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 delivers exceptional performance in creative writing, storytelling, role-play, and conversational scenarios—surpassing the capabilities of typical reasoning models, particularly in real-time voice assistance. Furthermore, this model introduces advanced agentic capabilities; it is specifically optimized to navigate agent frameworks like OpenCode, Cline, and Kilo Code, while seamlessly managing intricate toolchains and extensive, constraint-heavy prompts. The architecture natively supports massive context windows of up to 512k tokens, though the current Preview API is served at a 128k context using 8-bit quantization for efficient deployment. Trinity-Large-Preview is a testament to Arcee’s efficiency-first design, providing a production-grade frontier model with open weights and permissive licensing tailored for both real-world deployment and rigorous experimentation.
Retired on Apr 24, 2026: requests to this model ID now return an error. These models are live and work with the same API key.
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.
No. Trinity Large Preview (free) was retired on NagaAI on Apr 24, 2026, and requests to it now return an error. Live models you can use instead with the same API key: LFM3-1.7B, Flint and Xing4.0 29B A4B.
It takes text as input and returns text.
