Mini cpm API documentation

Authentication and Base URL

Start every request with your API key and the correct base URL. We use standard OpenAI headers for compatibility. Your key grants access to the uncensored model immediately. The base URL is HTTPS://api.cpmmini.com/v1. Use the header Authorization: Bearer . Keep your key secure. It identifies your prepaid credit account. No subscription fees apply here. Just pay per token used.

First Request

Send your first message to the chat completions endpoint. This confirms your key works and credits deduct correctly. The uncensored model responds without typical refusals. Use curl for a quick test. Replace YOUR_API_KEY with your actual key from the dashboard. This step verifies connectivity and latency. Errors like 401 indicate an invalid key. Check your account dashboard if it fails. The response returns the generated text.

Python SDK Integration

Use the official OpenAI Python library for programmatic access. Set the base URL to our endpoint. This ensures all requests route to our uncensored model. Install the library via pip. Pass your API key in the client initialization. Request the model uncensored. The SDK handles retries and JSON parsing. This approach simplifies integration into your existing bots. It works with async loops too. Check your credit balance after the call.

Node SDK Setup

Integrate with Node.js using the npm package. Configure the base URL to point to our API. This maintains compatibility with OpenAI standards. Install the dependency in your project. Initialize the client with your key. Call the chat completions method. The response object contains the generated text. Handle errors gracefully in your application. This setup supports both CommonJS and ES modules. It is ideal for server-side chatbots.

Streaming Responses

Stream tokens for real-time user experiences. Enable streaming in your request parameters. The API sends chunks as they generate. This reduces perceived latency for users. Use the SSE endpoint for continuous data. Parse each chunk to build the final message. This feature works with both Python and Node SDKs. It is essential for chat interfaces. Monitor the token usage in the final chunk. Your credit deducts based on total tokens sent.

Limits, Errors, and Context

Watch your rate limits and credit status. You get 300 requests per minute. Only eight concurrent requests per key are allowed. A 429 error means you hit the limit. A 402 error indicates insufficient credit. Top up with crypto to continue. The context window supports 100,000 tokens. This allows long conversations without losing history. Errors and refusals do not cost credits. Your prepaid credit never expires. Manage your keys in the dashboard.

cURL

Copycurl https://api.cpmmini.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Send test message"}]
  }'

Python

Copyfrom openai import OpenAI

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

Node.js

Copyimport OpenAI from "openai";

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

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)