Quickstart for GLM users

Installation and Configuration

To begin, ensure you have the official OpenAI SDK installed for your language. The API uses a standard header-based authentication scheme. You must set the Authorization header to Bearer your-api-key and configure the base URL to https://api.glmapi.cc/v1. This URL works with any client that supports the OpenAI Chat Completions format.

No special client initialization is required beyond standard configuration. The service acts as a drop-in replacement for existing OpenAI integrations. You can verify your setup by checking the available models endpoint.

First Request

Send a simple text completion request to test connectivity. Use the model identifier uncensored for the primary large language model. The API accepts standard parameters like max_tokens and temperature.

This request returns a direct text response. If you encounter a 401 error, verify your API key. A 402 error indicates insufficient prepaid credit.

Copycurl https://api.glmapi.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
  }'

Python SDK Integration

Use the official Python library to interact with the API. Initialize the client with your base URL and API key. The syntax mirrors the standard OpenAI client structure.

This approach allows you to swap providers without rewriting business logic. The model responds to standard prompt formats. You can control output length and randomness via standard parameters.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.glmapi.cc/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Node SDK Integration

For JavaScript environments, use the Node SDK. Configure the baseUrl to point to our API endpoint. This ensures all requests route correctly to our servers.

The SDK handles retries and response parsing automatically. You can pass standard completion parameters. The response object contains the generated text in the expected location.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.glmapi.cc/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

Streaming Responses

Enable streaming by setting the stream parameter to true. The API returns chunks via Server-Sent Events (SSE). Each chunk contains partial text and usage statistics.

This method reduces perceived latency for long responses. You can process tokens as they arrive. The final chunk includes the total token count for billing.

Copystream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Limits, Errors, and Context

The context window supports 100,000 tokens total, with a maximum output of 32,000 tokens. Requests exceeding the 8 MB body limit will fail. You are limited to 300 requests per minute and 8 concurrent requests per key.

Error 401 means an invalid key. Error 402 indicates no prepaid credit remains. Error 429 signals rate limiting. Credit never expires, and errors do not consume tokens. Privacy is maintained; prompts are not used for training.