Qwen: Qwen3 VL 235B A22B Instruct
qwen/qwen3-vl-235b-a22b-instruct
Cheapest provider
$0.20 / 1M
DeepInfra
Fastest provider (p95)
59 tok/s
Venice
Intelligence (estimated)
71.0
Family + generation + popularity + price tier
Per-provider performance
Latency / throughput / uptime / price measured across providers over the last 30 minutes of live traffic. This is what proves “sourced cheapest” — Atlas mode draws on these per call to serve the cheapest path that holds quality.
| Provider | Quant | Input $/1M | Output $/1M | Latency p50 / p95 | Throughput p50 / p95 | Uptime 30m | Success |
|---|---|---|---|---|---|---|---|
| DeepInfra | q8· fp8 | $0.2000 | $0.8800 | 1274ms / 5028ms | 26 / 37 tok/s | 96.71% | 86.4% |
| Parasail | q8· fp8 | $0.2100 | $1.9000 | 844ms / 3537ms | 20 / 52 tok/s | 99.54% | 99.5% |
| Venice | q8· fp8 | $0.2500 | $1.5000 | 2166ms / 4950ms | 28 / 59 tok/s | 96.81% | 77.0% |
| Alibaba | undisclosed | $0.2600 | $1.0400 | 835ms / 2199ms | 39 / 53 tok/s | 100.00% | 100.0% |
| AtlasCloud | q8· fp8 | $0.3000 | $1.5000 | 2191ms / 4703ms | 6 / 19 tok/s | 81.64% | 81.1% |
| Novita | full· bf16 | $0.3000 | $1.5000 | 1496ms / 6019ms | 19 / 46 tok/s | 80.86% | 79.6% |
“—” means live telemetry hasn’t accumulated enough recent traffic for that endpoint. “undisclosed” means the provider serves the model but doesn’t expose the quantization label (typically running fp8 / int8 internally).
Intelligence estimate
No public benchmark numbers indexed for this model yet, so the leaderboard score is derived from the catalogue data we sync: model family standing, generation, and live usage rank — applied identically to open- and closed-weight models. The heuristic ceiling sits below confirmed-benchmark frontier models so curated rankings stay clearly on top.
- ·qwen lg family base
Want a curated score? File a benchmark report and we’ll add it to the next sync.
How Atlas mode sources Qwen: Qwen3 VL 235B A22B Instruct
- Strict mode — pin Qwen: Qwen3 VL 235B A22B Instruct exactly and we pass it straight through, sourced from the cheapest provider above. The same model, no substitutions — currently DeepInfra at $0.20/1M.
- Atlas mode — the default. Each call is auto-optimized for the cheapest path that holds quality, at least 5% off going direct from call one and climbing as it ramps. You always see which model served the call and exactly what you saved — thumbs-down anything you don’t like for a full refund.