Qwen2.5 72B Instruct
qwen/qwen-2.5-72b-instruct
Cheapest provider
$0.36 / 1M
DeepInfra
Fastest provider (p95)
34 tok/s
DeepInfra
Intelligence (estimated)
73.5
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 |
|---|---|---|---|---|---|---|---|
| DeepInfra | q8· fp8 | $0.3600 | $0.4000 | 247ms / 1702ms | 28 / 34 tok/s | 100.00% | 100.0% |
| Novita | full· bf16 | $0.3800 | $0.4000 | 6020ms / 19774ms | 26.5 / 31.4 tok/s | — | 54.3% |
“—” 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
- ·v2.5 generation +3
Want a curated score? File a benchmark report and we’ll add it to the next sync.
How Atlas mode sources Qwen2.5 72B Instruct
- Strict mode — pin Qwen2.5 72B Instruct exactly and we pass it straight through, sourced from the cheapest provider above. The same model, no substitutions — currently DeepInfra at $0.36/1M.
- 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.