Skip to content
OpenKey

Trinity Mini

Arcee AIReleased Dec 1, 2025

Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active per token. Engineered for efficient reasoning over long contexts (131k) with robust function...

Try in playground
Context window
131K tokens
Max output
131K tokens
Input
text
Output
text
Tokenizer
Other
Released
Dec 1, 2025
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$0.045$0.0013$0.046
Output$0.150$0.0045$0.154

Supported parameters

  • include_reasoning
  • logprobs
  • max_completion_tokens
  • max_tokens
  • reasoning
  • response_format
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_k
  • top_logprobs
  • top_p

Call it

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

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-mini",
    "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-mini",
    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-mini",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Questions

How much does Trinity Mini cost via API?
Through OpenKey, Trinity Mini costs $0.046 per 1M input tokens and $0.154 per 1M output tokens. That is the provider price ($0.045 / $0.150) plus a flat 3% fee — nothing else.
What is Trinity Mini's context window?
Trinity Mini accepts up to 131K tokens of context and returns up to 131K tokens per request.
Is Trinity Mini OpenAI-compatible?
Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "arcee-ai/trinity-mini" using any OpenAI SDK — only the base URL and API key change.
What inputs does Trinity Mini support?
Trinity Mini accepts text input and produces text output.

More from Arcee AI

All Arcee AI models →