Alibaba: qwen3-coder-plus:free
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.
Pricing
Uptime
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 | All providers | Not sent by default |
| logprobs | All providers | - |
| max_tokens | All providers | - |
| presence_penalty | All providers | - |
| response_format | All providers | - |
| seed | All providers | - |
| stop | All providers | - |
| structured_outputs | All providers | - |
| temperature | All providers | Not sent by default |
| tool_choice | All providers | - |
| tools | All providers | - |
| top_k | All providers | - |
| top_logprobs | All providers | - |
| top_p | All providers | Not sent by default |