Alibaba: qwen3-coder-plus
A flagship code generation snapshot released by Alibaba Cloud on September 23, 2025. Built on the 480B total / 35B active parameter Mixture-of-Experts (MoE) architecture, this 0923 snapshot is a pivotal upgrade to the original qwen3-coder-plus. It significantly enhances tool-calling robustness and code safety during Agentic Coding workflows. Recognized as a premier choice for complex IDE integrations (e.g., Cursor, Cline, Qwen Code), it excels in cross-file refactoring, autonomous debugging, and automated code reviews, maintaining its status as a top-tier coding model in 2026.
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 |
| logprobs | All providers | - |
| max_tokens | All providers | - |
| presence_penalty | All providers | - |
| response_format | All providers | - |
| seed | All providers | - |
| structured_outputs | All providers | - |
| temperature | All providers | Not sent by default |
| tool_choice | All providers | - |
| tools | All providers | - |
| top_logprobs | All providers | - |
| top_p | All providers | Not sent by default |