All Models

Qwen2.5 Coder 32b Instruct

Tool Calling Open Weights Structured Output

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning** and **code fixing**. - A more comprehensive foundation for real-world applications such as **Code Agents**. Not only enhancing coding capabilities but also maintaining its strengths in mathematics and general competencies. To read more about its evaluation results, check out [Qwen 2.5 Coder's blog](https://qwenlm.github.io/blog/qwen2.5-coder-family/).

Providers 8
Released Nov 1, 2024
Input Modalities text
Output Modalities text
Tarsk Use coding

Available Providers (8)

Provider Model ID Input Cost Output Cost Context Max Output Docs
Nvidia qwen/qwen2.5-coder-32b-instruct $0.00/MTok $0.00/MTok 128K 4.1K
OpenRouter qwen/qwen-2.5-coder-32b-instruct $0.00/MTok $0.00/MTok 32.8K 8.2K
Chutes Qwen/Qwen2.5-Coder-32B-Instruct $0.03/MTok $0.11/MTok 32.8K 32.8K
Vultr Qwen2.5-Coder-32B-Instruct $0.20/MTok $0.60/MTok 15K 256
Kilo Gateway qwen/qwen-2.5-coder-32b-instruct $0.20/MTok $0.20/MTok 32.8K 8.2K
Alibaba (China) qwen2-5-coder-32b-instruct $0.29/MTok $0.86/MTok 131.1K 8.2K
Synthetic hf:Qwen/Qwen2.5-Coder-32B-Instruct $0.80/MTok $0.80/MTok 32.8K 32.8K
OVHcloud AI Endpoints qwen2.5-coder-32b-instruct $0.96/MTok $0.96/MTok 32.8K 32.8K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output