Qwen3.8 2.4T A95B
qwen/qwen3.8-2.4t-a95bInputOutput
Compare its 9 providersIncident RSSCompare with Qwen3.8 27B, Qwen-Plus, Qwen3.8 Flash
CompareQwen3.8 2.4T A95B
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Novitanovita | Healthy | 100% | 99.84% | 99.87% | 99.90% | 1.54s | 19.8s | 32 tps | 1.0M | $2.00 / $6.00 |
Togethertogether | Healthy | 100% | 99.95% | 99.96% | 99.90% | 1.62s | 19.8s | 39 tps | 1.0M | $2.00 / $6.00 |
Alibabaalibaba | No data | — | 99.22% | 99.90% | 99.92% | 1.88s | 68.8s | 30 tps | 1.0M | $2.00 / $6.00 |
| No data | — | 99.67% | 99.76% | 99.47% | 540ms | 4.37s | 99 tps | 262K | $2.00 / $6.00 | |
DigitalOceandigitalocean | No data | — | — | — | — | — | — | — | 262K | $2.00 / $6.00 |
Modalmodal | No data | — | 96.33% | 99.37% | 99.78% | — | — | — | 1.0M | $2.00 / $6.00 |
| No data | — | — | — | — | — | — | — | 1.0M | $2.00 / $6.00 | |
| No data | — | 99.71% | 99.89% | 99.74% | 4.21s | 14.0s | 31 tps | 1.0M | $2.00 / $6.00 | |
Venicevenice | No data | — | 94.62% | 98.42% | 99.37% | 646ms | 4.37s | 60 tps | 262K | $2.00 / $6.00 |
- Novita100%Healthy24h 99.84%
- 7d
- 99.87%
- 30d
- 99.90%
- p50
- 1.54s
- p99
- 19.8s
- Throughput
- 32 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $6.00
novita - Together100%Healthy24h 99.95%
- 7d
- 99.96%
- 30d
- 99.90%
- p50
- 1.62s
- p99
- 19.8s
- Throughput
- 39 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $6.00
together - No data24h 99.22%
- 7d
- 99.90%
- 30d
- 99.92%
- p50
- 1.88s
- p99
- 68.8s
- Throughput
- 30 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $6.00
alibaba - No data24h 99.67%
- 7d
- 99.76%
- 30d
- 99.47%
- p50
- 540ms
- p99
- 4.37s
- Throughput
- 99 tps
- Context
- 262K
- $/Mtok
- $2.00 / $6.00
deepinfra/fp4fp4 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $2.00 / $6.00
digitalocean - No data24h 96.33%
- 7d
- 99.37%
- 30d
- 99.78%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $2.00 / $6.00
modal - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $2.00 / $6.00
modal/nvfp4nvfp4 - No data24h 99.71%
- 7d
- 99.89%
- 30d
- 99.74%
- p50
- 4.21s
- p99
- 14.0s
- Throughput
- 31 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $6.00
siliconflow/fp8fp8 - No data24h 94.62%
- 7d
- 98.42%
- 30d
- 99.37%
- p50
- 646ms
- p99
- 4.37s
- Throughput
- 60 tps
- Context
- 262K
- $/Mtok
- $2.00 / $6.00
venice
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
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.
Daily availability
One row per endpoint · one dot per day · last 90 days.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 9 endpoints · 47 days with data, 31 endpoint-days below 90%.
Price changes
- Qwen3.8 2.4T A95BVenicevenice$2.50 → $2.00 / $7.50 → $6.00cache read $0.313 → $0.2502026-09-12 18:11 UTC
- Qwen3.8 2.4T A95BTogethertogether$2.50 → $2.00 / $6.25 → $6.00cache read $0.500 → $0.2502026-09-04 00:41 UTC
- Qwen3.8 2.4T A95BTogethertogether$2.00 → $2.50 / $6.00 → $6.25cache read $0.250 → $0.5002026-08-28 22:10 UTC
- Qwen3.8 2.4T A95BTogethertogether$2.50 → $2.00 / $6.25 → $6.00cache read $0.500 → $0.2502026-08-28 18:40 UTC