mixrouter
  1. 智谱
mixrouter
  • mixrouter接口说明
  • 已支持的模型列表
  • 大模型官方文档
  • 已支持的模型列表
    • 语言大模型
      • OpenAI
        • gpt-4
        • gpt-4.1
        • gpt-4o
        • gpt-4o-mini
        • gpt-5
        • gpt-5-chat
        • gpt-5-mini
        • gpt-5-nano
        • gpt-5.1
        • gpt-5.1-chat-latest
        • gpt-5.1-codex(仅支持/v1/responses)
        • gpt-5.2
        • gpt-5.2-chat
        • gpt-5.2-pro(仅支持/v1/responses)
        • gpt-oss-120b
        • o1
        • o3
        • o3-mini
        • o3-deep-research
        • o3-pro
        • o4-mini
        • o4-mini-deep-research
      • Google
        • gemini-2.0-flash
        • gemini-2.5-computer-use-preview-10-2025
        • gemini-2.5-flash
        • gemini-2.5-flash-lite
        • gemini-2.5-flash-lite-preview
        • gemini-2.5-pro
        • gemini-3-flash-preview
        • gemini-3-pro-preview
        • gemini-robotics-er-1.5-preview
      • Anthropic
        • 通用接口
        • claude-opus-4-5-20251101
        • claude-opus-4-20250514
        • claude-sonnet-4-20250514
        • claude-sonnet-4-5-20250929
      • DeepSeek
        • deepseek-chat
        • deepseek-reasoner
      • MiniMax
        • abab6.5s-chat
        • minimax-m2
      • Moonshot
        • kimi-k2
        • kimi-k2-0711-preview
        • kimi-k2-0905
        • kimi-k2-instruct
        • kimi-k2-thinking
        • moonshot-v1-128k
        • moonshot-v1-32k
        • moonshot-v1-8k
        • moonshot-v1-128k-vision-preview
        • moonshot-v1-32k-vision-preview
        • moonshot-v1-8k-vision-preview
      • xAI
        • grok-4
        • grok-4-1-fast-non-reasoning
        • grok-4-1-fast-reasoning
      • 字节跳动
        • 通用接口
      • 智谱
        • glm-4-plus
        • glm-4.5
        • glm-4.6
        • glm-4.7
      • 阿里巴巴
        • qwen-max
        • qwen-max-2025-01-25
        • qwen-max-latest
        • qwen-plus
        • qwen-plus-latest
        • qwen-turbo
        • qwen2.5-7b-instruct
        • qwen2.5-32b-instruct
        • qwen2.5-72b-instruct
        • qwen3-coder-plus
        • qwen3-coder-plus-2025-07-22
        • qwen3-max
        • qwen3-max-preview
        • qwen3-235b-a22b
        • qwen3-235b-a22b-instruct-2507
        • qwen3-235b-a22b-thinking-2507
        • qwen3-8b
        • qwen3-coder-30b-a3b-instruct
        • qwen3-next-80b-a3b-instruct
        • qwen3-next-80b-a3b-thinking
        • qwen-vl-max(视觉理解)
        • qwen-vl-plus(视觉理解)
        • qwen3-vl-235b-a22b-instruct(视觉理解)
        • qwen3-vl-235b-a22b-thinking(视觉理解)
