Qwen: Qwen3 235B A22B Thinking 2507
qwen/qwen3-235b-a22b-thinking-2507
Cheapest provider
$0.10 / 1M
WandB
Fastest provider (p95)
99 tok/s
WandB
Intelligence (composite)
83.1
MMLU-Pro · HumanEval · math · GPQA
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 |
|---|---|---|---|---|---|---|---|
| WandB | full· bf16 | $0.1000 | $0.1000 | 395ms / 1017ms | 84 / 99 tok/s | 100.00% | 84.3% |
| Alibaba | undisclosed | $0.1495 | $1.4950 | 638ms / 6083ms | 69 / 81 tok/s | 98.47% | 97.2% |
| DeepInfra | q8· fp8 | $0.2300 | $2.3000 | 615ms / 1742ms | 47 / 62.1 tok/s | 99.64% | 97.6% |
| AtlasCloud | q8· fp8 | $0.2800 | $2.3000 | 1257ms / 3269ms | 24 / 38.2 tok/s | 97.96% | 98.0% |
| Novita | q8· fp8 | $0.3000 | $3.0000 | 719ms / 3184ms | 49 / 63.9 tok/s | — | 81.3% |
“—” 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 breakdown
Composite score is a weighted average of public benchmarks (30% MMLU-Pro, 25% code pass@1, 25% math, 20% GPQA). Numbers come from model cards and the Artificial Analysis intelligence harness; missing components are renormalised over what’s present.
MMLU-Pro
84.4
broad reasoning
Code
74.1
pass@1 (HumanEval / LiveCodeBench)
AIME 2025
92.3
math accuracy
GPQA Diamond
81.1
hard reasoning
Source: Qwen3-235B-A22B-Thinking-2507 model card (MMLU-Pro 84.4, GPQA 81.1, LiveCodeBench v6 74.1, AIME25 92.3); huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507
How Atlas mode sources Qwen: Qwen3 235B A22B Thinking 2507
- Strict mode — pin Qwen: Qwen3 235B A22B Thinking 2507 exactly and we pass it straight through, sourced from the cheapest provider above. The same model, no substitutions — currently WandB at $0.10/1M.
- 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.