Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.90 |
| Output tokens | $0.90 |
Capabilities
VisionMultimodalReasoningFunction CallingTool UseJSON ModeCode Execution
About Qwen2.5 Coder 32B
32B flagship code specialist matching GPT-4o performance with SOTA multi-language repair (75.2% on MdEval) and 3.7% improvement on repo-wide context benchmarks.
Get Started
Model Specs
Released2024-11-12
Parameters32B
ArchitectureDecoder Only