GLM-5 is Zhipu AI's most capable foundation model — 745 billion parameters, 202K context, and frontier-level reasoning in a single unified architecture.
Capabilities
Chain complex inferences across mathematical proofs, scientific analysis, and strategic planning. Enhanced System 2 thinking for problems that require depth, not shortcuts.
Opus-level code generation across languages. Full-stack applications, terminal workflows, and SWE-bench verified performance.
async function solve(task) {
const plan = await reason(task);
return execute(plan);
}
Process images, documents, and text in a unified pipeline. Cross-modal understanding as a first-class capability.
Plan, execute, and adapt through multi-step workflows. AutoGLM-powered autonomous task completion.
Narratives, documents, and long-form content with natural conversational style.
5.9% sparsity MoE for cost-efficient inference. Deploy anywhere.
Architecture
Performance
Scores represent publicly reported evaluation results. Visit z.ai for the latest data.
Get Started
Available via API, open-weight download, or local deployment with the frameworks you already use.
from zhipuai import ZhipuAI
client = ZhipuAI(api_key="your-key")
response = client.chat.completions.create(
model="glm-5",
messages=[{
"role": "user",
"content": "Hello, GLM-5!"
}]
)
print(response.choices[0].message.content)