LLM Comparison

DeepSeek V3.2 Speciale vs Trinity Large Thinking

Side-by-side specs, pricing & capabilities · Updated April 2026

Add to comparison

2/6 models

Same tier:

	D DeepSeek V3.2 Speciale	T Trinity Large Thinking
Organization	DeepSeek	Arcee AI
OpenTools Score	64 80.1
Family	DeepSeek	Trinity
Status	Current	Current
Release Date	Dec 2025	Apr 2026
Context Window	164K tokens	262K tokens
Input Price	$0.40/M tokens	$0.22/M tokens
Output Price	$1.20/M tokens	$0.85/M tokens
Pricing Notes	Cache read: $0.2000/M tokens	Cache read: $0.0600/M tokens
Capabilities	textcode	textcodeextended-thinking
Max Output	164K tokens	262K tokens
API Identifier	`deepseek/deepseek-v3.2-speciale`	`arcee-ai/trinity-large-thinking`
Benchmarks
MMLU	87.1	—
HumanEval	89.2	—
MATH	90.2	—
	View DeepSeek V3.2 Speciale	View Trinity Large Thinking

Cost Calculator

Enter your expected monthly token usage to compare costs.

Input tokens / month

Output tokens / month

Model	Input	Output	Total / mo	vs Best
Trinity Large ThinkingCheapest	$0.22	$0.43	$0.65	—
DeepSeek V3.2 Speciale	$0.40	$0.60	$1.00	+55%

DeepSeek

DeepSeek V3.2 Speciale

DeepSeek V3.2 Speciale is a large language model from DeepSeek. Supports up to 163,840 token context window. Achieves 87.1% on MMLU. Available from $0.40/M input tokens.

Arcee AI

Trinity Large Thinking

Trinity Large Thinking is a large language model from Arcee AI. Supports up to 262,144 token context window. Available from $0.22/M input tokens.