1. 智谱
mixrouter
  • 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
          • embedding
          • 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-v4-pro
          • deepseek-chat
          • deepseek-reasoner
        • MiniMax
          • minimax-m2.5
          • 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-5
            POST
          • glm-5.3-flash
            POST
          • glm-4-plus
            POST
          • glm-4.5
            POST
          • glm-4.6
            POST
          • glm-4.7
            POST
        • 阿里巴巴
          • qwen3.5-122b-a10b(多模态)
          • qwen3.5-397b-a17b(多模态)
          • qwen3.6-27b
          • qwen3.6-35b-a3b
          • qwen3.5-35b-a3b
          • 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
          • hy3-preview
          • 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-3-pro-image-preview(google格式)
          • 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
          • glm-4.6v
        • 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
        • gemini-3.5-flash
      • google原生格式
        • google格式
        • gemini-3.5-flash
        • 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
      • anthropic格式
    • openai
      • gpt-5.2
      • openai格式
      • responses
    • deepseek
      • chat/completions
    • qwen
      • chat/completions(开启thinking)
      • 流式/chat/completions
      • qwen提交图生视频任务
    • 豆包
      • 豆包端到端实时语音
      • 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
  • mixrouter
    • qwen3.5-122b-a10b(多模态)
  1. 智谱

glm-5.3-flash

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-5.3-flash",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "image_url",
          "image_url": {
            "url": "https://cdn.bigmodel.cn/static/logo/register.png"
          }
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://cdn.bigmodel.cn/static/logo/api-key.png"
          }
        },
        {
          "type": "text",
          "text": "What are the pics talk about"
        }
      ]
    }
  ],
  "thinking": {
    "type": "enabled"
  },
  "reasoning_effort": "max",
  "max_tokens": 65536,
  "temperature": 1.0
}

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 'https://api.mixrouter.com/v1/chat/completions' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
  "model": "glm-5.3-flash",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "image_url",
          "image_url": {
            "url": "https://cdn.bigmodel.cn/static/logo/register.png"
          }
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://cdn.bigmodel.cn/static/logo/api-key.png"
          }
        },
        {
          "type": "text",
          "text": "What are the pics talk about"
        }
      ]
    }
  ],
  "thinking": {
    "type": "enabled"
  },
  "reasoning_effort": "max",
  "max_tokens": 65536,
  "temperature": 1.0
}'

Responses

🟢200OK
application/json
Bodyapplication/json

Example
{
    "id": "20260828230636a642f734fff9442d",
    "model": "glm-5",
    "object": "chat.completion",
    "created": 1787929622,
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "# Overview of the Two Images\n\nThese two screenshots show the **onboarding process for the BigModel platform** (智谱AI / Zhipu AI's open platform, the company behind GLM models).\n\n## Image 1: Login/Registration Modal\nA sign-up dialog with the title **\"完成登录/注册,开启开发之旅\"** (\"Complete login/registration, start your development journey\"). Key elements:\n\n- **Promotion**: New users get a free **20 million (2000万) tokens** trial package\n- **Three login methods**:\n  - 📱 **手机号登录** (Phone number login) — currently selected, with +86 country code and SMS verification code\n  - 👤 **账号登录** (Account login)\n  - **微信扫码登录** (WeChat QR code login) — QR code shown on the right\n- A blue **\"登录 / 注册\"** (Login/Register) button\n- Agreement checkbox for **《用户协议》** (User Agreement) and **《隐私政策》** (Privacy Policy)\n- An additional **CCF会员授权登录** (CCF member authorized login) option\n\n## Image 2: BigModel Console — API Keys Page\nAfter logging in, this shows the **API key management page**:\n\n- Top navigation: Console, Application Space, Experience Center, Developer Docs\n- A warning notice advising users **not to share API keys**, and explaining the new key format `{id}.{secret}`\n- A table listing an existing API key (default project), with creation date (2025-04-17), last usage (2025-07-09), and owner ID\n- A blue **\"添加新的API Key\"** (\"Add new API Key\") button\n\n## In Short\nTogether, these images depict a **step-by-step guide**: register an account on the BigModel platform → go to the console → create/manage your **API Key**, which is required to call Zhipu's GLM models via API in your own applications.",
                "reasoning_content": "The user is asking about two images. Let me analyze them.\n\nImage 1: Shows a login/registration modal dialog in Chinese. The title says \"完成登录/注册,开启开发之旅\" (Complete login/registration, start your development journey). It mentions new users get a free 20 million tokens experience package (新用户免费赠送专享 2000万 tokens体验包). There are options:\n- 手机号登录 (Phone number login) - active tab\n- 账号登录 (Account login)\n- 微信扫码登录 (WeChat QR code scan login)\n- Phone number input with +86 country code\n- Verification code input with \"获取验证码\" (Get verification code) button\n- Blue \"登录 / 注册\" (Login/Register) button\n- Checkbox agreeing to 《用户协议》(User Agreement) and 《隐私政策》(Privacy Policy)\n- CCF会员授权登录 (CCF member authorization login) option\n- The background appears to be from an AI/tech website (blurred)\n\nImage 2: Shows the BigModel platform (智谱AI's open platform - Zhipu AI, which is the company behind GLM models). This is the API keys management page in the console:\n- Top navigation: 控制台 (Console), 应用空间 (Application Space), 体验中心 (Experience Center), 开发文档 (Developer Documentation)\n- Left sidebar: 设置 (Settings), 项目管理 (Project Management), API keys (selected), 速率限制 (Rate Limits), 用户权益 (User Benefits), 安全管理 (Security Management), 工单记录 (Ticket Records)\n- Main content: API keys page with a notice (提示) warning users not to share API keys and explaining the new format {id}.{secret}\n- Table showing an API key entry: 名称 (Name): 默认项目(144555) (Default project), API key: a6af...crTz, 创建时间 (Created): 2025-04-17 10:22:09, 上次使用时间 (Last used): 2025-07-09, 所属人 (Owner): 43621709087144555\n- \"添加新的API Key\" (Add new API Key) button\n\nSo these two images together show the process of:\n1. Registering/logging into the BigModel (Zhipu AI) platform\n2. Managing API keys in the console after login\n\nThis is likely a tutorial or documentation showing how to get started with the BigModel platform (Zhipu AI's GLM models API).\n\nI should explain this clearly and maybe note the workflow they represent. I should respond in English since the question was in English, though I can include Chinese translations."
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 10129,
        "completion_tokens": 976,
        "total_tokens": 11105,
        "prompt_tokens_details": {
            "cached_tokens": 0,
            "text_tokens": 0,
            "audio_tokens": 0,
            "image_tokens": 0,
            "video_tokens": 0
        },
        "completion_tokens_details": {
            "text_tokens": 0,
            "audio_tokens": 0,
            "image_tokens": 0,
            "reasoning_tokens": 557
        },
        "output_tokens_details": {
            "text_tokens": 0,
            "audio_tokens": 0,
            "image_tokens": 0,
            "reasoning_tokens": 0
        },
        "input_tokens": 0,
        "output_tokens": 0,
        "input_tokens_details": null,
        "claude_cache_creation_5_m_tokens": 0,
        "claude_cache_creation_1_h_tokens": 0
    }
}
Modified at 2026-08-28 15:07:50
Previous
glm-5
Next
glm-4-plus
Built with