OtherDec 1, 2025

Arcee AI: Trinity Mini (free)

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.

Context Window
131K
tokens
Max Output
tokens
Released
Dec 1, 2025
Arena Rank

Capabilities

👁Vision
🧠Reasoning
🔧Tool Calling
Prompt Caching
🖥Computer Use
🎨Image Generation

Supported Parameters

Include Reasoning
Show reasoning tokens
Max Tokens
Output length limit
Reasoning
Extended thinking
Response Format
JSON mode / structured output
structured_outputs
Temperature
Controls randomness
Tool Choice
Control tool usage
Tool Calling
Function calling support
Top K
Top-K sampling
Top P
Nucleus sampling

Pricing Comparison

RouterInput / 1MOutput / 1MCached Input / 1M
OpenRouterFreeFree
Vercel AI$0.04$0.15

Model IDs

OpenRouterarcee-ai/trinity-mini:free

Tags

reasoningtool-calling
Compare with another model

Related Models