API Documentation for Developers

Authentication & Base URL

Your API key authenticates every request. Pass it in the Authorization header as a bearer token. The base URL is https://api.keyapiglm.com/v1. This endpoint works with any OpenAI-compatible client. You can replace the standard OpenAI base URL in your code. Our service handles the routing to our uncensored model.

First Request

Send a POST request to /v1/chat/completions. Include your model ID and prompt. The response contains the generated text. You can start with a simple text completion. Our API returns raw tokens without extra formatting.

Copycurl https://api.keyapiglm.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Verify endpoint latency for high traffic loads"}]
  }'

Verify your key works immediately. Check the response for the choices array. Each choice has a message with your generated content. Errors return standard HTTP codes.

Python SDK Integration

Install the openai package. Set the base URL to our endpoint. Initialize the client with your API key. Call the chat.completions.create method. Pass the model ID uncensored. This works with existing OpenAI code. No extra wrappers needed.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.keyapiglm.com/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)

Handle the response object. Extract the text from the first choice. Your script runs smoothly. Debugging is easy with standard logging.

Node SDK Setup

Import the OpenAI client in Node. Configure the base URL. Pass your key to the constructor. Call the chat completion function. Use the same model ID. This approach saves time. You reuse familiar patterns. The API responds quickly.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.keyapiglm.com/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);

Log the generated text. Check for errors in the catch block. Your Node app integrates seamlessly. No custom HTTP clients required. Standard JSON responses arrive as expected.

Streaming Responses (SSE)

Enable streaming by setting stream: true. The API sends Server-Sent Events. Each chunk contains partial text. Concatenate these chunks for the full response. This reduces perceived latency. Users see text appear instantly.

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)

Handle each chunk in your event loop. The final chunk includes token usage. Stop streaming when the model finishes. This method works with any SSE client. Your UI updates in real time.

Limits & Errors

Rate limits are 300 requests per minute. Concurrent requests max out at 8 per key. Request bodies cannot exceed 8 MB. Context window is 100,000 tokens. Errors return standard codes. Use 401 for invalid keys. Use 402 for insufficient credit. Use 429 for rate limits. Check the response body for details. Retry logic handles temporary issues. Your integration stays stable.