Qwen: Qwen3 235B A22B Instruct 2507
qwen/qwen3-235b-a22b-2507
Cheapest provider
$0.07 / 1M
DeepInfra
Fastest provider (p95)
—
No throughput data yet — populated as traffic accumulates
Intelligence (estimated)
71.0
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 |
|---|---|---|---|---|---|---|---|
| DeepInfra | q8· fp8 | $0.0710 | $0.1000 | — | — | 93.31% | — |
| Novita | q8· fp8 | $0.0900 | $0.5800 | — | — | 99.98% | — |
| Parasail | q8· fp8 | $0.1000 | $0.6000 | — | — | 99.90% | — |
| WandB | full· bf16 | $0.1000 | $0.1000 | — | — | 99.96% | — |
| Alibaba | undisclosed | $0.1495 | $0.5980 | — | — | 100.00% | — |
| AtlasCloud | q8· fp8 | $0.2000 | $0.8800 | — | — | 99.94% | — |
| Friendli | undisclosed | $0.2000 | $0.8000 | — | — | 93.90% | — |
| Together | undisclosed | $0.2000 | $0.6000 | — | — | 95.55% | — |
| undisclosed | $0.2200 | $0.8800 | — | — | 99.66% | — | |
| undisclosed | $0.2500 | $1.0000 | — | — | 99.93% | — | |
| StreamLake | undisclosed | $0.2800 | $1.1200 | — | — | 91.87% | — |
| Cerebras | full· fp16 | $0.6000 | $1.2000 | — | — | 100.00% | — |
“—” 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
Want a curated score? File a benchmark report and we’ll add it to the next sync.
How Atlas routes Qwen: Qwen3 235B A22B Instruct 2507
- 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 235B A22B Instruct 2507 that’s currently DeepInfra at $0.07/1M.
- Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.