Skip to content
NerdLevelTech

MiniMax

MiniMax M3.1 Flash

1M context and open weights at a Chinese price

Open weightsNewReleased: October 19, 2026Self-hostingHigh volumeVerified: October 24, 2026

What it is

MiniMax’s agentic Flash model: a 1M context, native multimodal input, adjustable thinking depth, open weights on Hugging Face, and $0.15/$0.60 per 1M tokens on the global API.

NLT take

A serious open-weight agent model with a million-token window and a clear USD rate. The remaining question is operational: confirm which MiniMax platform your key belongs to before you put it in a cost model.

Before you switch

The USD rates are on the global MiniMax platform; the Chinese platform quotes CNY. Use the right one for your key, and check the Ollama tag before pulling.

Cost for a real task

The same task on every model: 50,000 input tokens and 10,000 output tokens, at the base tier.

Task cost

$0.014

50K input + 10K output tokens

Input, per 1M
$0.15
Output, per 1M
$0.60
Cached input, per 1M
$0.015

Pricing source: MiniMax pricing (USD)

Specs

Maker
MiniMax
Licence
Open weights
Released
October 19, 2026
Context window
1,000,000 tokens
Input / output
Text · Image → Text

Also known as: MiniMax-M3.1-Flash · minimax-m3.1-flash:cloud

Watch it in action

Hands-on videos from creators we trust. They open on YouTube; we do not host or re-upload them.

From our coverage

Articles about this model or its family. A “Background” tag means we have not covered this exact release yet.

Sources & model links

Every number on this card traces back to one of these links. The maker page proves the positioning, the pricing page proves the rates, the Hugging Face repo proves the weights exist, and the Ollama page proves a local tag.

Official

Open weights

Run locally