Maas-Model-platform/backend/parsed_json/qwen-plus.json

{
  "model_code": "qwen-plus",
  "model_intro": "Qwen3系列Plus模型，实现思考模式和非思考模式的有效融合，可在对话中切换模式。推理能力显著超过QwQ，通用能力显著超过Qwen2.5-Plus，达到同规模业界SOTA水平。",
  "model_tags": ["Qwen3", "深度思考", "文本生成"],
  "model_capabilities": {
    "input_modalities": ["text"],
    "output_modalities": ["text"],
    "features": {
      "model_experience": true,
      "function_calling": true,
      "structured_output": true,
      "web_search": true,
      "prefix_continuation": true,
      "cache": true,
      "batch_inference": true,
      "model_tuning": false
    }
  },
  "model_pricing": [
    {
      "input_range": "输入<=128K",
      "unit": "元/千tokens",
      "input": 0.0008,
      "input_thinking": 0.0008,
      "input_cache_hit": 0.00016,
      "input_cache_hit_thinking": 0.00016,
      "input_batch": 0.0004,
      "input_batch_thinking": 0.0004,
      "explicit_cache_create": 0.001,
      "explicit_cache_hit": 0.00008,
      "explicit_cache_create_thinking": 0.001,
      "explicit_cache_hit_thinking": 0.00008,
      "output": 0.002,
      "output_thinking": 0.008,
      "output_batch": 0.001,
      "output_thinking_batch": 0.004
    },
    {
      "input_range": "128K<输入<=256K",
      "unit": "元/千tokens",
      "input": 0.0024,
      "input_thinking": 0.0024,
      "input_cache_hit": 0.00048,
      "input_cache_hit_thinking": 0.00048,
      "input_batch": 0.0012,
      "input_batch_thinking": 0.0012,
      "explicit_cache_create": 0.003,
      "explicit_cache_hit": 0.00024,
      "explicit_cache_create_thinking": 0.003,
      "explicit_cache_hit_thinking": 0.00024,
      "output": 0.02,
      "output_thinking": 0.024,
      "output_batch": 0.01,
      "output_thinking_batch": 0.012
    },
    {
      "input_range": "256K<输入<=1M",
      "unit": "元/千tokens",
      "input": 0.0048,
      "input_thinking": 0.0048,
      "input_cache_hit": 0.00096,
      "input_cache_hit_thinking": 0.00096,
      "input_batch": 0.0024,
      "input_batch_thinking": 0.0024,
      "explicit_cache_create": 0.006,
      "explicit_cache_hit": 0.00048,
      "explicit_cache_create_thinking": 0.006,
      "explicit_cache_hit_thinking": 0.00048,
      "output": 0.048,
      "output_thinking": 0.064,
      "output_batch": 0.024,
      "output_thinking_batch": 0.032
    }
  ],
  "model_limits": {
    "max_input_length": "997K",
    "max_input_length_thinking": "995K",
    "max_output_length": "32K",
    "max_output_length_thinking": "32K",
    "max_thinking_length": "80K",
    "rpm": 15000,
    "tpm": 5000000,
    "context_length": "1M"
  },
  "api_examples": {
    "curl": [
      "curl -X POST https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions \\\n-H \"Authorization: Bearer $DASHSCOPE_API_KEY\" \\\n-H \"Content-Type: application/json\" \\\n-d '{\n    \"model\": \"qwen-plus\",\n    \"messages\": [\n        {\n            \"role\": \"user\", \n            \"content\": \"你是谁\"\n        }\n    ],\n    \"stream\": true,\n    \"enable_thinking\": true\n}'"
    ]
  }
}