Qwen3.8 27B: 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) | 98.01% | 98.60% | 98.60% | 669ms◆ (best) | 20.8s | 41 tps | 262K | $0.450 / $3.20 | |
Alibabaalibaba | Healthy | 100%◆ (best) | 99.91% | 99.86%◆ (best) | 99.86%◆ (best) | 1.81s | 93.7s | 45 tps | 1.0M | $0.575 / $3.45 |
| Healthy | 100%◆ (best) | 98.56% | 99.13% | 99.13% | 2.14s | 17.3s | 22 tps | 66K | $0.480 / $3.40 | |
| Healthy | 100%◆ (best) | 99.84% | 99.53% | 99.53% | 1.26s | 15.8s | 61 tps | 262K | $0.450 / $3.20 | |
| Healthy | 100%◆ (best) | 99.82% | 99.27% | 99.27% | 1.00s | 12.0s◆ (best) | 102 tps◆ (best) | 262K | $0.450 / $3.20 | |
| Healthy | 98.25% | 98.92% | 98.40% | 98.40% | 1.38s | 20.6s | 22 tps | 262K | $0.450 / $3.20 | |
| Degraded | 94.23% | 97.47% | 97.68% | 97.68% | 7.29s | 50.9s | 12 tps | 262K | $0.400 / $3.00◆ (best) |
- AkashML100%◆ (best)Healthy24h 98.01%
- 7d
- 98.60%
- 30d
- 98.60%
- p50
- 669ms◆ (best)
- p99
- 20.8s
- Throughput
- 41 tps
- Context
- 262K
- $/Mtok
- $0.450 / $3.20
akashml/bf16bf16 - Alibaba100%◆ (best)Healthy24h 99.91%
- 7d
- 99.86%◆ (best)
- 30d
- 99.86%◆ (best)
- p50
- 1.81s
- p99
- 93.7s
- Throughput
- 45 tps
- Context
- 1.0M
- $/Mtok
- $0.575 / $3.45
alibaba - Io Net100%◆ (best)Healthy24h 98.56%
- 7d
- 99.13%
- 30d
- 99.13%
- p50
- 2.14s
- p99
- 17.3s
- Throughput
- 22 tps
- Context
- 66K
- $/Mtok
- $0.480 / $3.40
io-net/fp8fp8 - Reka100%◆ (best)Healthy24h 99.84%
- 7d
- 99.53%
- 30d
- 99.53%
- p50
- 1.26s
- p99
- 15.8s
- Throughput
- 61 tps
- Context
- 262K
- $/Mtok
- $0.450 / $3.20
reka/fp8fp8 - Venice100%◆ (best)Healthy24h 99.82%
- 7d
- 99.27%
- 30d
- 99.27%
- p50
- 1.00s
- p99
- 12.0s◆ (best)
- Throughput
- 102 tps◆ (best)
- Context
- 262K
- $/Mtok
- $0.450 / $3.20
venice/fp8fp8 - Parasail98.25%Healthy24h 98.92%
- 7d
- 98.40%
- 30d
- 98.40%
- p50
- 1.38s
- p99
- 20.6s
- Throughput
- 22 tps
- Context
- 262K
- $/Mtok
- $0.450 / $3.20
parasail/fp8fp8 - Chutes94.23%Degraded24h 97.47%
- 7d
- 97.68%
- 30d
- 97.68%
- p50
- 7.29s
- p99
- 50.9s
- Throughput
- 12 tps
- Context
- 262K
- $/Mtok
- $0.400 / $3.00◆ (best)
chutes/fp8fp8
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.