Strengths
- 1M-token context, 128K output
- Function calling with tool streaming
- Thinking effort low, high or max
- Published weights
Best For
- Coding agents
- Long agentic tasks
- Code security review
Run It in EDDI
The fastest route is the Manager: open the agent wizard or the Platform Operator and pick the provider and model. To configure it yourself, follow these steps for the provider you want.
Z.ai · type: "zhipu"
Model ids: glm-5.3, glm-5.3-flash, glm-5.3-flashx, glm-5.2
1. Store the credential
Add the provider's API key to the Secrets Vault in the Manager, or with PUT /secretstore/secrets/default/zhipu-key, under the name used below. Configurations reference it as ${vault:…}, so the key never appears in plain text.
${vault:zhipu-key}2. Configure the LLM task
Use this as the langchain.json of the agent's workflow, or paste the parameters into the LLM editor in the Manager.
{
"tasks": [
{
"actions": [
"send_message"
],
"id": "chat",
"type": "zhipu",
"parameters": {
"apiKey": "${vault:zhipu-key}",
"modelName": "glm-5.3",
"systemMessage": "You are a helpful assistant",
"addToOutput": "true"
}
}
]
}Or create the whole agent in one call
setup_agent writes the rules, LLM configuration and workflow, then deploys the agent. Call it over MCP or POST /administration/agents/setup.
setup_agent(
agentName: "My glm-5.3 agent",
systemPrompt: "You are a helpful assistant.",
provider: "zhipu",
model: "glm-5.3",
apiKey: "${vault:zhipu-key}"
)Notes for EDDI
- This provider requires the model's reasoning to be sent back during tool loops. EDDI's preset does it for you: leave
returnThinkingandsendThinkingat their defaults.
Related Models
Sources
The facts on this page come from the vendor's documentation, checked on 2026-09-30. Models change quickly, so confirm limits with the vendor before you rely on them. Prices are not listed here: see the vendor's pricing page.