MODELS
MiniMax: MiniMax M3
by MiniMax
Overview
MiniMax M3 is a MiniMax frontier multimodal coding model with a 1M-token context window for agentic reasoning, tool use, coding, multimodal chat input, and long-context tasks.
Details
MiniMax M3 is listed by MiniMax as a coding and agentic frontier model with 1M-context MSA and native multimodality. MiniMax API documentation describes MiniMax-M3 as a frontier multimodal coding model with a 1,000,000-token context window and documents Anthropic- and OpenAI-compatible API calls using the MiniMax-M3 model ID. MiniMax release notes say it was released for agentic reasoning, tool use, coding, multimodal chat input, and long-context tasks. The OpenRouter listing describes MiniMax-M3 as supporting text, image, and video inputs with text output and being suited for long-horizon agentic work and coding.
When to Use
Use for coding workflows where MiniMax’s documented focus on frontier coding code understanding multi-turn dialogue and reasoning is relevant. Use for agentic reasoning tool-use or long-horizon agent workflows that benefit from a 1M-token context window. Use for multimodal chat/input scenarios involving text image or video inputs with text output as described in supplied model listings.
Getting Started
- Review the official model page: https://www.minimax.io/models/text/m3
- Read MiniMax API model documentation and invocation guidance
- including the MiniMax-M3 model ID and OpenAI-/Anthropic-compatible API examples: https://platform.minimax.io/docs/guides/text-generation
- Check the pay-as-you-go pricing page for current MiniMax-M3 LLM tiers: https://platform.minimax.io/docs/guides/pricing-paygo
- For coding-tool integration
- follow MiniMax’s guide for Claude Code
- Cursor
- OpenCode
- Cline
- Roo Code
- and related tools: https://platform.minimax.io/docs/guides/text-ai-coding-tools
- Optionally inspect the OpenRouter listing for router-specific integration metadata: https://openrouter.ai/minimax/minimax-m3
Key Features
- •1
- •000
- •000-token context window documented by MiniMax API docs.
- •Native multimodality described on MiniMax’s official model page.
- •Agentic reasoning
- •tool use
- •coding
- •multimodal chat input
- •and long-context task support listed in MiniMax release notes.
- •OpenAI- and Anthropic-compatible API invocation documented by MiniMax.
- •Coding-tool setup guidance provided for Claude Code
- •Cursor
- •OpenCode
- •Cline
- •Roo Code
- •and other tools.
Capabilities
- •text-generation
- •multimodal-input
- •image-input
- •video-input
- •long-context
- •coding
- •agentic-reasoning
- •tool-use
- •api-access
Last updated Jun 1, 2026