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
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
DeepInfradeepinfra/fp4fp4 | Healthy | 100% | 95.76% | 1.60s | 6.23s | 37 tps | 262K | $2.00 / $6.00 |
Modalmodal/nvfp4nvfp4 | Healthy | 100% | 99.54% | 1.06s | 5.66s | 78 tps | 1.0M | $2.00 / $6.00 |
Alibabaalibaba | No data | — | 99.94% | 1.27s | 3.54s | 38 tps | 1.0M | $2.00 / $6.00 |
DigitalOceandigitalocean | Down | — | 97.77% | — | — | — | 262K | $2.00 / $6.00 |
SiliconFlowsiliconflow/fp8fp8 | No data | — | 99.47% | 1.28s | 6.26s | 38 tps | 1.0M | $2.00 / $6.00 |
Togethertogether | No data | — | 99.87% | 5.18s | 7.26s | 77 tps | 1.0M | $2.50 / $6.25 |
Venicevenice | No data | — | 98.39% | 1.14s | 8.87s | 94 tps | 262K | $2.50 / $7.50 |
- DeepInfra100%Healthy24h 95.76%
- p50
- 1.60s
- p99
- 6.23s
- Throughput
- 37 tps
- Context
- 262K
- $/Mtok
- $2.00 / $6.00
deepinfra/fp4fp4 - Modal100%Healthy24h 99.54%
- p50
- 1.06s
- p99
- 5.66s
- Throughput
- 78 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $6.00
modal/nvfp4nvfp4 - Alibaba—No data24h 99.94%
- p50
- 1.27s
- p99
- 3.54s
- Throughput
- 38 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $6.00
alibaba - DigitalOcean—Down24h 97.77%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $2.00 / $6.00
digitalocean - SiliconFlow—No data24h 99.47%
- p50
- 1.28s
- p99
- 6.26s
- Throughput
- 38 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $6.00
siliconflow/fp8fp8 - Together—No data24h 99.87%
- p50
- 5.18s
- p99
- 7.26s
- Throughput
- 77 tps
- Context
- 1.0M
- $/Mtok
- $2.50 / $6.25
together - Venice—No data24h 98.39%
- p50
- 1.14s
- p99
- 8.87s
- Throughput
- 94 tps
- Context
- 262K
- $/Mtok
- $2.50 / $7.50
venice
Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
4 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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.
Throughput
Median tokens per second.