Skip to content
OpenKey

Trinity Large Thinking

Arcee AIReleased Apr 1, 2026

Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7...

Try in playground
Context window
262K tokens
Max output
80K tokens
Input
text
Output
text
Tokenizer
Other
Released
Apr 1, 2026
Reasoning
always on

Pricing

Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.

Per 1M tokensProvider+ 3% feeYou pay
Input$0.250$0.0075$0.258
Output$0.800$0.024$0.824
Cache read$0.060$0.0018$0.062

Benchmarks

Design Arena

CategoryEloWin rateRank
3Dmodels115841.3%#59
ASCII artmodels108737.1%#45
Codemodels116540.1%#62
Data vizmodels114239.3%#69
Game devmodels114238.1%#68
SVGmodels107335.2%#59
UI componentsmodels110032.5%#73
Websitesmodels117741.3%#60

Head-to-head preference voting. How we filter and rank

Supported parameters

  • include_reasoning
  • max_tokens
  • reasoning
  • temperature
  • tool_choice
  • tools
  • top_k
  • top_p

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model arcee-ai/trinity-large-thinking.

Code sample language
curl https://api.openkey.ai/v1/chat/completions \
  -H "Authorization: Bearer $OPENKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "arcee-ai/trinity-large-thinking",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.openkey.ai/v1",
    api_key=os.environ["OPENKEY_API_KEY"],
)

completion = client.chat.completions.create(
    model="arcee-ai/trinity-large-thinking",
    messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.openkey.ai/v1",
  apiKey: process.env.OPENKEY_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "arcee-ai/trinity-large-thinking",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Questions

How much does Trinity Large Thinking cost via API?
Through OpenKey, Trinity Large Thinking costs $0.258 per 1M input tokens and $0.824 per 1M output tokens. That is the provider price ($0.250 / $0.800) plus a flat 3% fee — nothing else.
What is Trinity Large Thinking's context window?
Trinity Large Thinking accepts up to 262K tokens of context and returns up to 80K tokens per request.
Is Trinity Large Thinking OpenAI-compatible?
Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "arcee-ai/trinity-large-thinking" using any OpenAI SDK — only the base URL and API key change.
What inputs does Trinity Large Thinking support?
Trinity Large Thinking accepts text input and produces text output.

More from Arcee AI

All Arcee AI models →