MiniMax M3.1 Flash

MiniMax’s fast multimodal model for coding and agentic workflows, computer use included. Text, images and video in, with a context of a million tokens.

Get an API key API & docs

MiniMax M3.1 Flash MiniMax

Context: 1M; tokens
Inputs: Text, images and video

Best for

Coding
Agentic workflows
Computer use

What it does best.

Coding: Write and fix code across a project.
Agentic workflows: Multi-step work with tools, from plan to result.
Computer use: Operate a screen: read it, click, type, check the result.

It mines while it answers.

On the Peryn API, every request mines as much $PEARL as it can while it is served: inside the AI work, and in the gaps between requests.

How Peryn works

The model.

Made by: MiniMax
Context: 1M tokens
Size: About 428B parameters, mixture of experts: 23B active per token
Inputs: Text, images and video
Licence: MiniMax Community License
Official name: MiniMax-M3.1-Flash

From MiniMax’s official model card. Built with MiniMax M3.1-Flash.

One call, OpenAI-compatible.

Use the OpenAI SDK: set our base URL and your key, and keep your code.

import osfrom openai import OpenAI client = OpenAI(base_url="https://api.peryn.ai/v1",api_key=os.environ["PERYN_API_KEY"],) stream = client.chat.completions.create(model="minimax-m3.1-flash",messages=[{"role": "user", "content": "Hello"}],stream=True,)for chunk in stream:if chunk.choices:print(chunk.choices[0].delta.content or "", end="")

Other models on Peryn: DeepSeek V4.1 Flash · GLM-5.3-Flash · Hy4