OpenAI compatible

MiniMax API

Access MiniMax models via OpenAI-compatible endpoint. Drop-in replacement - just change the base URL.

Base URL
https://api.infercom.ai/v1

MiniMax models are fully OpenAI-compatible on Infercom. Use base URL api.infercom.ai/v1 with your existing OpenAI SDK - no code changes needed. MiniMax-M2.7 Ultraspeed is available with 400+ tokens/second inference speeds, EU-hosted in Munich for full GDPR compliance.

Available Models

All MiniMax models available on Infercom. Use the model ID in your API requests.

ModelModel IDParametersContextSpeedBest For
MiniMax-M2.7 UltraspeedMiniMax-M2.7229B MoE192K tokens428 tok/sSelf-critique, multi-agent, agentic coding

Output Throughput, p50, 10K input / 1K output, single request. Last measured: July 2026.

Model IDs are case-sensitive. Use exactly as shown.

Quick Start

Works with any OpenAI-compatible SDK. Just point to our endpoint.

Integration takes three steps: First, sign up at cloud.infercom.ai to get your API key. Second, change your base URL from api.openai.com to api.infercom.ai/v1. Third, set your model to MiniMax-M2.7. Your existing code, prompts, and tooling all work unchanged.

Python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.infercom.ai/v1",
    api_key="your-api-key"
)

response = client.chat.completions.create(
    model="MiniMax-M2.7",
    messages=[{"role": "user", "content": "Hello"}],
    stream=True
)

for chunk in response:
    print(chunk.choices[0].delta.content, end="")
JavaScript
import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.infercom.ai/v1',
  apiKey: 'your-api-key',
});

const response = await client.chat.completions.create({
  model: 'MiniMax-M2.7',
  messages: [{ role: 'user', content: 'Hello' }],
});

console.log(response.choices[0].message.content);
curl
curl https://api.infercom.ai/v1/chat/completions \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "MiniMax-M2.7",
    "messages": [{"role": "user", "content": "Hello"}],
    "stream": true
  }'
LangChain
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    base_url="https://api.infercom.ai/v1",
    api_key="your-api-key",
    model="MiniMax-M2.7"
)

response = llm.invoke("Explain quantum computing")
print(response.content)

Supported Endpoints

  • POST /v1/chat/completions

    OpenAI Chat Completions (streaming supported)

  • POST /v1/messages

    Anthropic Messages API

  • POST /v1/responses

    OpenAI Responses API

  • GET /v1/models

    List available models

Why Use Infercom for MiniMax

EU-Hosted

Munich datacenter. Full GDPR compliance. No US CLOUD Act exposure.

Up to 10x Faster

SambaNova's dataflow architecture delivers world-record inference speeds.

No Persistent Storage

Your prompts and outputs are never stored persistently or used for training.

Drop-in Compatible

Works with OpenAI SDK, Anthropic SDK, LangChain, LlamaIndex, and any OpenAI-compatible tool.

Frequently Asked Questions

Is MiniMax API compatible with OpenAI?

Yes. MiniMax models on Infercom are fully OpenAI-compatible. Use base URL api.infercom.ai/v1 with your existing OpenAI SDK, LangChain, LlamaIndex, or any OpenAI-compatible tool. No code changes needed beyond the base URL.

What is the base URL for MiniMax API?

The base URL is https://api.infercom.ai/v1. Set this as your base_url in the OpenAI SDK or baseURL in JavaScript. Supported endpoints: /chat/completions (OpenAI), /messages (Anthropic), /responses (OpenAI Responses API), and /models.

Can I use LangChain with MiniMax?

Yes. Use ChatOpenAI from langchain_openai with base_url='https://api.infercom.ai/v1' and model='MiniMax-M2.7'. LlamaIndex, CrewAI, and other frameworks that support OpenAI also work.

What is MiniMax M2.7 Ultraspeed?

MiniMax M2.7 Ultraspeed is a 229B MoE model (10B active parameters) with built-in self-critique, native multi-agent support, and a 192K context window. It runs at 400+ tokens/second on Infercom's EU infrastructure and is our flagship model for agentic coding and multi-step reasoning.

Is MiniMax API GDPR compliant?

Yes. MiniMax models on Infercom run on EU-hosted infrastructure in Munich, Germany. Full GDPR compliance with no persistent storage - prompts and outputs are never stored persistently or used for training. No US CLOUD Act exposure.

Start Using MiniMax Today

Get your API key in 30 seconds. Pay only for the tokens you use.