TheRouter.aiTheRouter.ai
返回模型列表

GLM 4.6V Flash

zhipuzhipu/glm-4.6v-flash

API 使用指南

视觉对话补全（图像 / 视频 / PDF 输入）

GLM-4.6V-Flash 通过 api.therouter.ai 的标准 OpenAI /v1/chat/completions 端点访问。与 GPT-4o 一样，以 image_url 内容块传入图像。支持在单次请求中混合传入文本、图像、视频和 PDF 输入。函数调用通过标准 tools / tool_choice 参数实现——图像和视觉工具输出原生处理。API 完全免费，不消耗额度。

cURL
# Image understanding — free via TheRouter
curl https://api.therouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zhipu/glm-4.6v-flash",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "image_url",
            "image_url": { "url": "https://therouter.ai/assets/vision-sample.png" }
          },
          {
            "type": "text",
            "text": "Summarise the key trends shown in this chart."
          }
        ]
      }
    ],
    "max_tokens": 1024
  }'

多模态函数调用

GLM-4.6V-Flash 是首款支持原生多模态函数调用的 GLM 视觉模型。以标准 OpenAI tools 格式定义工具；模型可将图像直接作为工具参数传入，并无需将视觉工具输出（图表、截图、搜索结果）转换为文本即可解读。

cURL
curl https://api.therouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zhipu/glm-4.6v-flash",
    "messages": [
      {
        "role": "user",
        "content": [
          { "type": "image_url", "image_url": { "url": "https://therouter.ai/assets/vision-sample.png" } },
          { "type": "text", "text": "Is the server status healthy? Trigger an alert if not." }
        ]
      }
    ],
    "tools": [{
      "type": "function",
      "function": {
        "name": "trigger_alert",
        "description": "Trigger an ops alert",
        "parameters": {
          "type": "object",
          "properties": {
            "service_name": { "type": "string" },
            "severity": { "type": "string", "enum": ["low","medium","high"] },
            "message": { "type": "string" }
          },
          "required": ["service_name","severity","message"]
        }
      }
    }],
    "tool_choice": "auto",
    "max_tokens": 512
  }'
事实档案 — 本页每条断言可在此回溯来源
来源URL采集于
发布日期huggingface.co ↗2026-06-09已核实
参数量huggingface.co ↗2026-06-09已核实
架构huggingface.co ↗2026-06-09已核实
上下文窗口docs.z.ai ↗2026-06-09已核实
最大输出 token 数huggingface.co ↗2026-06-09已核实
输入模态docs.z.ai ↗2026-06-09已核实
输出模态docs.z.ai ↗2026-06-09已核实
定价docs.z.ai ↗2026-06-09已核实
原生函数调用huggingface.co ↗2026-06-09已核实
训练数据截止——未知
许可huggingface.co ↗2026-06-09待核实
本地部署支持huggingface.co ↗2026-06-09已核实
推荐解码参数huggingface.co ↗2026-06-09已核实
Z.ai 发布 GLM-4.6V 系列，首次集成原生多模态函数调用huggingface.co ↗2026-06-09已核实
帮助与联系