A10B: 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100%◆ (best) | 98.92% | 97.47% | 96.16% | 662ms◆ (best) | 10.7s | 91 tps | 262K | $0.260 / $2.08◆ (best) |
| Healthy | 96.47% | 99.66% | 99.17% | 99.59% | 888ms | 23.2s | 115 tps◆ (best) | 262K | $0.400 / $3.20 | |
| Healthy | 96.43% | 98.51% | 94.92% | 93.46% | 1.31s | 4.88s◆ (best) | 46 tps | 262K | $0.260 / $2.08◆ (best) | |
| No data | — | 99.04% | 98.17% | 98.01% | 1.46s | 12.4s | 49 tps | 262K | $0.300 / $2.40 | |
| No data | — | — | 99.92%◆ (best) | 99.74%◆ (best) | — | — | — | 262K | $0.290 / $2.40 |
- Alibaba100%◆ (best)Healthy24h 98.92%
- 7d
- 97.47%
- 30d
- 96.16%
- p50
- 662ms◆ (best)
- p99
- 10.7s
- Throughput
- 91 tps
- Context
- 262K
- $/Mtok
- $0.260 / $2.08◆ (best)
alibaba - Novita96.47%Healthy24h 99.66%
- 7d
- 99.17%
- 30d
- 99.59%
- p50
- 888ms
- p99
- 23.2s
- Throughput
- 115 tps◆ (best)
- Context
- 262K
- $/Mtok
- $0.400 / $3.20
novita/bf16bf16 - SiliconFlow96.43%Healthy24h 98.51%
- 7d
- 94.92%
- 30d
- 93.46%
- p50
- 1.31s
- p99
- 4.88s◆ (best)
- Throughput
- 46 tps
- Context
- 262K
- $/Mtok
- $0.260 / $2.08◆ (best)
siliconflow/fp8fp8 - No data24h 99.04%
- 7d
- 98.17%
- 30d
- 98.01%
- p50
- 1.46s
- p99
- 12.4s
- Throughput
- 49 tps
- Context
- 262K
- $/Mtok
- $0.300 / $2.40
atlas-cloud/fp8fp8 - No data24h —
- 7d
- 99.92%◆ (best)
- 30d
- 99.74%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.290 / $2.40
deepinfra/fp4fp4
Measured 5m 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.