      • 百度
        • ernie-x1-32k
      • 腾讯
        • hunyuan-t1-latest
      • 讯飞
        • SparkDesk-v4.0
      • 蚂蚁
        • Ling-1T
        • Ring-1T
      • 阶跃星辰
        • step-3
    • 图片生成
      • 通用接口
        • 图片生成
        • 图片编辑
      • OpenAI
        • gpt-image系列图片生成
        • gpt-image系列图片编辑
        • dall-e-3图片生成
      • Google
        • gemini-2.5-flash-image
        • gemini-2.5-flash-image-preview
        • gemini-3-pro-image-preview
      • Anthropic
      • BFL
        • flux-1-kontext-pro
      • ImagineArt
        • imagineart-1.5-preview
    • 音视频处理
      • OpenAI
        • gpt-4o-audio-preview
        • gpt-audio
      • 阿里巴巴
        • qwen3-tts-flash
      • Elevenlabs
        • eleven_v3
      • MiniMax
        • 通用接口
    • 视频生成
      • Vidu
        • vidu-2.0-img2video
        • viduq2-pro提交图生视频任务
      • 字节跳动
        • 提交图生视频生成任务
        • 提交文生视频生成任务
      • 快手
        • 提交图生视频任务
        • 提交文生视频任务
      • 腾讯
        • hunyuan-video-v1.5
      • 海螺
        • 提交图生视频任务
        • 提交文生视频任务
      • sora
        • sora-2
        • sora-2-pro
      • Google
        • veo-3.1-generate-preview
        • veo-3.1-fast-generate-preview
      • 阿里巴巴
        • wan2.6-i2v
        • wan2.6-t2v
      • pixverse
        • pixverse-v5.5-t2v
        • pixverse-v5.5-i2v
    • 多模态模型
      • 智谱
        • glm-4.5v
          POST
        • glm-4.6v
          POST
      • 阿里巴巴
        • qwen2.5-omni-7b
        • qwen2.5-vl-72b-instruct
        • qwen3-omni-flash-2025-12-01
      • 日日新
        • SenseNova-V6-Pro
    • Realtime
      • OpenAI
        • gpt-4o-mini-realtime-preview
        • gpt-4o-realtime-preview
    • 向量化
      • OpenAI
        • text-embedding-3-large
        • text-embedding-3-small
        • text-embedding-ada-002
        • text-embedding-v1
  • 已支持的搜索服务
    • serper
      • get方式
      • post方式
  • gemini
    • openai格式
      • gemini-开启thinking
      • chat/completions
    • google原生格式
      • google格式
      • gemini-robotics-er-1.5-preview
  • anthropic
    • anthropic格式
      • tools调用
      • thinking
      • image理解
      • code_execution
    • openai格式
    • openai格式
      POST
    • anthropic格式
      POST
  • openai
    • gpt-5.2
      POST
    • openai格式
      POST
    • responses
      POST
  • deepseek
    • chat/completions
  • qwen
    • chat/completions(开启thinking)
    • 流式/chat/completions
    • qwen提交图生视频任务
  • 豆包
    • chat/completions
    • qwen提交文生视频任务
    • 获取视频生成任务结果
  • 获取异步任务结果
    GET
  1. 智谱

