Please rotate your device

To continue exploring this website, please rotate your device to a vertical orientation

MiniMax M2.1

MiniMax/MiniMax M2.1

An update to MiniMax M2 with improved coding and reasoning performance

large language

MiniMax M2.1 is a 230B-parameter MoE model with 10B active parameters. It scores competitively across benchmarks for coding and agentic tool use.

MiniMax M2.1 shows improved performance across coding benchmarks
MiniMax M2.1 shows improved performance across coding benchmarks

Input

python
from openai import OpenAI
import os

model_url = "" # Copy in from API pane in Baseten model dashboard

client = OpenAI(
    api_key=os.environ['BASETEN_API_KEY'],
    base_url=model_url
)

# Chat completion
response_chat = client.chat.completions.create(
    model="",
    messages=[
        {"role": "user", "content": "Write FizzBuzz."}
    ],
    temperature=0.6,
    max_tokens=100,
)
print(response_chat)

Output

json
{
  "id": "143",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "logprobs": null,
      "message": {
        "content": "[Model output here]",
        "role": "assistant",
        "audio": null,
        "function_call": null,
        "tool_calls": null
      }
    }
  ],
  "created": 1741224586,
  "model": "",
  "object": "chat.completion",
  "service_tier": null,
  "system_fingerprint": null,
  "usage": {
    "completion_tokens": 145,
    "prompt_tokens": 38,
    "total_tokens": 183,
    "completion_tokens_details": null,
    "prompt_tokens_details": null
  }
}