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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100%◆ (best) | 98.37% | 97.77% | 98.58% | 1.48s | 6.21s | 21 tps | 262K | $0.250 / $0.750 | |
PrimeIntellectprimeintellect | Healthy | 99.77% | 99.60% | — | — | 978ms | 3.42s | 50 tps | 262K | $0.117 / $0.455◆ (best) |
Alibabaalibaba | Healthy | 99.58% | 99.21% | 99.18%◆ (best) | 99.74%◆ (best) | 524ms◆ (best) | 2.30s◆ (best) | 81 tps◆ (best) | 131K | $0.117 / $0.455◆ (best) |
- Parasail100%◆ (best)Healthy24h 98.37%
- 7d
- 97.77%
- 30d
- 98.58%
- p50
- 1.48s
- p99
- 6.21s
- Throughput
- 21 tps
- Context
- 262K
- $/Mtok
- $0.250 / $0.750
parasail/bf16bf16 - PrimeIntellect99.77%Healthy24h 99.60%
- 7d
- —
- 30d
- —
- p50
- 978ms
- p99
- 3.42s
- Throughput
- 50 tps
- Context
- 262K
- $/Mtok
- $0.117 / $0.455◆ (best)
primeintellect - Alibaba99.58%Healthy24h 99.21%
- 7d
- 99.18%◆ (best)
- 30d
- 99.74%◆ (best)
- p50
- 524ms◆ (best)
- p99
- 2.30s◆ (best)
- Throughput
- 81 tps◆ (best)
- Context
- 131K
- $/Mtok
- $0.117 / $0.455◆ (best)
alibaba
Measured 5m 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.