Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.20 |
| Output tokens | $0.60 |
Capabilities
VisionMultimodalReasoningFunction CallingTool UseJSON ModeCode Execution
About Qwen2.5 72B
Flagship 72B model leading open-source benchmarks with 86.1% MMLU and exceptional performance in math, coding, and reasoning. Outperforms some proprietary models on specific tasks.
Model Specs
Released2024-06-07
Parameters72.7B
Context128K
ArchitectureDecoder Only