Author's Description
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.
Key Specifications
Supported Parameters
This model supports the following parameters:
Features
This model supports the following features:
Performance Summary
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) model optimized for complex reasoning. While it tends to have longer response times, ranking in the 12th percentile for speed, and is positioned at premium pricing levels (5th percentile), its reliability is exceptional, demonstrating a 100% success rate across all benchmarks. The model exhibits outstanding performance in specialized domains. It achieved perfect accuracy in General Knowledge and near-perfect scores in Coding (98.0%, top 3 in accuracy) and Reasoning (98.0%, 90th percentile), aligning with its "thinking-only" design. Mathematics also shows strong results at 92.9% accuracy (75th percentile). Its ability to handle complex instructions is a notable weakness, with only 26.3% accuracy in Instruction Following. Hallucination rates are low at 94.0% accuracy, indicating a good grasp of uncertainty. Classification tasks, such as Keyword Topic Relevance (90.0%) and Email Classification (99.0%), are handled competently. The model's strengths lie in structured logical reasoning, mathematics, science, and long-form generation, making it highly suitable for agentic workflows and tasks requiring high-token outputs.
Model Pricing
Current Pricing
Feature | Price (per 1M tokens) |
---|---|
Prompt | $0.7 |
Completion | $8.4 |
Price History
Available Endpoints
Provider | Endpoint Name | Context Length | Pricing (Input) | Pricing (Output) |
---|---|---|---|---|
Alibaba
|
Alibaba | qwen/qwen3-235b-a22b-thinking-2507 | 131K | $0.7 / 1M tokens | $8.4 / 1M tokens |
Novita
|
Novita | qwen/qwen3-235b-a22b-thinking-2507 | 131K | $0.11 / 1M tokens | $0.6 / 1M tokens |
Chutes
|
Chutes | qwen/qwen3-235b-a22b-thinking-2507 | 262K | $0.11 / 1M tokens | $0.6 / 1M tokens |
Novita
|
Novita | qwen/qwen3-235b-a22b-thinking-2507 | 131K | $0.3 / 1M tokens | $3 / 1M tokens |
DeepInfra
|
DeepInfra | qwen/qwen3-235b-a22b-thinking-2507 | 262K | $0.3 / 1M tokens | $2.9 / 1M tokens |
Parasail
|
Parasail | qwen/qwen3-235b-a22b-thinking-2507 | 262K | $0.11 / 1M tokens | $0.6 / 1M tokens |
Together
|
Together | qwen/qwen3-235b-a22b-thinking-2507 | 262K | $0.65 / 1M tokens | $3 / 1M tokens |
Crusoe
|
Crusoe | qwen/qwen3-235b-a22b-thinking-2507 | 262K | $0.11 / 1M tokens | $0.6 / 1M tokens |
Cerebras
|
Cerebras | qwen/qwen3-235b-a22b-thinking-2507 | 131K | $0.6 / 1M tokens | $2.9 / 1M tokens |
GMICloud
|
GMICloud | qwen/qwen3-235b-a22b-thinking-2507 | 131K | $0.6 / 1M tokens | $3 / 1M tokens |
SiliconFlow
|
SiliconFlow | qwen/qwen3-235b-a22b-thinking-2507 | 262K | $0.13 / 1M tokens | $0.6 / 1M tokens |
Chutes
|
Chutes | qwen/qwen3-235b-a22b-thinking-2507 | 262K | $0.11 / 1M tokens | $0.6 / 1M tokens |
Benchmark Results
Benchmark | Category | Reasoning | Strategy | Free | Executions | Accuracy | Cost | Duration |
---|
Other Models by qwen
|
Released | Params | Context |
|
Speed | Ability | Cost |
---|---|---|---|---|---|---|---|
Qwen: Qwen3 VL 235B A22B Thinking | Sep 23, 2025 | 235B | 131K |