glm-4.6v

POST
https://api.mixrouter.com/v1/chat/completions

Request

Authorization
Provide your bearer token in the
Authorization
header when making requests to protected resources.
Example:
Authorization: Bearer ********************
Body Params application/jsonRequired

Example
{
  "model": "glm-4.6v",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "video_url",
          "video_url": {
            "url": "https://cdn.bigmodel.cn/agent-demos/lark/113123.mov"
          }
        },
        {
          "type": "text",
          "text": "What are the video show about?"
        }
      ]
    }
  ],
  "thinking": {
    "type": "enabled"
  }
}

Request Code Samples

Shell
JavaScript
Java
Swift
Go
PHP
Python
HTTP
C
C#
Objective-C
Ruby
OCaml
Dart
R
Request Request Example
Shell
JavaScript
Java
Swift
curl --location --request POST 'https://api.mixrouter.com/v1/chat/completions' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data-raw '{
  "model": "glm-4.6v",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "video_url",
          "video_url": {
            "url": "https://cdn.bigmodel.cn/agent-demos/lark/113123.mov"
          }
        },
        {
          "type": "text",
          "text": "What are the video show about?"
        }
      ]
    }
  ],
  "thinking": {
    "type": "enabled"
  }
}'

Responses

🟢200OK
application/json
Body

Example
{
    "choices": [
        {
            "finish_reason": "stop",
            "index": 0,
            "message": {
                "content": "\nThe video shows a user performing a web search for the Chinese AI company \"智谱\" (Zhipu AI) on Google and then navigating to its official website.\n\nHere is a step-by-step breakdown of the actions shown in the frames:\n\n1.  The video begins with a user on the Google homepage.\n2.  The user types the Chinese characters \"智谱\" (the name of the company Zhipu AI) into the Google search bar.\n3.  The user clicks the \"Google Search\" button to perform the search.\n4.  The search results page loads, displaying links related to Zhipu AI, including its official website.\n5.  The user clicks on the first search result, which is the link to the Zhipu AI website (www.zhipuai.cn).\n6.  The browser then loads and displays the homepage of the Zhipu AI platform, titled \"Z.ai GLM Large Model Open Platform\".",
                "reasoning_content": "Here is a thinking process to arrive at the answer:\n\n1.  **Analyze the Request:** The user wants to know what the provided video (represented by a series of still frames) is about. I need to examine the sequence of images to understand the actions and context.\n\n2.  **Examine the Sequence of Frames:**\n    *   **Frames 1-3:** The video starts with a user on the Google homepage. The search bar is empty.\n    *   **Frame 4:** The user has typed the Chinese characters \"智谱\" into the Google search bar. \"智谱\" is the name of a Chinese AI company (Zhipu AI).\n    *   **Frame 5:** The user clicks the \"Google Search\" button.\n    *   **Frames 6-7:** The page shows a loading screen with a spinner and the text \"Searching...\".\n    *   **Frames 8-9:** The search results page is displayed. The search query \"智谱\" is still in the bar. The results show several links related to \"智谱\" (Zhipu AI), including its official website (www.zhipuai.cn), its chatbot (ChatGLM), and its AI platform. This confirms the user is searching for information about the Zhipu AI company.\n    *   **Frame 10:** The user clicks on the first search result, which is the link to the official Zhipu AI website (www.zhipuai.cn).\n    *   **Frames 11-12:** The browser navigates to the Zhipu AI website. The page loads and displays the homepage for \"Z.ai GLM Large Model Open Platform\".\n\n3.  **Synthesize the Information:** The video shows a complete sequence of actions: a user performing a web search on Google for \"智谱\" (Zhipu AI) and then clicking on a search result to navigate to the official website of Zhipu AI. The website is an open platform for large language models.\n\n4.  **Formulate the Answer:** I will structure the answer to first give a concise summary and then provide a more detailed, step-by-step description of the events shown in the video frames. This provides both a quick answer and the supporting evidence.\n\n    *   **Summary:** The video demonstrates a user searching for \"Zhipu AI\" on Google and visiting its official website.\n    *   **Detailed Steps:**\n        *   Start at the Google homepage.\n        *   Type \"智谱\" (Zhipu) into the search bar.\n        *   Initiate the search.\n        *   View the search results for Zhipu AI.\n        *   Click on the official Zhipu AI website link.\n        *   The browser loads and displays the homepage of the Zhipu AI platform.\n\n5.  **Final Review:** The answer is clear, accurate, and directly based on the visual evidence provided in the frames. It correctly identifies the subject of the search (\"智谱\" / Zhipu AI) and the outcome (visiting their website). The language is appropriate and the structure is logical.",
                "role": "assistant"
            }
        }
    ],
    "created": 1767002639,
    "id": "2025122918030760906d9f5858403d",
    "model": "glm-4.6v",
    "object": "chat.completion",
    "request_id": "2025122918030760906d9f5858403d",
    "usage": {
        "completion_tokens": 838,
        "prompt_tokens": 72255,
        "prompt_tokens_details": {
            "cached_tokens": 4
        },
        "total_tokens": 73093
    }
}
Modified at 2025-12-31 06:43:37
Previous
glm-4.5v
Next
qwen2.5-omni-7b
Built with