Zhipu

Z.ai: GLM-5

Chat
z-ai/glm-5

GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading closed-source models. With advanced agentic planning, deep backend reasoning, and iterative self-correction, GLM-5 moves beyond code generation to full-system construction and autonomous execution.

200K context window
128K max output tokens
Released: 2026-02-11
Supported Protocols:OpenAIopenaiAnthropicanthropic
Available Providers:ZhipuZhipuBaiLianAliyun
Capabilities:Function CallingReasoningPrompt CachingWeb Search

Pricing

TypePrice
Input Tokens$1/M
Output Tokens$3.2/M
Cache Read$0.2/M
Web Search$0.005/R

Code Examples

from openai import OpenAI
client = OpenAI(
base_url="https://api.ofox.ai/v1",
api_key="YOUR_OFOX_API_KEY",
)
response = client.chat.completions.create(
model="z-ai/glm-5",
messages=[
{"role": "user", "content": "Hello!"}
],
)
print(response.choices[0].message.content)

Frequently Asked Questions

Z.ai: GLM-5 on Ofox.ai costs $1/M per million input tokens and $3.2/M per million output tokens. Pay-as-you-go, no monthly fees.

Discord

Join our Discord server

Discord