Back to models
GLM 5.3Open weightsAgentic coding

Coding model template

Give the model everything it needs to code.

Structure your task, repository context, success criteria, and execution boundaries before sending it to GLM 5.3.

50%

Coding gain vs. GLM-5.2

Max

Recommended coding effort

Enabled

Required thinking mode

Task configuration

Required coding values

Fields marked Required provide the minimum context for a reliable coding task.

Generated output

Coding prompt template

# Coding task
[Describe the feature, bug, or refactor to complete]

## Technical stack
- Language: TypeScript
- Framework: Next.js

## Repository context
[Add relevant files, architecture notes, and existing behavior]

## Acceptance criteria
[List the tests and observable outcomes that define success]

## Constraints
[Add compatibility, security, performance, and scope boundaries]

Inspect the existing implementation, make the smallest complete change, run relevant checks, and summarize the result.

API request

Ready-to-use values

POST
/v1/ula/chat/completions
{
  "model": "glm-5.3",
  "messages": [
    {
      "role": "system",
      "content": "You are a senior software engineer. Inspect context carefully, implement safely, and verify your work."
    },
    {
      "role": "user",
      "content": "# Coding task\n[Describe the feature, bug, or refactor to complete]\n\n## Technical stack\n- Language: TypeScript\n- Framework: Next.js\n\n## Repository context\n[Add relevant files, architecture notes, and existing behavior]\n\n## Acceptance criteria\n[List the tests and observable outcomes that define success]\n\n## Constraints\n[Add compatibility, security, performance, and scope boundaries]\n\nInspect the existing implementation, make the smallest complete change, run relevant checks, and summarize the result."
    }
  ],
  "thinking": {
    "type": "enabled"
  },
  "reasoning_effort": "max",
  "temperature": 1,
  "top_p": 0.95,
  "max_tokens": 8192,
  "stream": true
}