Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.18 |
| Output tokens | $0.54 |
Capabilities
VisionMultimodalReasoningFunction CallingTool UseJSON ModeCode Execution
About Qwen2.5 72B Instruct
Instruction-optimized flagship variant for demanding production applications requiring high-accuracy complex problem-solving across industries.
Get Started
Model Specs
Released2024-06-07
Parameters72.7B
Context128K
ArchitectureDecoder Only