Qwen3-235B-A22B-Thinking-2507

Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144 tokens of context. This "thinking-only" variant enhances structured logical reasoning, mathematics, science, and long-form generation, showing strong benchmark performance across AIME, SuperGPQA, LiveCodeBench, and MMLU-Redux. It enforces a special reasoning mode (</think>) and is designed for high-token outputs (up to 81,920 tokens) in challenging domains. The model is instruction-tuned and excels at step-by-step reasoning, tool use, agentic workflows, and multilingual tasks. This release represents the most capable open-source variant in the Qwen3-235B series, surpassing many closed models in structured reasoning use cases.

Available at 30 Providers

	Provider	Model Name	Original Model	Input ($/1M)	Output ($/1M)	Free
	iFlow	Qwen3-235B-A22B-Thinking	qwen3-235b-a22b-thinking-2507	$0.00	$0.00		Visit
	ModelScope	Qwen3-235B-A22B-Thinking-2507	Qwen/Qwen3-235B-A22B-Thinking-2507	$0.00	$0.00		Visit
	Weights & Biases	Qwen3-235B-A22B-Thinking-2507	Qwen/Qwen3-235B-A22B-Thinking-2507	$0.10	$0.10		Visit
	Chutes.ai	Qwen3-235B-A22B-Thinking-2507	Qwen/Qwen3-235B-A22B-Thinking-2507	$0.11	$0.60		Visit
	IO.NET	Qwen 3 235B Thinking	Qwen/Qwen3-235B-A22B-Thinking-2507	$0.11	$0.60		Visit
	OpenRouter	Qwen3 235B A22B Thinking 2507	qwen/qwen3-235b-a22b-thinking-2507	$0.11	$0.60
	SiliconFlow (China)	Qwen/Qwen3-235B-A22B-Thinking-2507	Qwen/Qwen3-235B-A22B-Thinking-2507	$0.13	$0.60		Visit
	SiliconFlow	Qwen/Qwen3-235B-A22B-Thinking-2507	Qwen/Qwen3-235B-A22B-Thinking-2507	$0.13	$0.60		Visit
	Routeway	Alibaba: Qwen3 235B A22B Thinking 2507	qwen3-235b-a22b-thinking-2507	$0.18	$0.70
	submodel	Qwen3 235B A22B Thinking 2507	Qwen/Qwen3-235B-A22B-Thinking-2507	$0.20	$0.60		Visit
	Atlas Cloud	Qwen3 235B A22B Thinking 2507	qwen/qwen3-235b-a22b-thinking-2507	$0.20	$2.30
	Nebius Token Factory	Qwen3-235B-A22B-Thinking-2507	Qwen/Qwen3-235B-A22B-Thinking-2507	$0.20	$0.80
	DeepInfra	Qwen3-235B-A22B-Thinking-2507	Qwen/Qwen3-235B-A22B-Thinking-2507	$0.23	$2.39		Visit
	AIHubMix	qwen3-235b-a22b-thinking-2507	qwen3-235b-a22b-thinking-2507	$0.28	$2.80
	AIHubMix	qwen-3-235b-a22b-thinking-2507	qwen-3-235b-a22b-thinking-2507	$0.28	$2.80
	AIHubMix	Qwen3-235B-A22B-Thinking-2507	Qwen3-235B-A22B-Thinking-2507	$0.28	$2.80
	ZenMUX	Qwen: Qwen3 235B A22B Thinking 2507	qwen/qwen3-235b-a22b-thinking-2507	$0.28	$2.78		Visit
	Novita AI	qwen3-235b-a22b-thinking-2507	qwen/qwen3-235b-a22b-thinking-2507	$0.30	$3.00		Visit
	Hugging Face	Qwen3-235B-A22B-Thinking-2507	Qwen/Qwen3-235B-A22B-Thinking-2507	$0.30	$3.00		Visit
	Venice	Qwen 3 235B A22B Thinking 2507	qwen3-235b-a22b-thinking-2507	$0.45	$3.50		Visit
	Synthetic.new	Qwen/Qwen3-235B-A22B-Thinking-2507	Qwen/Qwen3-235B-A22B-Thinking-2507	$0.65	$3.00		Visit
	Together AI	Qwen3 235B A22B Thinking 2507 FP8	Qwen/Qwen3-235B-A22B-Thinking-2507	$0.65	$3.00		Visit
	AIMLAPI	Qwen 3 Thinking 2507	alibaba/qwen3-235b-a22b-thinking-2507	-	-		Visit
	Friendli	Qwen3 235B A22B Thinking 2507	Qwen/Qwen3-235B-A22B-Thinking-2507	-	-		Visit
	Nano-GPT	Qwen 3 235b A22B 2507 Thinking	Qwen/Qwen3-235B-A22B-Thinking-2507	-	-		Visit
	ValorGPT	Qwen3 235B A22B Thinking 2507	qwen-qwen3-235b-a22b-thinking-2507	-	-
	Yupp	Qwen3 235B A22B Thinking 2507 FP8 (Together AI)	Qwen/Qwen3-235B-A22B-Thinking-2507	-	-		Visit
	Yupp	Qwen3 235B A22B Thinking 2507 (OpenRouter)	qwen/qwen3-235b-a22b-thinking-2507	-	-		Visit
	Yupp	Qwen3-235B-A22B-Thinking-2507	qwen3-235b-a22b-thinking-2507	-	-		Visit
	LangDB	qwen3-235b-a22b-thinking-2507	qwen3-235b-a22b-thinking-2507	-	-