modelbenchmark.io

Trinity Mini

trinity-mini

Compare

Reasoning-tuned 26B MoE model with 3B active parameters for agents, tools, and multi-step workloads

Specification

most-agreed values

Context
131K
Max output
131K
Released
2025-12-01
Knowledge cutoff
2024-10
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.045
Output
$0.15

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
clarifai · arcee-ai$0.045$0.15131K131K
together_ai$0.045$0.15