Arcee AI
Arcee AI: Trinity Mini
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.
| Specifications | |
|---|---|
| Provider | Arcee AI |
| Input pricing | $0.04/M tokens |
| Output pricing | $0.15/M tokens |
| Context length | 131K tokens |
| Max output | 131K tokens |
| Input modalities | text |
| Output modalities | text |
| Tokenizer | Other |
| Content moderated | No |
| HuggingFace | arcee-ai/Trinity-Mini |
Supported Parameters
include_reasoningmax_tokensreasoningresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_p