Trinity Large Thinking
All models
Arcee AiArcee AiReleased April 1, 2026

Trinity Large Thinking

262K context$0.220/M input$0.850/M output

Trinity Large Thinking is an open-source reasoning model developed by Arcee AI. It excels in reasoning tasks, agentic workloads, and benchmarks such as PinchBench. The model supports reasoning-enabled workflows, allowing users to access its step-by-step thinking process for enhanced decision-making capabilities.

What is Trinity Large Thinking?

Trinity Large Thinking is an AI model from Arcee Ai that Agent Mag tracks for pricing, context window, modalities, benchmarks, and API compatibility. Builders can use this page to compare Trinity Large Thinking against other models for agent workflows and production deployments.

Model ID

Trinity Large Thinking is an open-source reasoning model developed by Arcee AI. It excels in reasoning tasks, agentic workloads, and benchmarks such as PinchBench. The model supports reasoning-enabled workflows, allowing users to access its step-by-step thinking process for enhanced decision-making capabilities.

Architecture & Specifications
Tokenizer
Other
License
Open Source
Released
April 1, 2026
Modalities
Input
text
Output
text
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biasmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Strengths
  • Strong performance in reasoning tasks
  • Excels in agentic workloads
  • Supports reasoning-enabled workflows
  • High benchmark scores in PinchBench and τ²-Bench Telecom
  • Open-source availability
Limitations
  • Low performance in research-level physics reasoning (CritPt: 0.9%)
  • Moderate hallucination rate (13.4%)
  • Limited coding capabilities (Terminal-Bench Hard: 22.7%)
  • Relatively low accuracy in omniscience tasks (22.8%)
  • Performance variability across benchmarks
Recommended Use Cases
Scientific reasoning and analysis
Agentic workflows and automation
Instruction-following tasks
Coding for scientific computing
Conversational AI in dual-control scenarios

Related content

Data enriched Apr 24, 2026. Pricing from OpenRouter API.