Trinity Large

arcee

Trinity Large (Preview) is a 400B-parameter (13B active) sparse mixture-of-experts language model, engineered to scale model capacity while maintaining inference efficiency over long contexts. It delivers strong performance in reasoning-heavy workloads including math, coding-related tasks, and multi-step agent workflows. With a 131K context window and native function calling, it excels at complex tasks requiring deep understanding and structured outputs.

Try Now

Capabilities

Tool Use

Example Use Cases

Complex multi-step reasoning tasks

Coding and math-heavy workloads

Agent workflows requiring strong task decomposition

Technical Specifications

Context Window

131,000 tokens

Max Output

131,000 tokens

Cache Miss Cost

$0.25 per 1M tokens

Non-Reasoning Cost

$1 per 1M tokens

Web Search Cost

$15 per 1K calls

Code Execution Cost

$0.19 per 1K calls

⚠️ Legacy

Made legacy on

Reason

Untested

Recommended Replacement

Qwen3 Max