All Models
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...
Available Providers (14)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 ModelScope | Qwen/Qwen3-235B-A22B-Thinking-2507 | $0.00/MTok | $0.00/MTok | 262.1K | 131.1K | |
 OpenRouter | qwen/qwen3-235b-a22b-thinking-2507 | $0.08/MTok | $0.31/MTok | 262.1K | 81.9K | |
 Weights & Biases | Qwen/Qwen3-235B-A22B-Thinking-2507 | $0.10/MTok | $0.10/MTok | 262.1K | 262.1K | |
 Chutes | Qwen/Qwen3-235B-A22B-Thinking-2507 | $0.11/MTok | $0.60/MTok | 262.1K | 262.1K | |
 submodel | Qwen/Qwen3-235B-A22B-Thinking-2507 | $0.20/MTok | $0.60/MTok | 262.1K | 131.1K | |
 Nebius Token Factory | Qwen/Qwen3-235B-A22B-Thinking-2507 | $0.20/MTok | $0.80/MTok | 262.1K | 8.2K | |
 LLM Gateway | qwen3-235b-a22b-thinking-2507 | $0.20/MTok | $0.60/MTok | 262K | 8.2K | |
 AIHubMix | qwen3-235b-a22b-thinking-2507 | $0.28/MTok | $2.80/MTok | 262.1K | 262.1K | |
 Jiekou.AI | qwen/qwen3-235b-a22b-thinking-2507 | $0.30/MTok | $3.00/MTok | 131.1K | 131.1K | |
 Hugging Face | Qwen/Qwen3-235B-A22B-Thinking-2507 | $0.30/MTok | $3.00/MTok | 262.1K | 131.1K | |
 NovitaAI | qwen/qwen3-235b-a22b-thinking-2507 | $0.30/MTok | $3.00/MTok | 131.1K | 32.8K | |
 Vercel AI Gateway | alibaba/qwen3-235b-a22b-thinking | $0.30/MTok | $2.90/MTok | 262.1K | 262.1K | |
 Synthetic | hf:Qwen/Qwen3-235B-A22B-Thinking-2507 | $0.65/MTok | $3.00/MTok | 256K | 32K | |
 Qiniu | qwen3-235b-a22b-thinking-2507 | —/MTok | —/MTok | 262.1K | 4.1K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output