Qwen: Qwen3 235B A22B Thinking 2507
qwen/qwen3-235b-a22b-thinking-2507
Cheapest provider
$0.15 / 1M
Alibaba
Fastest provider (p95)
74 tok/s
Alibaba
Intelligence (composite)
83.1
MMLU-Pro · HumanEval · math · GPQA
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 |
|---|---|---|---|---|---|---|---|
| Alibaba | undisclosed | $0.1495 | $1.4950 | 520ms / 4552ms | 52 / 74 tok/s | 100.00% | 100.0% |
| DeepInfra | q8· fp8 | $0.2300 | $2.3000 | 913ms / 10941ms | 37 / 47 tok/s | — | 95.4% |
| AtlasCloud | q8· fp8 | $0.2800 | $2.3000 | 1398ms / 10879ms | 56 / 72 tok/s | — | 100.0% |
| Novita | q8· fp8 | $0.3000 | $3.0000 | 717ms / 3585ms | 39 / 49 tok/s | — | 62.0% |
“—” 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 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 routes Qwen: Qwen3 235B A22B Thinking 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 Thinking 2507 that’s currently Alibaba at $0.15/1M.
- Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.