Qwen: Qwen3 Coder 30B A3B Instruct
qwen/qwen3-coder-30b-a3b-instruct
Cheapest provider
$0.07 / 1M
Novita
Fastest provider (p95)
108 tok/s
Novita
Intelligence (estimated)
69.0
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 |
|---|---|---|---|---|---|---|---|
| Novita | q8· fp8 | $0.0700 | $0.2700 | 1396ms / 2901ms | 69 / 108 tok/s | 99.85% | 99.7% |
| SiliconFlow | q8· fp8 | $0.0700 | $0.2800 | 1869ms / 3904ms | 41 / 57 tok/s | 99.85% | 99.8% |
| Amazon Bedrock | undisclosed | $0.1500 | $0.6000 | — | — | — | — |
| Alibaba | undisclosed | $0.2925 | $1.4625 | 1058ms / 1877ms | 86 / 104.7 tok/s | — | 100.0% |
“—” 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 coder 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 Coder 30B A3B Instruct
- Strict mode — pin Qwen: Qwen3 Coder 30B A3B Instruct exactly and we pass it straight through, sourced from the cheapest provider above. The same model, no substitutions — currently Novita at $0.07/1M.
- 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.