Qwen3 VL 235B A22B Instruct
qwen/qwen3-vl-235b-a22b-instructInputOutput
Compare its 6 providersIncident RSSCompare with Qwen3 235B A22B Instruct 2507, Qwen3 30B A3B Instruct 2507, Qwen3 Coder 480B A35B
CompareQwen3 VL 235B A22B Instruct
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 96.07% | 96.04% | 95.78% | 1.44s | 5.27s | 45 tps | 131K | $0.300 / $1.50 | |
Alibabaalibaba | Healthy | 99.54% | 99.28% | 98.95% | 99.46% | 652ms | 2.83s | 48 tps | 131K | $0.260 / $1.04 |
| Healthy | 98.85% | 99.37% | 99.15% | 99.10% | 902ms | 7.83s | 43 tps | 131K | $0.210 / $1.90 | |
| Healthy | 97.06% | 96.83% | 96.46% | 96.21% | 1.99s | 27.1s | 27 tps | 128K | $0.210 / $1.90 | |
| Down | 83.33% | 97.28% | 96.83% | 95.83% | 1.73s | 14.1s | 19 tps | 262K | $0.200 / $0.880 | |
PrimeIntellectprimeintellect | No data | — | 98.75% | 92.89% | 92.89% | 1.29s | 47.9s | 42 tps | 262K | $0.300 / $1.50 |
- Novita100%Healthy24h 96.07%
- 7d
- 96.04%
- 30d
- 95.78%
- p50
- 1.44s
- p99
- 5.27s
- Throughput
- 45 tps
- Context
- 131K
- $/Mtok
- $0.300 / $1.50
novita/bf16bf16 - Alibaba99.54%Healthy24h 99.28%
- 7d
- 98.95%
- 30d
- 99.46%
- p50
- 652ms
- p99
- 2.83s
- Throughput
- 48 tps
- Context
- 131K
- $/Mtok
- $0.260 / $1.04
alibaba - Parasail98.85%Healthy24h 99.37%
- 7d
- 99.15%
- 30d
- 99.10%
- p50
- 902ms
- p99
- 7.83s
- Throughput
- 43 tps
- Context
- 131K
- $/Mtok
- $0.210 / $1.90
parasail/fp8fp8 - Venice97.06%Healthy24h 96.83%
- 7d
- 96.46%
- 30d
- 96.21%
- p50
- 1.99s
- p99
- 27.1s
- Throughput
- 27 tps
- Context
- 128K
- $/Mtok
- $0.210 / $1.90
venice/fp8fp8 - DeepInfra83.33%Down24h 97.28%
- 7d
- 96.83%
- 30d
- 95.83%
- p50
- 1.73s
- p99
- 14.1s
- Throughput
- 19 tps
- Context
- 262K
- $/Mtok
- $0.200 / $0.880
deepinfra/fp8fp8 - No data24h 98.75%
- 7d
- 92.89%
- 30d
- 92.89%
- p50
- 1.29s
- p99
- 47.9s
- Throughput
- 42 tps
- Context
- 262K
- $/Mtok
- $0.300 / $1.50
primeintellect
Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
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.
Daily availability
One row per endpoint · one dot per day · last 90 days.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 6 endpoints · 47 days with data, 82 endpoint-days below 90%.