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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Alibabaalibaba | Healthy | 100%◆ (best) | 99.92% | 99.91% | 99.92%◆ (best) | 1.32s | 10.3s | 33 tps | 1.0M | $2.00 / $6.00◆ (best) |
| Healthy | 100%◆ (best) | 99.99% | 99.75% | 99.48% | 3.37s | 16.9s | 64 tps | 262K | $2.00 / $6.00◆ (best) | |
Modalmodal | Healthy | 100%◆ (best) | 99.21% | 99.20% | 99.74% | 318ms◆ (best) | 2.65s◆ (best) | 173 tps◆ (best) | 1.0M | $2.00 / $6.00◆ (best) |
Novitanovita | Healthy | 100%◆ (best) | 99.99% | 99.87% | 99.90% | 4.16s | 42.8s | 36 tps | 1.0M | $2.00 / $6.00◆ (best) |
| Healthy | 100%◆ (best) | 99.80% | 99.88% | 99.73% | 5.47s | 31.6s | 31 tps | 1.0M | $2.00 / $6.00◆ (best) | |
Togethertogether | Healthy | 100%◆ (best) | 99.95% | 99.99%◆ (best) | 99.90% | 416ms | 3.72s | 151 tps | 1.0M | $2.00 / $6.00◆ (best) |
DigitalOceandigitalocean | No data | — | — | — | — | — | — | — | 262K | $2.00 / $6.00◆ (best) |
| No data | — | — | — | — | — | — | — | 1.0M | $2.00 / $6.00◆ (best) | |
Venicevenice | No data | — | 99.46% | 98.36% | 99.35% | 1.11s | 75.5s | 74 tps | 262K | $2.00 / $6.00◆ (best) |
- Alibaba100%◆ (best)Healthy24h 99.92%
- 7d
- 99.91%
- 30d
- 99.92%◆ (best)
- p50
- 1.32s
- p99
- 10.3s
- Throughput
- 33 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $6.00◆ (best)
alibaba - DeepInfra100%◆ (best)Healthy24h 99.99%
- 7d
- 99.75%
- 30d
- 99.48%
- p50
- 3.37s
- p99
- 16.9s
- Throughput
- 64 tps
- Context
- 262K
- $/Mtok
- $2.00 / $6.00◆ (best)
deepinfra/fp4fp4 - Modal100%◆ (best)Healthy24h 99.21%
- 7d
- 99.20%
- 30d
- 99.74%
- p50
- 318ms◆ (best)
- p99
- 2.65s◆ (best)
- Throughput
- 173 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $2.00 / $6.00◆ (best)
modal - Novita100%◆ (best)Healthy24h 99.99%
- 7d
- 99.87%
- 30d
- 99.90%
- p50
- 4.16s
- p99
- 42.8s
- 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
- 5.47s
- p99
- 31.6s
- Throughput
- 31 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $6.00◆ (best)
siliconflow/fp8fp8 - Together100%◆ (best)Healthy24h 99.95%
- 7d
- 99.99%◆ (best)
- 30d
- 99.90%
- p50
- 416ms
- p99
- 3.72s
- Throughput
- 151 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $6.00◆ (best)
together - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 262K
- $/Mtok
- $2.00 / $6.00◆ (best)
digitalocean - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $2.00 / $6.00◆ (best)
modal/nvfp4nvfp4 - No data24h 99.46%
- 7d
- 98.36%
- 30d
- 99.35%
- p50
- 1.11s
- p99
- 75.5s
- Throughput
- 74 tps
- Context
- 262K
- $/Mtok
- $2.00 / $6.00◆ (best)
venice
Measured 4m 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.