Qwen2.5 Coder 32B
About
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.
Capabilities
VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution
Providers(2)
Compare all →| Provider | Input (per 1M) | Output (per 1M) | Type | |
|---|---|---|---|---|
| DeepInfra | $20 | $20 | Serverless | |
| Fireworks AI | $0.9 | $0.9 | Serverless |
Specifications
FamilyQwen2.5 Coder
Released2024-11-12
Parameters32B
ArchitectureDecoder Only
Specializationcoding
Trainingfinetuning
Fine-tuningbase
