minimax-m3

MiniMax

minimax-m3

MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work.

Context 1MToolsReasoningVisionVideo

Pricing

Entry tier — longer context costs more

Input

S$0.778/M

Output

S$3.11/M

Cache read

Reusing a prompt already cached upstream

S$0.156/M

Cache write

Storing a prompt for later reuse

Not offered

Struck-through figures are the vendor's published list price.

Performance

Loading throughput, latency, and success rate…

Quick start

Full documentation

The API is OpenAI-compatible — point the base URL here and pass the model id.

cURL

curl https://api.lulutokens.ai/v1/chat/completions \  -H "Authorization: Bearer $LULU_API_KEY" \  -H "Content-Type: application/json" \  -d '{    "model": "minimax-m3",    "messages": [{"role": "user", "content": "Hello"}]  }'

Python

from openai import OpenAIclient = OpenAI(base_url="https://api.lulutokens.ai/v1", api_key="LULU_API_KEY")response = client.chat.completions.create(    model="minimax-m3",    messages=[{"role": "user", "content": "Hello"}],)

Endpoints:openaiopenai-responseanthropic