Qwen: Qwen3 VL 235B A22B Instruct
qwen/qwen3-vl-235b-a22b-instruct
Cheapest provider
$0.20 / 1M
DeepInfra
Fastest provider (p95)
69 tok/s
DeepInfra
Intelligence (estimated)
71.0
Family + generation + popularity + price tier
Per-provider performance
Latency / throughput / uptime measured across providers over the last 30 minutes of live traffic. Atlas’s router weighs these per call (with the eval-gate signal) when picking a variant for Standard and Batch tiers.
| Provider | Quant | Input $/1M | Output $/1M | Latency p50 / p95 | Throughput p50 / p95 | Uptime 30m | Success |
|---|---|---|---|---|---|---|---|
| DeepInfra | q8· fp8 | $0.2000 | $0.8800 | 876ms / 2480ms | 40 / 69 tok/s | 99.79% | 35.2% |
| Parasail | q8· fp8 | $0.2100 | $1.9000 | 1227ms / 4030ms | 24 / 50 tok/s | 99.80% | 100.0% |
| Venice | q8· fp8 | $0.2500 | $1.5000 | 872ms / 3355ms | 31 / 50 tok/s | 99.50% | 77.2% |
| Alibaba | undisclosed | $0.2600 | $1.0400 | 885ms / 2053ms | 38 / 50 tok/s | 99.93% | 99.9% |
| AtlasCloud | q8· fp8 | $0.3000 | $1.5000 | 1114ms / 3420ms | 33 / 45 tok/s | 78.80% | 73.3% |
| Novita | full· bf16 | $0.3000 | $1.5000 | 2109ms / 5855ms | 24 / 40 tok/s | 87.55% | 91.9% |
“—” 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 routes Qwen: Qwen3 VL 235B A22B Instruct
- Realtime tier — direct passthrough at the upstream’s native precision. Best for hard latency / quality guarantees.
- Standard tier — Atlas picks the cheapest provider variant whose quantization has stayed green on your operation’s eval gates. For Qwen: Qwen3 VL 235B A22B Instruct that’s currently DeepInfra at $0.20/1M.
- Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.