Quickstart for Minicpm users

Base URL and Authentication

To use this API, you need an API key and the correct base URL. Our service is fully compatible with the standard OpenAI client libraries. You do not need to install new dependencies or learn a new SDK. Simply point your existing client to our endpoint.

Generate a key on the Get API key page. You can sign in with Google or use an email and password. The key is displayed immediately. Store it securely. Every request must include this key in the Authorization header.

The base URL for all requests is: https://api.minicpm.cc/v1. This URL handles chat completions, model listing, and streaming responses. There are no separate endpoints for embeddings or vision. This is a text-only API.

First Request

Send a standard chat completion request to start generating text. The model ID is always uncensored. This model is an open-weight large language model tuned to answer without content refusals for lawful adult use. It is not GPT, Claude, or any other vendor's model.

Set the model field to uncensored. Provide your messages in the standard array format. The API returns a text response. You can control the output length with max_tokens. If you do not set it, the default max output is 2,048 tokens.

Python SDK Integration

Use the official OpenAI Python library to interact with the API. You only need to configure the base URL and API key. The rest of the library works as expected. This includes support for streaming, function calling, and JSON mode.

Install the library with pip install openai. Initialize the client with your base URL and key. Send messages to the chat completions endpoint. The response object contains the generated text, token usage, and finish reason. You can access these fields directly in your Python code.

Node SDK Integration

The Node.js SDK works identically to the Python version. Install the package and configure the base URL. The client handles authentication and request formatting automatically. This allows you to integrate the API into your backend services quickly.

Pass the base URL and API key to the OpenAI client constructor. Use the chat.completions.create method. The response structure matches the OpenAI standard. You can handle errors, check token usage, and process the content. This approach ensures compatibility with existing codebases that already use OpenAI.

Streaming Responses

Enable streaming by setting stream: true in your request. The API returns a sequence of Server-Sent Events (SSE). Each event contains a chunk of the response. This allows you to display text to the user as it is generated.

The final chunk includes the token usage statistics. This is useful for tracking costs. Streaming reduces the perceived latency for users. It is recommended for chat interfaces. You can parse the events in your client code to build the final response or display tokens in real time.

Limits, Errors, and Context

The model supports a 100,000 token context window. This includes both the prompt and the completion. The maximum output per request is 32,000 tokens. You can adjust the max_tokens parameter to control this.

Rate limits are set to 300 requests per minute per key. You can have 8 concurrent requests. The request body must be under 8 MB. If the key is invalid, you will receive a 401 error. If you have no credit, you will receive a 402 error. If you exceed the rate limit, you will receive a 429 error. Errors and refusals do not consume credit.

cURL

Copycurl https://api.minicpm.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

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.minicpm.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.js

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.minicpm.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

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)

2026-050