Qwen3 VL 235B A22B Instruct
qwen/qwen3-vl-235b-a22b-instructInputOutput
Compare its 5 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% | 99.59% | 99.16% | 99.10% | 824ms | 6.56s | 40 tps | 131K | $0.210 / $1.90 | |
Alibabaalibaba | Healthy | 98.92% | 99.18% | 98.94% | 99.47% | 756ms | 2.83s | 43 tps | 131K | $0.260 / $1.04 |
| Healthy | 98.86% | 96.60% | 97.03% | 95.85% | 3.92s | 13.1s | 15 tps | 262K | $0.200 / $0.880 | |
| Healthy | 97.56% | 97.48% | 96.62% | 96.20% | 2.49s | 7.18s | 19 tps | 128K | $0.210 / $1.90 | |
| No data | — | 96.17% | 96.20% | 95.80% | 1.90s | 11.6s | 36 tps | 131K | $0.300 / $1.50 |
- Parasail100%Healthy24h 99.59%
- 7d
- 99.16%
- 30d
- 99.10%
- p50
- 824ms
- p99
- 6.56s
- Throughput
- 40 tps
- Context
- 131K
- $/Mtok
- $0.210 / $1.90
parasail/fp8fp8 - Alibaba98.92%Healthy24h 99.18%
- 7d
- 98.94%
- 30d
- 99.47%
- p50
- 756ms
- p99
- 2.83s
- Throughput
- 43 tps
- Context
- 131K
- $/Mtok
- $0.260 / $1.04
alibaba - DeepInfra98.86%Healthy24h 96.60%
- 7d
- 97.03%
- 30d
- 95.85%
- p50
- 3.92s
- p99
- 13.1s
- Throughput
- 15 tps
- Context
- 262K
- $/Mtok
- $0.200 / $0.880
deepinfra/fp8fp8 - Venice97.56%Healthy24h 97.48%
- 7d
- 96.62%
- 30d
- 96.20%
- p50
- 2.49s
- p99
- 7.18s
- Throughput
- 19 tps
- Context
- 128K
- $/Mtok
- $0.210 / $1.90
venice/fp8fp8 - No data24h 96.17%
- 7d
- 96.20%
- 30d
- 95.80%
- p50
- 1.90s
- p99
- 11.6s
- Throughput
- 36 tps
- Context
- 131K
- $/Mtok
- $0.300 / $1.50
novita/bf16bf16
Measured 4m 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.
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 · 5 endpoints · 46 days with data, 78 endpoint-days below 90%.