Qwen3 VL 8B Instruct: 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 | 98.64%◆ (best) | 99.23% | 99.18%◆ (best) | 99.74%◆ (best) | 535ms◆ (best) | 2.20s◆ (best) | 85 tps◆ (best) | 131K | $0.117 / $0.455◆ (best) |
| Degraded | 97.17% | 98.17% | 97.74% | 98.57% | 1.20s | 14.9s | 23 tps | 262K | $0.250 / $0.750 | |
PrimeIntellectprimeintellect | Healthy | 97.05% | 98.47% | 98.92% | 98.92% | 975ms | 3.73s | 69 tps | 262K | $0.117 / $0.455◆ (best) |
- Alibaba98.64%◆ (best)Healthy24h 99.23%
- 7d
- 99.18%◆ (best)
- 30d
- 99.74%◆ (best)
- p50
- 535ms◆ (best)
- p99
- 2.20s◆ (best)
- Throughput
- 85 tps◆ (best)
- Context
- 131K
- $/Mtok
- $0.117 / $0.455◆ (best)
alibaba - Parasail97.17%Degraded24h 98.17%
- 7d
- 97.74%
- 30d
- 98.57%
- p50
- 1.20s
- p99
- 14.9s
- Throughput
- 23 tps
- Context
- 262K
- $/Mtok
- $0.250 / $0.750
parasail/bf16bf16 - PrimeIntellect97.05%Healthy24h 98.47%
- 7d
- 98.92%
- 30d
- 98.92%
- p50
- 975ms
- p99
- 3.73s
- Throughput
- 69 tps
- Context
- 262K
- $/Mtok
- $0.117 / $0.455◆ (best)
primeintellect
Measured 3m 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.