Qwen3.8 2.4T A95B: 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) | 99.99% | 99.75% | 99.47% | 1.06s | 5.28s | 88 tps | 262K | $2.00 / $6.00◆ (best) | |
Novitanovita | Healthy | 100%◆ (best) | 99.99% | 99.87% | 99.90% | 4.31s | 30.0s | 36 tps | 1.0M | $2.00 / $6.00◆ (best) |
| Healthy | 100%◆ (best) | 99.80% | 99.88% | 99.73% | 5.69s | 44.4s | 32 tps | 1.0M | $2.00 / $6.00◆ (best) | |
Alibabaalibaba | No data | — | 99.92% | 99.91% | 99.92%◆ (best) | 2.03s | 14.3s | 41 tps | 1.0M | $2.00 / $6.00◆ (best) |
DigitalOceandigitalocean | No data | — | — | — | — | — | — | — | 262K | $2.00 / $6.00◆ (best) |
Modalmodal | No data | — | 99.27% | 99.20% | 99.74% | 212ms◆ (best) | 2.45s◆ (best) | 156 tps◆ (best) | 1.0M | $2.00 / $6.00◆ (best) |
| No data | — | — | — | — | — | — | — | 1.0M | $2.00 / $6.00◆ (best) | |
Togethertogether | No data | — | 99.93% | 99.99%◆ (best) | 99.90% | 430ms | 6.02s | 142 tps | 1.0M | $2.00 / $6.00◆ (best) |
Venicevenice | No data | — | 99.45% | 98.36% | 99.35% | 1.25s | 17.7s | 92 tps | 262K | $2.00 / $6.00◆ (best) |
- DeepInfra100%◆ (best)Healthy24h 99.99%
- 7d
- 99.75%
- 30d
- 99.47%
- p50
- 1.06s
- p99
- 5.28s
- Throughput
- 88 tps
- Context
- 262K
- $/Mtok
- $2.00 / $6.00◆ (best)
deepinfra/fp4fp4 - Novita100%◆ (best)Healthy24h 99.99%
- 7d
- 99.87%
- 30d
- 99.90%
- p50
- 4.31s
- p99
- 30.0s
- Throughput
- 36 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $6.00◆ (best)
novita - SiliconFlow100%◆ (best)Healthy24h 99.80%
- 7d
- 99.88%
- 30d
- 99.73%
- p50
- 5.69s
- p99
- 44.4s
- Throughput
- 32 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $6.00◆ (best)
siliconflow/fp8fp8 - No data24h 99.92%
- 7d
- 99.91%
- 30d
- 99.92%◆ (best)
- p50
- 2.03s
- p99
- 14.3s
- Throughput
- 41 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $6.00◆ (best)
alibaba - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $2.00 / $6.00◆ (best)
digitalocean - No data24h 99.27%
- 7d
- 99.20%
- 30d
- 99.74%
- p50
- 212ms◆ (best)
- p99
- 2.45s◆ (best)
- Throughput
- 156 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $2.00 / $6.00◆ (best)
modal - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $2.00 / $6.00◆ (best)
modal/nvfp4nvfp4 - No data24h 99.93%
- 7d
- 99.99%◆ (best)
- 30d
- 99.90%
- p50
- 430ms
- p99
- 6.02s
- Throughput
- 142 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $6.00◆ (best)
together - No data24h 99.45%
- 7d
- 98.36%
- 30d
- 99.35%
- p50
- 1.25s
- p99
- 17.7s
- Throughput
- 92 tps
- Context
- 262K
- $/Mtok
- $2.00 / $6.00◆ (best)
venice
Measured 1m 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.
Throughput
Median tokens per second.