Description
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 calling and multi-step agent workflows.
API Usage Examples
OpenAI Compatible Endpoint
Use this endpoint with any OpenAI-compatible library. Model: Arcee AI: Trinity Mini (arcee-ai/trinity-mini)
curl https://api.ridvay.com/v1/chat/completions -H "Content-Type: application/json" -H "Authorization: Bearer YOUR_API_KEY" -d '{
"model": "arcee-ai/trinity-mini",
"messages": [
{
"role": "user",
"content": "Explain the capabilities of the Arcee AI: Trinity Mini model"
}
],
"temperature": 0.7,
"max_tokens": 1024
}'Supported Modalities
- Text
API Pricing
- Input: 0.045$ / 1M tokens
- Output: 0.15$ / 1M tokens
Token Limits
- Max Output: 131,072 tokens
- Max Context: 131,072 tokens
Subscription Tiers
- free
- pro
- ultimate