Publish time
2025/12/8Model Series
GLMInput type
Output type
Context Window
128,000Max Output Length
2,048Input Price
¥1 / 1M tokensOutput Price
¥3 / 1M tokensGLM-4.6V 是 GLM 系列在多模态方向上的一次重要迭代，它将训练时上下文窗口提升到128k tokens，在视觉理解精度上达到同参数规模 SOTA，并首次在模型架构中将 Function Call（工具调用）能力原生融入视觉模型，打通从「视觉感知」到「可执行行动（Action）」的链路，为真实业务场景中的多模态 Agent 提供统一的技术底座。
Zhinao API routes requests to the best-fit provider and automatically fails over to the one with highest availability.
TTFT
14.16s
Throughput
3.67tps
Uptime
100.00%
Provider Model
bigmodel/glm-4.6v
Supported Parameters
Recent Uptime
Reasoning
-
Supported Response Formats
Request Log Collection
-
Distillable
-
Total Context
128,000
Max Output
2,048
Input Price
¥1 / 1M tokens
Output Price
¥3 / 1M tokens
Compare different providers across Zhinao API
25.00 tok/s
1.01 s
Uptime for z-ai/glm-4.6v across all providers
Zhinao API normalizes requests and responses across providers for you
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.360.cn/v1",
apiKey: process.env.ZHINAO_API_KEY,
});
const response = await client.chat.completions.create({
model: "z-ai/glm-4.6v",
messages: [
{ role: "user", content: "Hello, how are you?" }
],
temperature: 0.7,
max_tokens: 1000,
});
console.log(response.choices[0].message.content);