qwen-vl-ocr.json 1.5 KB

1234567891011121314151617181920212223242526272829303132333435363738
  1. {
  2. "model_code": "qwen-vl-ocr",
  3. "model_intro": "通义千问VL-OCR(qwen-vl-ocr),即基于Qwen-VL训练的OCR识别大模型。通过统一模型的方式聚合多种图文识别、解析、处理类任务,提供强大的图文识别能力。",
  4. "model_tags": ["视觉理解"],
  5. "model_capabilities": {
  6. "input_modalities": ["text", "image"],
  7. "output_modalities": ["text"],
  8. "features": {
  9. "model_experience": true,
  10. "function_calling": false,
  11. "structured_output": false,
  12. "web_search": false,
  13. "prefix_continuation": false,
  14. "cache": false,
  15. "batch_inference": false,
  16. "model_tuning": false
  17. }
  18. },
  19. "model_pricing": {
  20. "unit": "元/千tokens",
  21. "input": 0.005,
  22. "input_batch": 0.0025,
  23. "output": 0.005,
  24. "output_batch": 0.0025
  25. },
  26. "model_limits": {
  27. "max_input_length": "30K",
  28. "max_output_length": "4K",
  29. "rpm": 600,
  30. "tpm": 6000000,
  31. "context_length": "34K"
  32. },
  33. "api_examples": {
  34. "curl": [
  35. "curl --location 'https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions' \\\n--header \"Authorization: Bearer $DASHSCOPE_API_KEY\" \\\n--header 'Content-Type: application/json' \\\n--data '{\n \"model\": \"qwen-vl-ocr\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": [\n {\"type\": \"image_url\", \"image_url\": {\"url\": \"https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20241108/ctdzex/biaozhun.jpg\"}},\n {\"type\": \"text\", \"text\": \"请仅输出图像中的文本内容。\"}\n ]\n }]\n}'"
  36. ]
  37. }
  38. }