Qwen: Qwen3 VL 30B A3B Instruct
qwen/qwen3-vl-30b-a3b-instruct
Cheapest provider
$0.13 / 1M
Alibaba
Fastest provider (p95)
91 tok/s
AtlasCloud
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 | $0.5200 | 663ms / 1739ms | 45.5 / 81 tok/s | 100.00% | 100.0% |
| AtlasCloud | q8· fp8 | $0.1500 | $0.6000 | 931ms / 2350ms | 43 / 91 tok/s | 95.98% | 99.9% |
| DeepInfra | q8· fp8 | $0.1500 | $0.6000 | 378ms / 1255ms | 30 / 42 tok/s | 99.97% | 100.0% |
| Novita | full· bf16 | $0.2000 | $0.7000 | 1820ms / 4526ms | 25 / 58 tok/s | 98.85% | 98.7% |
| Phala | undisclosed | $0.2000 | $0.7000 | 882ms / 2277ms | 35 / 56 tok/s | 99.95% | 99.8% |
| Venice | undisclosed | $0.2500 | $0.9000 | 1413ms / 2276ms | 28 / 52 tok/s | 100.00% | 80.7% |
| SiliconFlow | q8· fp8 | $0.2900 | $1.0000 | 4651ms / 23154ms | 8 / 15.7 tok/s | 97.03% | 94.2% |
“—” 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 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 30B A3B Instruct 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.