MiniMax API: First request in five minutes

Install the OpenAI SDK

Start by installing the official OpenAI SDK for your preferred language. The library handles request formatting and streaming automatically. Ensure you have Python 3.8+ or Node.js 18+ installed. Run pip install openai for Python or npm install openai for Node. The SDK simplifies interaction with the /v1/chat/completions endpoint. It manages headers, retries, and SSE parsing so you can focus on the prompt. This works because our API follows the OpenAI chat completions standard. You do not need a custom client library. Standard SDK methods map directly to our endpoints. This reduces integration time and leverages existing developer knowledge.

Configure Your Base URL & Key

Set your API key and base URL in your environment variables. Our base URL is https://api.minimaxapikey.com/v1. This allows you to use standard OpenAI clients without modification. Create an account to generate your key. The key is shown immediately after signup. No card is needed for the trial. Store the key securely. Pass it as a header or environment variable. The SDK uses OPENAI_API_KEY by default. You can override the base URL to point to our servers. This ensures all requests go to the uncensored model. Verify your key works with a simple ping. This step prevents authentication errors later.

Send a Basic Chat Completion

Make your first request to generate text. Use the POST method on /v1/chat/completions. Specify the model as uncensored. Pass a message array with a user prompt. The API returns a completion token. This is the core text generation feature. It supports 64k context window. You can send long prompts or conversation history. The response includes the generated text and token usage. This is ideal for creative writing or unrestricted dialogue. Ensure the content is lawful. The model does not refuse adult topics. It only blocks sexual content involving minors. Start simple to verify connectivity.

Enable Streaming (SSE)

For real-time output, enable streaming. Set the stream parameter to true. The API returns Server-Sent Events (SSE). Each chunk contains part of the response. This reduces perceived latency. Users see text appear as it is generated. The SDK handles chunk parsing automatically. You can display text incrementally in a UI. This is crucial for chat interfaces. Streaming works with all model responses. It does not affect token counting. Each chunk includes usage data at the end. Use this for better user experience. It feels more responsive than waiting for the full response. Configure your client to buffer chunks correctly.

Use Tool/Function Calling

Support structured outputs with function calling. Define tools in the request body. The model can call functions based on the prompt. This enables integration with external systems. Pass tool definitions and user messages. The response includes a tool call object. Execute the function and feed results back. This works with standard OpenAI SDKs. It allows complex workflows. You can build agents or assistants. The model maintains context across calls. This is powerful for automation. Ensure your tool definitions are precise. The API handles the routing of tool outputs. It keeps the conversation coherent. Use this for dynamic content generation.

Check Available Models

Verify the model list via GET /v1/models. This endpoint returns available models. Our API serves one model: uncensored. It is an open-weight model. It is not GPT, Claude, or Gemini. The response confirms the model ID. Use this to debug client configurations. Ensure your code targets the correct model. The endpoint is fast and reliable. It returns JSON data. You can parse this for UI displays. It confirms your API key is valid. Use this for automated health checks. It is part of the standard OpenAI spec. No extra configuration is needed. This ensures compatibility with existing tools.

cURL

Copycurl https://api.minimaxapikey.com/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.minimaxapikey.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.minimaxapikey.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)