Qwen3.5-35B-A3B: 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| No data | — | — | — | — | — | — | — | 262K | $0.140 / $1.00 | |
Alibabaalibaba | No data | — | — | 95.84% | 96.12% | — | — | — | 262K | $0.163 / $1.30 |
| No data | — | — | 99.12% | 98.53% | — | — | — | 262K | $0.225 / $1.80 | |
| No data | — | — | — | — | — | — | — | 262K | $0.250 / $1.25 | |
| No data | — | — | 99.81% | 99.65% | — | — | — | 262K | $0.080 / $0.750◆ (best) | |
| No data | — | — | 99.76% | 98.83% | — | — | — | 262K | $0.140 / $1.00 | |
| No data | — | — | 99.88% | 99.82% | — | — | — | 262K | $0.150 / $1.00 | |
| No data | — | — | 94.91% | 94.56% | — | — | — | 262K | $0.240 / $1.80 | |
Venicevenice | No data | — | — | 99.92%◆ (best) | 99.93%◆ (best) | — | — | — | 256K | $0.313 / $1.25 |
- No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.140 / $1.00
akashml/fp8fp8 - No data24h —
- 7d
- 95.84%
- 30d
- 96.12%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.163 / $1.30
alibaba - No data24h —
- 7d
- 99.12%
- 30d
- 98.53%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.225 / $1.80
atlas-cloud/fp8fp8 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.250 / $1.25
coreweave/fp8fp8 - No data24h —
- 7d
- 99.81%
- 30d
- 99.65%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.080 / $0.750◆ (best)
darkbloom/fp4fp4 - No data24h —
- 7d
- 99.76%
- 30d
- 98.83%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.140 / $1.00
deepinfra/fp8fp8 - No data24h —
- 7d
- 99.88%
- 30d
- 99.82%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.150 / $1.00
parasail/fp8fp8 - No data24h —
- 7d
- 94.91%
- 30d
- 94.56%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.240 / $1.80
siliconflow/fp8fp8 - No data24h —
- 7d
- 99.92%◆ (best)
- 30d
- 99.93%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 256K
- $/Mtok
- $0.313 / $1.25
venice
No recent measurement. ◆ marks the best value in each column among these endpoints.
Price vs latency
No endpoint currently reports both a price and a latency.
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.