Arcee

Trinity Large Thinking

CTX262K

Beta

49Quality

Reasoning · Tools

Input$0.25/M

Output$0.80/M

Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use

Open weightsOpenMDW 1.1 license850/1044

Drag to turn

ArceeTextCommonBeta

Trinity Large Thinking

Reasoning-optimized 398B MoE agent model with extended thinking for long-horizon and multi-turn tool use

trinity-large-thinking

Type: Text
Quality: 49 · Top 51% on the LMArena Text
Context window: 262,144 tokens
Max output: 262,144 tokens
Input price: $0.25 / 1M tokens
Output price: $0.80 / 1M tokens
Cache read: $0.06 / 1M tokens
Cache write: —
Parameters: 399B (398,635,286,016)
Downloads: 2.3K in the last 30 days
Likes: 190
Access to weights: Open download
Released: Apr 1, 2026
Knowledge cutoff: —
Takes in: Text
Puts out: Text
Reasoning: Yes
Tool calling: Yes
Structured output: No
File attachments: No
Access: Open weights
License: OpenMDW 1.1 license
Rarity: Common
Set number: 850/1044

Open Arcee docs Weights on Hugging Face Quality 49 Where to run it 5 Meet its creature Battle Qwen3-VL 30B-A3B

License read from the model’s Hugging Face card. Specs from models.dev, downloads from Hugging Face, last changed Oct 19, 2026. Official source: docs.arcee.ai.

How good is it?

Public leaderboard scores for Trinity Large Thinking, refreshed daily from Epoch AI and LMArena.

Top 51% of the 416 models on the LMArena Text: #212.

Quality is the share of a leaderboard’s models this one beats, from 0 to 100. Chat models are rated on Epoch AI’s Capabilities Index when it lists them, otherwise on LMArena; image and video models on LMArena’s image and video arenas.

Leaderboards

LMArena Text#212 of 416
People compare two anonymous answers and vote for the better one.1,340 rating
LMArena Text · Coding#222 of 411
The text arena’s coding prompts only.1,358 rating
LMArena Text · Math#197 of 400
The text arena’s math prompts only.1,366 rating
LMArena Text · Creative writing#213 of 414
The text arena’s creative writing prompts only.1,308 rating
LMArena WebDev#136 of 145
Each model builds a web app from the same prompt; people pick the better one.1,238 rating

Scores from LMArena, licensed CC BY 4.0. Boards list models under their own names, so a close match is shown with the name it was scored under. Credits

Where to run it

5 providers sell Trinity Large Thinking through an API. Prices are per million tokens, cheapest first.

CheapestArcee$0.25 in · $0.80 out
From the labArcee$0.25 in · $0.80 out

API providers

Provider	Input	Output	Context
ArceeOfficialCheapest paid`trinity-large-thinking`	$0.25	$0.80	262K
Kilo Gateway`arcee-ai/trinity-large-thinking`	$0.25	$0.80	262K
OpenRouter`arcee-ai/trinity-large-thinking`	$0.25	$0.80	262K
Vercel AI Gateway`arcee-ai/trinity-large-thinking`	$0.25	$0.80	262K
NanoGPT`arcee-ai/trinity-large-thinking`	$0.25	$0.90	262K

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

Face off

Current text models from other labs at a similar output price.