Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.12 |
| Output tokens | $0.36 |
Capabilities
VisionMultimodalReasoningFunction CallingTool UseJSON ModeCode Execution
About Qwen2.5 7B
Versatile 7B mid-size model with exceptional code generation and math performance, reaching 83% on MATH benchmark. Supports 128K context and offers multimodal vision-language variants.
Model Specs
Released2024-06-07
Parameters7.61B
Context128K
ArchitectureDecoder Only