Qwen: Qwen3 VL 30B A3B Thinking
qwen/qwen3-vl-30b-a3b-thinking
Cheapest provider
$0.13 / 1M
Alibaba
Fastest provider (p95)
134 tok/s
Alibaba
Intelligence (estimated)
58.0
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 |
|---|---|---|---|---|---|---|---|
| Alibaba | undisclosed | $0.1300 | $1.5600 | 567ms / 1676ms | 118 / 133.8 tok/s | — | — |
| Novita | full· fp16 | $0.2000 | $1.0000 | 1692ms / 3987ms | 64.5 / 102 tok/s | — | — |
| SiliconFlow | q8· fp8 | $0.2900 | $1.0000 | 2700ms / 4149ms | 22.5 / 47.5 tok/s | — | — |
“—” 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 sm 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 30B A3B Thinking
- 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 30B A3B Thinking that’s currently Alibaba at $0.13/1M.
- Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.