GLM 5GLM 5
API Keys

Quick Start

Make your first OpenAI-compatible GLM 5 API request in a few minutes.

OpenAI SDK compatible

Keep your existing OpenAI SDK for the documented Chat Completions subset, then change the API key, base URL, and model. For most new integrations, start with glm-5.3.

OpenAI-compatible API reference, focused for GLM 5

The GLM 5 API uses an OpenAI-compatible Chat Completions interface: send a bearer-authenticated JSON request to the versioned /chat/completions endpoint, provide a model and messages, and read the response from choices and usage.

The reference pages in these docs follow that same structure: request body, message format, response fields, streaming chunks, tool calls, models, errors, limits, and billing. GLM 5 keeps the compatible shape but exposes a curated, predictable model surface:

  • Use https://glm5.app/api/v1 as the base URL.
  • Use a model ID returned by GET /models, such as glm-5.3.
  • Use max_completion_tokens for new code. The legacy max_tokens field still works for existing OpenAI-compatible clients.
  • Use stream: true when you want Server-Sent Events and handle data: [DONE].
  • Use tools and tool_choice for function calling on models that support tools.

Only the parameters documented in this API reference are guaranteed to affect request behavior. For the supported request fields, see Chat Completions.

Base URLhttps://glm5.app/api/v1OpenAI-compatible
Recommended modelglm-5.3Coding, reasoning & agents
Context and outputModel-specificLimits vary by model

Using an OpenAI-compatible client?

Set the base URL to https://glm5.app/api/v1, authenticate with your sk-glm5-... key, and choose a model ID returned by GET /models, such as glm-5.3.

Getting started

Create an API key

Sign in, open API Keys, and create a key for your application. The full key is shown once, so store it in a password manager or secret store.

GLM5_API_KEY=sk-glm5-your-key

Never expose an API key in browser code, public repositories, screenshots, or client-side environment variables.

Choose a model

glm-5.3 is the recommended default for coding, reasoning, agent workflows, and long-form tasks. Use a different model when its price or behavior better fits your application.

GLM-5.3

Recommended GLM model for coding, reasoning, agents, and long-form work.

GLM-5.2

Stable GLM option for coding, reasoning, and tool workflows.

GLM-5

Lower-cost GLM model for general chat and structured tasks.

Choose a calling method

Call the REST endpoint directly or use the official OpenAI SDK. Both use the documented Chat Completions parameters and return the same response shape.

HTTP API

Works in every language and runtime.

OpenAI Python SDK

Use the familiar OpenAI Python client.

OpenAI Node.js SDK

Use the OpenAI package in Node.js or server runtimes.

Make your first request

POSThttps://glm5.app/api/v1/chat/completions

Bearer authentication · JSON request and response

max_completion_tokens is optional. Set it when your application needs a predictable response length; omit it to use the selected model's default. GLM 5 may reserve credits using an internal estimate for billing, but that estimate does not change the requested output limit.

curl https://glm5.app/api/v1/chat/completions \
  -H "Authorization: Bearer $GLM5_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.3",
    "messages": [
      {
        "role": "system",
        "content": "You are a concise technical assistant."
      },
      {
        "role": "user",
        "content": "Give me a three-step API launch checklist."
      }
    ],
    "max_completion_tokens": 1024
  }'

Compatibility scope

GLM 5 implements the documented Chat Completions subset. Extra SDK fields may be accepted, but only the fields listed in this reference are guaranteed to affect request behavior. Check Chat Completions before depending on a parameter.

Keep context costs predictable

Chat Completions is stateless

Every request is billed for all messages you send in that request. If your client resends the complete conversation on every turn, the input grows and the same history is charged again. Keep a bounded history, summarize older turns, and start a new conversation when earlier context is no longer needed.

For predictable billing:

  • Set max_completion_tokens when your workflow needs a predictable output cap.
  • Monitor the usage.prompt_tokens and usage.completion_tokens fields.
  • Do not append unlimited chat history.
  • Handle context-limit errors because supported models can have different limits.
  • Use streaming for responsiveness, not as a way to reduce input-token cost.

Read Context and cost control before connecting an autonomous agent or a long-running chat client.

Explore more

Chat Completions

Request parameters, message roles, responses, and usage.

Models and pricing

Compare model capabilities and credit rates.

Function calling

Connect models to functions and application data.

Errors

Handle authentication, quota, validation, and rate-limit errors.

On this page

OpenAI-compatible API reference, focused for GLM 5
Getting started
Keep context costs predictable
Explore more