MiniMax
MiniMax M2.7
Specs
- Input price
- $0.3/M
- Output price
- $1.2/M
- Context window
- 196.608K tokens
MiniMax's 228B Mixture-of-Experts model for complex agent harnesses and productivity workflows - Agent Teams, compound skills, and dynamic tool search at a budget price point.
Capabilities
- 228B parameter Mixture-of-Experts architecture
- Built to drive complex agent harnesses: Agent Teams, compound skills, and dynamic tool search
- 196K-token context window
- Function calling for multi-step productivity and back-office automation
Best for
- Agentic back-office workflows: claims intake, referral routing, eligibility checks
- High-volume conversational and search applications on a budget
- Agent-harness teams that need strong tool calling without M3's multimodal and long-context footprint
Limitations to keep in mind
- Text-only; no image input
- 196K context is narrower than the 512K served on M3
- Superseded by MiniMax M3 for multimodal and long-context agentic work
HIPAA-compliant hosting
MiniMax M2.7 is available under our HIPAA-compliant design-partner program, with a signed Business Associate Agreement (BAA), encryption in transit and at rest, and access controls. We are currently onboarding design partners, with general availability coming soon. Run the model behind a unified OpenRouter-style API and swap to another model with a single parameter. For the deployment requirements behind that, see our 2026 guide to HIPAA compliance for AI & LLM APIs.
Pricing in context
Open source models like MiniMax M2.7 can be served efficiently on optimized inference infrastructure, with savings passed through to you. Exact savings depend on the model and your volume, but open source inference is typically a fraction of the per-token cost of closed-source frontier models on Azure OpenAI or AWS Bedrock - without cloud egress lock-in or minimum commitments. See the full pricing comparison or browse the model catalog.
Related models
Design partner program
Run MiniMax M2.7 under HIPAA
Join the waitlist to be prioritized. We'll reach out with a qualification call and early access.