LLM Reference
OpenRouter

Using MiniMax M3 on OpenRouter

Implementation guide · MiniMax M3 · MiniMax

Serverless

Quick Start

  1. 1
    Create an account at OpenRouter and generate an API key.
  2. 2
    Use the OpenRouter SDK or REST API to call minimax/minimax-m3 — see the documentation for request format.
  3. 3
    You'll be billed $0.30/1M input, $1.20/1M output tokens. See full pricing.

Code Examples

See OpenRouter documentation for integration details.

About OpenRouter

OpenRouter provides a unified interface for Large Language Models with better pricing, improved uptime, and no subscription requirements. Route across providers for cost optimization and reliability.

OpenRouter is a multi-provider LLM aggregator offering unified API access to 300+ models from all major labs and emerging providers, with automatic failover for reliability.

Pricing on OpenRouter

TypePrice (per 1M)
Input tokens$0.30
Output tokens$1.20
Image input$1.00
Video input$1.00

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode ExecutionPrompt Caching

About MiniMax M3

MiniMax's frontier open-weight multimodal model with MiniMax Sparse Attention (MSA) architecture enabling economical 1M-token context (1/20th compute vs prior generation). Scored 59% SWE-bench Pro, surpassing GPT-5.5. Accepts text, image, and video input. Max output 512K tokens. Pricing: $0.60/$2.40 per 1M tokens in/out (list). Open-weight model weights release pending.

Model Specs

Released2026-06-01
Context1m
ArchitectureDecoder Only

Provider

OpenRouter
OpenRouter

OpenRouter, Inc.

New York, NY, USA