Trinity Large Preview by Arcee-ai — Pricing, Benchmarks & Real Outputs
Share
Loading...
Compare Trinity Large Preview
Alternatives to Trinity Large Preview
Trinity Large Preview is good. These would like a word anyway.
Trinity Large Preview is good. These would like a word anyway.
Trinity Large Preview is good. These would like a word anyway.
Trinity-Large-Preview is a frontier-scale open-weight language model from Arcee, built as a 400B-parameter sparse Mixture-of-Experts with 13B active parameters per token using 4-of-256 expert routing. It excels in creative writing, storytelling, role-play, chat scenarios, and real-time voice assistance. Trained to navigate well in agent harnesses like OpenCode, Cline, and Kilo Code, and to handle complex toolchains and long, constraint-filled prompts.
import requests
response = requests.post(
"https://openrouter.ai/api/v1/chat/completions" ,
headers={
"Authorization""Bearer $OPENROUTER_API_KEY" : ,
"Content-Type""application/json" :
},
json={
"model""arcee-ai/trinity-large-preview:free" : ,
"messages""role""user""content""Hello!" : [{: , : }]
}
)
print(response.json())Replace $OPENROUTER_API_KEY with your API key from openrouter.ai/keys
Taste is judged on an uncapped scale, originality first. The space past 100 is craft today's models rarely reach.
Unique words vs. total words. Higher = richer vocabulary.
Average words per sentence.
"Might", "perhaps", "arguably" per 100 words.
**Bold** markers per 1,000 characters.
Bullet and numbered list items per 1,000 characters.
Markdown headings per 1,000 characters.
Emoji per 1,000 characters.
"However", "moreover", "furthermore" per 100 words.
35 outputs from Trinity Large Preview
Trinity-Large-Preview is a frontier-scale open-weight language model from Arcee, built as a 400B-parameter sparse Mixture-of-Experts with 13B active parameters per token using 4-of-256 expert routing. It excels in creative writing, storytelling, role-play, chat scenarios, and real-time voice assistance. Trained to navigate well in agent harnesses like OpenCode, Cline, and Kilo Code, and to handle complex toolchains and long, constraint-filled prompts.
import requests
response = requests.post(
"https://openrouter.ai/api/v1/chat/completions" ,
headers={
"Authorization""Bearer $OPENROUTER_API_KEY" : ,
"Content-Type""application/json" :
},
json={
"model""arcee-ai/trinity-large-preview:free" : ,
"messages""role""user""content""Hello!" : [{: , : }]
}
)
print(response.json())Replace $OPENROUTER_API_KEY with your API key from openrouter.ai/keys
Taste is judged on an uncapped scale, originality first. The space past 100 is craft today's models rarely reach.
Unique words vs. total words. Higher = richer vocabulary.
Average words per sentence.
"Might", "perhaps", "arguably" per 100 words.
**Bold** markers per 1,000 characters.
Bullet and numbered list items per 1,000 characters.
Markdown headings per 1,000 characters.
Emoji per 1,000 characters.
"However", "moreover", "furthermore" per 100 words.
35 outputs from Trinity Large Preview