Qwen3.6 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100%◆ (best) | 99.39% | 99.69% | 99.69% | 581ms | 3.64s◆ (best) | 84 tps | 262K | $0.140 / $1.00 | |
| Healthy | 100%◆ (best) | 98.86% | 99.30% | 99.30% | 899ms | 9.98s | 104 tps | 262K | $0.186 / $1.11 | |
| Healthy | 100%◆ (best) | 99.33% | 99.65% | 99.65% | 542ms◆ (best) | 5.81s | 141 tps◆ (best) | 262K | $0.250 / $1.25 | |
| Degraded | 100%◆ (best) | 97.74% | 93.85% | 93.85% | 755ms | 22.5s | 52 tps | 262K | $0.100 / $0.950 | |
| Healthy | 100%◆ (best) | 99.42% | 99.38% | 99.38% | 555ms | 9.72s | 122 tps | 262K | $0.190 / $1.19 | |
| Healthy | 100%◆ (best) | 98.78% | 99.20% | 99.20% | 547ms | 4.90s | 52 tps | 262K | $0.150 / $1.00 | |
| Healthy | 100%◆ (best) | 97.05% | 98.01% | 98.01% | 1.88s | 21.4s | 38 tps | 262K | $0.200 / $1.60 | |
| Healthy | 100%◆ (best) | 99.68% | 99.85%◆ (best) | 99.85%◆ (best) | 664ms | 4.98s | 105 tps | 256K | $0.100 / $1.00 | |
Phalaphala | Degraded | 95.31% | 96.51% | 98.16% | 98.16% | 1.51s | 9.09s | 106 tps | 262K | $0.200 / $1.27 |
| Degraded | 91.38% | 86.87% | 87.93% | 87.93% | 4.86s | 23.3s | 40 tps | 262K | $0.080 / $0.750◆ (best) | |
Darkbloomdarkbloom | No data | — | — | 69.81% | 69.81% | — | — | — | 262K | $0.080 / $0.750◆ (best) |
- AkashML100%◆ (best)Healthy24h 99.39%
- 7d
- 99.69%
- 30d
- 99.69%
- p50
- 581ms
- p99
- 3.64s◆ (best)
- Throughput
- 84 tps
- Context
- 262K
- $/Mtok
- $0.140 / $1.00
akashml/fp8fp8 - AtlasCloud100%◆ (best)Healthy24h 98.86%
- 7d
- 99.30%
- 30d
- 99.30%
- p50
- 899ms
- p99
- 9.98s
- Throughput
- 104 tps
- Context
- 262K
- $/Mtok
- $0.186 / $1.11
atlas-cloud/fp8fp8 - CoreWeave100%◆ (best)Healthy24h 99.33%
- 7d
- 99.65%
- 30d
- 99.65%
- p50
- 542ms◆ (best)
- p99
- 5.81s
- Throughput
- 141 tps◆ (best)
- Context
- 262K
- $/Mtok
- $0.250 / $1.25
coreweave/fp8fp8 - DeepInfra100%◆ (best)Degraded24h 97.74%
- 7d
- 93.85%
- 30d
- 93.85%
- p50
- 755ms
- p99
- 22.5s
- Throughput
- 52 tps
- Context
- 262K
- $/Mtok
- $0.100 / $0.950
deepinfra/fp8fp8 - Io Net100%◆ (best)Healthy24h 99.42%
- 7d
- 99.38%
- 30d
- 99.38%
- p50
- 555ms
- p99
- 9.72s
- Throughput
- 122 tps
- Context
- 262K
- $/Mtok
- $0.190 / $1.19
io-net/fp8fp8 - Parasail100%◆ (best)Healthy24h 98.78%
- 7d
- 99.20%
- 30d
- 99.20%
- p50
- 547ms
- p99
- 4.90s
- Throughput
- 52 tps
- Context
- 262K
- $/Mtok
- $0.150 / $1.00
parasail/fp8fp8 - SiliconFlow100%◆ (best)Healthy24h 97.05%
- 7d
- 98.01%
- 30d
- 98.01%
- p50
- 1.88s
- p99
- 21.4s
- Throughput
- 38 tps
- Context
- 262K
- $/Mtok
- $0.200 / $1.60
siliconflow/fp8fp8 - Venice100%◆ (best)Healthy24h 99.68%
- 7d
- 99.85%◆ (best)
- 30d
- 99.85%◆ (best)
- p50
- 664ms
- p99
- 4.98s
- Throughput
- 105 tps
- Context
- 256K
- $/Mtok
- $0.100 / $1.00
venice/fp8fp8 - Phala95.31%Degraded24h 96.51%
- 7d
- 98.16%
- 30d
- 98.16%
- p50
- 1.51s
- p99
- 9.09s
- Throughput
- 106 tps
- Context
- 262K
- $/Mtok
- $0.200 / $1.27
phala - Darkbloom91.38%Degraded24h 86.87%
- 7d
- 87.93%
- 30d
- 87.93%
- p50
- 4.86s
- p99
- 23.3s
- Throughput
- 40 tps
- Context
- 262K
- $/Mtok
- $0.080 / $0.750◆ (best)
darkbloom/fp4fp4 - No data24h —
- 7d
- 69.81%
- 30d
- 69.81%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $0.080 / $0.750◆ (best)
darkbloom
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, averaged over the hour.
Throughput
Median tokens per second.