Capabilities
VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution
About Trinity Mini
26B sparse MoE with 3B active parameters per token and 128K context window. Trained on 10T tokens. Fully post-trained for reasoning and instruction following, suitable for cloud or on-premises deployment. Available via Arcee AI API and OpenRouter.
Get Started
Model Specs
Released2025-02-01
Parameters26B
Context128K
ArchitectureSparse Mixture of Experts (MoE)