Using Trinity-Large-Preview on Arcee AI

Implementation guide · Trinity · Arcee AI

ServerlessOpen Source

Arcee AI exposes Trinity-Large-Preview through model ID trinity-large-preview. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-06-29. Next refresh: weekly.

Quick Start

1
Create an account at Arcee AI and generate an API key.
2
Use the Arcee AI SDK or REST API to call trinity-large-preview.

API Portal Model Card

Code Examples

Code examples for this provider have not been sourced yet.

Pricing on Arcee AI

Capabilities

JSON / Tool useStructured Outputs

About Trinity-Large-Preview

400B sparse MoE instruct model with 13B active parameters per token, served at 128K context via 8-bit quantized API. Trained on 20T tokens. Production-ready for agentic and tool-use applications; predecessor to Trinity-Large-Thinking. Available free on OpenRouter.

Full model details →

Model Specs

Released2026-01-27

Parameters400B

Context128k

ArchitectureMixture of Experts