Alibaba: qwen3-235b-a22b-thinking-2507:free
The flagship Mixture-of-Experts (MoE) reasoning model released by Alibaba Cloud on July 25, 2025. As the pinnacle of the Qwen3 series, it features a 235B total parameter architecture specifically post-trained for deep Chain-of-Thought (CoT) reasoning. It natively generates <think> blocks to reveal its analytical process before providing a final answer. Boasting a staggering 92.3 on the AIME 2025 benchmark, its reasoning prowess rivals OpenAI o1, o3-mini, and DeepSeek-R1, making it the definitive choice for scientific research, advanced software engineering, and complex strategic planning.
All providers for this model are busy right now
Every upstream provider has hit its rate limit. The model comes back automatically once limits lift, usually within hours. Try again in a little while or switch to another model.
Request this model on DiscordPricing
Performance
Usage & Ranking
Supported parameters
All providers = every upstream serving this model supports it. Some providers = depends on which upstream handles the request. Default = the value sent when you leave the parameter unset.
| Parameter | Providers | Default |
|---|---|---|
| frequency_penalty | Some providers | Not sent by default |
| include_reasoning | All providers | - |
| logit_bias | Some providers | - |
| logprobs | Some providers | - |
| max_tokens | All providers | - |
| min_p | Some providers | - |
| presence_penalty | All providers | - |
| reasoning | All providers | - |
| repetition_penalty | Some providers | - |
| response_format | Some providers | - |
| seed | All providers | - |
| stop | Some providers | - |
| temperature | All providers | Not sent by default |
| tool_choice | Some providers | - |
| tools | Some providers | - |
| top_k | Some providers | - |
| top_logprobs | Some providers | - |
| top_p | All providers | Not sent by default |