Models / Arcee AIArcee / / Arcee AI Trinity Mini API
Arcee AI Trinity Mini API

This model is not currently supported on Together AI.
Visit our Models page to view all the latest models.
Trinity Mini brings frontier-level language understanding to your applications without frontier costs. This 26B sparse mixture-of-experts model activates just 3B parameters per token, delivering exceptional reasoning, tool use, and multi-turn conversation capabilities across a 128K context window. Whether you're building conversational AI, agentic workflows, or production systems requiring long-context understanding, Trinity Mini offers the efficiency and performance to scale from prototype to production seamlessly.
Arcee AI Trinity Mini API Usage
Endpoint
How to use Arcee AI Trinity Mini
Model details
Architecture Overview:
• Sparse mixture-of-experts (MoE) architecture with 26B total parameters and 3B activated per token
• Efficient attention mechanism that reduces memory and compute requirements while preserving long-context coherence
• 128K-token context window supporting extended document processing and multi-turn interactions
Training Methodology:
• Trained with continuous reinforcement learning techniques for ongoing capability improvements
• Built by Arcee AI's collaborative research team focused on delivering best-in-class per-parameter performance
• Optimized for multi-turn conversations, tool use, and structured outputs
Performance Characteristics:
• Strong context utilization that fully leverages long inputs for coherent multi-turn reasoning
• Reliable function and tool calling capabilities for agent workflows
• High inference efficiency generating tokens rapidly while minimizing compute
• Outstanding price-to-performance ratio compared to dense models of similar capability
Prompting Arcee AI Trinity Mini
Applications & Use Cases
Conversational AI Applications:
• Multi-turn customer support chatbots with long conversation history
• Virtual assistants with tool integration and function calling
• Interactive documentation and knowledge base systems
Agentic Workflows:
• Multi-step agent systems requiring tool use and reasoning
• Workflow automation with structured output generation
• RAG systems with extended context understanding
Enterprise Integration:
• Cost-efficient production deployments via Together AI APIs
• Internal tooling with natural language interfaces
• Document analysis and processing pipelines with 128K context support
