Skip to main content

Overview

MiniMax models pair very large context windows with low cost, which makes them a good fit for long-running conversations and bulk document work.

Available Models

MiniMax M3

1 credit • MiniMax’s flagship model with a 1M-token context window and native multimodal (image) input.
  • 1M context window
  • Exceptional reasoning (reasoning model)
  • Speed: Medium • Cost: Low
  • Vision: images supported
  • Model id: MiniMax-M3

MiniMax M2.7

1 credit • Agentic MiniMax M2 model tuned for coding and reasoning, with a 205K context window.
  • 205K context window
  • Excellent reasoning (reasoning model)
  • Speed: Medium • Cost: Low
  • Model id: MiniMax-M2.7

MiniMax M2.5

1 credit • Cost-efficient MiniMax M2 tier for general-purpose tasks, with a 205K context window.
  • 205K context window
  • Excellent reasoning (reasoning model)
  • Speed: Fast • Cost: Very_low
  • Model id: MiniMax-M2.5

Setup

Using BoostGPT-Hosted API Keys

1

Select a model

In your BoostGPT dashboard, choose any MiniMax model when creating or configuring an agent.
2

Start chatting

Credits are deducted per step at the rate shown on each model above. Nothing else to configure.

Using Your Own API Key

Bring your own key to bill MiniMax directly instead of spending BoostGPT credits. See Bring Your Own Keys.

Next Steps

Model Comparison

Compare every model across all providers

Provider Overview

See all supported providers