Qwen: Qwen3 Coder 480B A35B
qwen/qwen3-coder
Cheapest provider
$0.22 / 1M
Fastest provider (p95)
—
No throughput data yet — populated as traffic accumulates
Intelligence (estimated)
70.0
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 |
|---|---|---|---|---|---|---|---|
| undisclosed | $0.2200 | $1.8000 | — | — | — | — | |
| DeepInfra | q4· fp4 | $0.3000 | $1.0000 | — | — | 99.96% | — |
| Venice | q8· fp8 | $0.3500 | $1.5000 | — | — | — | — |
| Novita | q8· fp8 | $0.3800 | $1.5500 | — | — | — | — |
| AtlasCloud | q8· fp8 | $0.7800 | $3.8000 | — | — | — | — |
| Alibaba | undisclosed | $0.9750 | $4.8750 | — | — | — | — |
| WandB | full· bf16 | $1.0000 | $1.5000 | — | — | — | — |
“—” 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
- ·≥1M context +1
Want a curated score? File a benchmark report and we’ll add it to the next sync.
How Atlas mode sources Qwen: Qwen3 Coder 480B A35B
- Strict mode — pin Qwen: Qwen3 Coder 480B A35B exactly and we pass it straight through, sourced from the cheapest provider above. The same model, no substitutions — currently Google at $0.22/1M.
- 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.