Text input
Image input
Text output
|
★ | ★ | $$$$$ |
Qwen: Qwen3 VL 235B A22B Instruct | Sep 23, 2025 | 235B | 131K |
Text input
Image input
Text output
|
★★★ | ★★★★★ | $$$ |
Qwen: Qwen3 Max | Sep 23, 2025 | — | 256K |
Text input
Text output
|
★★★★ | ★★★★★ | $$$$ |
Qwen: Qwen3 Coder Plus | Sep 23, 2025 | ~480B | 128K |
Text input
Text output
|
★★★★ | ★★★★ | $$$$ |
Qwen: Qwen3 Coder Flash | Sep 17, 2025 | — | 128K |
Text input
Text output
|
★★★★ | ★★★ | $$$ |
Qwen: Qwen3 Next 80B A3B Thinking | Sep 11, 2025 | 80B | 262K |
Text input
Text output
|
★ | ★★★★ | $$$$$ |
Qwen: Qwen3 Next 80B A3B Instruct | Sep 11, 2025 | 80B | 262K |
Text input
Text output
|
★★★★ | ★★★★★ | $$$$ |
Qwen: Qwen Plus 0728 | Sep 08, 2025 | ~20B | 1M |
Text input
Text output
|
★★★★★ | ★★★ | $$$ |
Qwen: Qwen3 30B A3B Thinking 2507 | Aug 28, 2025 | 30B | 262K |
Text input
Text output
|
★★ | ★★★ | $$$$ |
Qwen: Qwen3 Coder 30B A3B Instruct | Jul 31, 2025 | 30B | 262K |
Text input
Text output
|
★★★★ | ★★★ | $$ |
Qwen: Qwen3 30B A3B Instruct 2507 | Jul 29, 2025 | 30B | 131K |
Text input
Text output
|
★★★★ | ★★★★ | $$$ |
Qwen: Qwen3 Coder 480B A35B | Jul 22, 2025 | 480B | 1M |
Text input
Text output
|
★ | ★★★ | $$$ |
Qwen: Qwen3 235B A22B Instruct 2507 | Jul 21, 2025 | 235B | 262K |
Text input
Text output
|
★★ | ★★★ | $$$ |
Qwen: Qwen3 30B A3B | Apr 28, 2025 | 30B | 40K |
Text input
Text output
|
★ | ★★★★★ | $$$$ |
Qwen: Qwen3 8B | Apr 28, 2025 | 8B | 128K |
Text input
Text output
|
★ | ★★★ | $$$ |
Qwen: Qwen3 14B | Apr 28, 2025 | 14B | 40K |
Text input
Text output
|
★★ | ★★★★ | $$$ |
Qwen: Qwen3 32B | Apr 28, 2025 | 32B | 40K |
Text input
Text output
|
★ | ★★★★★ | $$$ |
Qwen: Qwen3 235B A22B | Apr 28, 2025 | 235B | 40K |
Text input
Text output
|
★ | ★★★★ | $$$$ |
Qwen: Qwen2.5 VL 32B Instruct | Mar 24, 2025 | 32B | 128K |
Text input
Image input
Text output
|
★ | ★★★ | $$$ |
Qwen: QwQ 32B | Mar 05, 2025 | 32B | 131K |
Text input
Text output
|
★ | ★★★ | $$$ |
Qwen: Qwen VL Plus | Feb 04, 2025 | — | 7K |
Text input
Image input
Text output
|
★★★★ | ★★ | $$$ |
Qwen: Qwen VL Max | Feb 01, 2025 | — | 7K |
Text input
Image input
Text output
|
★★★ | ★★★ | $$$$ |
Qwen: Qwen-Turbo | Feb 01, 2025 | — | 1M |
Text input
Text output
|
★★★★★ | ★★★★ | $$ |
Qwen: Qwen2.5 VL 72B Instruct | Feb 01, 2025 | 72B | 32K |
Text input
Image input
Text output
|
★★★★ | ★★★★ | $$ |
Qwen: Qwen-Plus | Feb 01, 2025 | — | 131K |
Text input
Text output
|
★★★★ | ★★★★ | $$$ |
Qwen: Qwen-Max | Feb 01, 2025 | — | 32K |
Text input
Text output
|
★★★★ | ★★★★ | $$$$ |
Qwen: QwQ 32B Preview Unavailable | Nov 27, 2024 | 32B | 32K |
Text input
Text output
|
— | ★ | $$ |
Qwen2.5 Coder 32B Instruct | Nov 11, 2024 | ~500B | 32K |
Text input
Text output
|
★★★★★ | ★★★★★ | $ |
Qwen: Qwen2.5 7B Instruct | Oct 15, 2024 | ~500B | 32K |
Text input
Text output
|
★ | ★★ | $ |
Qwen2.5 72B Instruct | Sep 18, 2024 | ~500B | 32K |
Text input
Text output
|
★★★ | ★★ | $$ |
Qwen: Qwen2.5-VL 7B Instruct | Aug 27, 2024 | ~500B | 32K |
Text input
Image input
Text output
|
★★★★ | ★★ | $$ |
Qwen 2 72B Instruct Unavailable | Jun 06, 2024 | ~500B | 32K |
Text input
Text output
|
★★★★ | ★★ | $$$$ |