models/arcee-ai/trinity-large-thinking
A
arcee-ai·active

Arcee AI: Trinity Large Thinking

arcee-ai's mid-tier model. Context window: 262K tokens.

Overall score
4.23
/5.00 · ranked #80
Input
$0.250
per 1M tokens
Output
$0.800
per 1M tokens
Context
262K
tokens
Blended
$0.662
3:1 out:in ratio

Price drops, new benchmarks, model updates. Stay current on Arcee AI: Trinity Large Thinking.

One email per change. Unsubscribe anytime.

modelpicker.aipowered by live benchmark data

Scores by test

Methodology →
Structured Output
5.0
Strategic Analysis
5.0
Constrained Rewriting
4.0
Creative Problem Solving
4.0
Tool Calling
5.0
Faithfulness
5.0
Classification
4.0
Long Context
4.0
Safety Calibration
1.0
Persona Consistency
4.0
Agentic Planning
5.0
Multilingual
5.0
Tabular Data
4.0
SciCode
36.1

What you need to know

Arcee AI: Trinity Large Thinking is optimized for high-precision technical execution, specifically in structured output, tool calling, and agentic planning. It achieves perfect scores in strategic analysis and faithfulness, making it a reliable choice for complex workflows where logical consistency and adherence to schemas are critical.

The model offers a substantial 262K context window at a moderate price point, with a blended cost of $0.693/MTok. While it ranks in the middle of the pack overall (#74 of 130), its utility is concentrated in agentic capabilities and multilingual support rather than general-purpose creativity or nuanced rewriting.

A critical failure point is the model's safety calibration, which scores a 1/5. This indicates a lack of robust guardrails, meaning the model may produce unfiltered or unsafe content if not managed by an external moderation layer.

Use this model if you are building autonomous agents or data pipelines that require strict structured outputs and high strategic reasoning. Skip this model if your application is user-facing and requires built-in safety filters or high-level creative prose.

Strengths — Top 3

Structured Output5.0/5.0
Strategic Analysis5.0/5.0
Tool Calling5.0/5.0

Relative weaknesses — Bottom 3

Safety Calibration1.0/5.0
Constrained Rewriting4.0/5.0
Creative Problem Solving4.0/5.0

Similar models

GGemma 4 31B$0.2784.38DR1 0528$1.744.46GGemini 3 Flash Preview$2.384.46Oo3$6.504.31