Trinity Mini
Arcee AI
Trinity Mini is a 26B-parameter (3B active) sparse mixture-of-experts language model, engineered for efficient inference over long contexts with robust function calling and multi-step agent workflows.
- Language
- Tool use
- Context
- 131K
- Max output
- 131K
- Input / 1M
- $0.045
- Output / 1M
- $0.150
Quickstart
Point any OpenAI-compatible client at Maxynetic Systems and pass arcee-ai/trinity-mini as the model.
curl https://api.maxynetic.com/v1/chat/completions \
-H "Authorization: Bearer $MAXYNETIC_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "arcee-ai/trinity-mini",
"messages": [{ "role": "user", "content": "Explain routing in one line." }]
}'Pricing
Billed per token with no markup on the underlying provider rate.
Input
Per 1M prompt tokens
$0.045
Output
Per 1M completion tokens
$0.150
A 1M-token prompt with 250K tokens of output costs about $0.082.