---
id: "arcee-ai/trinity-large-thinking"
also: ["arcee-ai/trinity-large-thinking", "arcee-ai/Trinity-Large-Thinking", "vercel/arcee-ai/trinity-large-thinking"]
card_usd_per_m: "0.25 in, 0.8 out, at arcee-ai"
cheapest_list_usd_per_m: "0.22 in, 0.85 out, at parasail/fp4 on openrouter"
cheapest_effective_usd_per_m: "0.0515 in, 0.6597 out, at arcee-ai on openrouter"
context: 262144
max_output: 80000
input: ["text"]
output: ["text"]
released: "2026-04-01"
params: ["frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 3
gateways: "openrouter (2), vercel (1)"
no_training: 2
trains: 0
retains_prompts: 1
intelligence: 10.8000
coding: 25.8000
agentic: 1
---
# Arcee AI: Trinity Large Thinking

Trinity-Large-Thinking is a reasoning-optimized variant of Arcee AI's Trinity-Large family — a 398B-parameter sparse Mixture-of-Experts (MoE) model with approximately 13B active parameters per token. Built on Trinity-Large-Base and post-trained with extended chain-of-thought reasoning and agentic RL, Trinity-Large-Thinking delivers state-of-the-art performance on agentic benchmarks while maintaining strong general capabilities.