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.
fromimport openai OpenAI
client = OpenAI(
"https://openrouter.ai/api/v1" base_url=,
"$OPENROUTER_API_KEY" api_key=,
)
response = client.chat.completions.create(
"arcee-ai/trinity-large-preview:free" model=,
"role""user""content""Hello!" messages=[{: , : }],
)
print(response.choices[0].message.content)Set OPENROUTER_API_KEY with your OpenRouter API key from openrouter.ai/keys.
Taste is judged on an uncapped scale, originality first. The space past 100 is craft today's models rarely reach.
Unique words vs. total words. Higher = richer vocabulary.
Average words per sentence.
"Might", "perhaps", "arguably" per 100 words.
**Bold** markers per 1,000 characters.
Bullet and numbered list items per 1,000 characters.
Markdown headings per 1,000 characters.
Emoji per 1,000 characters.
"However", "moreover", "furthermore" per 100 words.
35 outputs · generated before accounting joined the chat
Trinity-Large-Preview is a frontier-scale open-weight language model from Arcee, built as a 400B-parameter sparse Mixture-of-Experts with 13B active parameters per token using 4-of-256 expert routing. It excels in creative writing, storytelling, role-play, chat scenarios, and real-time voice assistance. Trained to navigate well in agent harnesses like OpenCode, Cline, and Kilo Code, and to handle complex toolchains and long, constraint-filled prompts.
fromimport openai OpenAI
client = OpenAI(
"https://openrouter.ai/api/v1" base_url=,
"$OPENROUTER_API_KEY" api_key=,
)
response = client.chat.completions.create(
"arcee-ai/trinity-large-preview:free" model=,
"role""user""content""Hello!" messages=[{: , : }],
)
print(response.choices[0].message.content)Set OPENROUTER_API_KEY with your OpenRouter 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 · generated before accounting joined the chat