Qwen3.8 2.4T A95B
qwen/qwen3.8-2.4t-a95b
Compare with Qwen3.8 27B, Qwen-Plus, Qwen3.8 Max
CompareQwen3.8 2.4T A95B
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
DigitalOceandigitalocean | Healthy | 100% | 93.64% | 98.64% | 98.64% | 3.73s | 10.5s | 10 tps | 262K | $2.00 / $6.00 |
| Healthy | 100% | 99.92% | 99.78% | 99.78% | 1.27s | 17.0s | 45 tps | 1.0M | $2.00 / $6.00 | |
Togethertogether | Healthy | 100% | 99.92% | 99.77% | 99.77% | 502ms | 1.07s | 83 tps | 1.0M | $2.50 / $6.25 |
Alibabaalibaba | No data | — | 99.93% | 100% | 100% | 1.35s | 1.65s | 38 tps | 1.0M | $2.00 / $6.00 |
| Down | — | 94.88% | 96.56% | 96.56% | 1.74s | 11.3s | 7.0 tps | 262K | $2.00 / $6.00 | |
| No data | — | 98.99% | 99.05% | 99.05% | 1.68s | 34.2s | 98 tps | 1.0M | $2.00 / $6.00 | |
Venicevenice | No data | — | 99.23% | 98.46% | 98.46% | 884ms | 1.75s | 97 tps | 262K | $2.50 / $7.50 |
- DigitalOcean100%Healthy24h 93.64%
- 7d
- 98.64%
- 30d
- 98.64%
- p50
- 3.73s
- p99
- 10.5s
- Throughput
- 10 tps
- Context
- 262K
- $/Mtok
- $2.00 / $6.00
digitalocean - SiliconFlow100%Healthy24h 99.92%
- 7d
- 99.78%
- 30d
- 99.78%
- p50
- 1.27s
- p99
- 17.0s
- Throughput
- 45 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $6.00
siliconflow/fp8fp8 - Together100%Healthy24h 99.92%
- 7d
- 99.77%
- 30d
- 99.77%
- p50
- 502ms
- p99
- 1.07s
- Throughput
- 83 tps
- Context
- 1.0M
- $/Mtok
- $2.50 / $6.25
together - No data24h 99.93%
- 7d
- 100%
- 30d
- 100%
- p50
- 1.35s
- p99
- 1.65s
- Throughput
- 38 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $6.00
alibaba - Down24h 94.88%
- 7d
- 96.56%
- 30d
- 96.56%
- p50
- 1.74s
- p99
- 11.3s
- Throughput
- 7.0 tps
- Context
- 262K
- $/Mtok
- $2.00 / $6.00
deepinfra/fp4fp4 - No data24h 98.99%
- 7d
- 99.05%
- 30d
- 99.05%
- p50
- 1.68s
- p99
- 34.2s
- Throughput
- 98 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $6.00
modal/nvfp4nvfp4 - No data24h 99.23%
- 7d
- 98.46%
- 30d
- 98.46%
- p50
- 884ms
- p99
- 1.75s
- Throughput
- 97 tps
- Context
- 262K
- $/Mtok
- $2.50 / $7.50
venice
Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
3 endpoints reporting no data are omitted from the charts.
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.