All Models
Trinity Mini
Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active per token. Engineered for efficient reasoning over long contexts (131k) with robust function calling and multi-step agent workflows.
Available Providers (4)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 OpenRouter | arcee-ai/trinity-mini:free | $0.00/MTok | $0.00/MTok | 131.1K | 131.1K | |
 Clarifai | arcee_ai/AFM/models/trinity-mini | $0.04/MTok | $0.15/MTok | 131.1K | 131.1K | |
 NanoGPT | arcee-ai/trinity-mini | $0.05/MTok | $0.15/MTok | 131.1K | 8.2K | |
 Vercel AI Gateway | arcee-ai/trinity-mini | $0.05/MTok | $0.15/MTok | 131.1K | 131.1K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output