Arcee Ai logo

Arcee Ai

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.

Input / 1M tokens
$0.045
Output / 1M tokens
$0.150
Context window
131K tokens
Provider
Arcee Ai

Performance

Median streaming throughput and first-token latency measured by Artificial Analysis.

Output tokens / sec
Time to first token