Using Trinity-Large-Preview on OpenRouter

Implementation guide · Trinity · Arcee AI

ServerlessOpen Source

Quick Start

1
Create an account at OpenRouter and generate an API key.
2
Use the OpenRouter SDK or REST API to call arcee-ai/trinity-large-preview — see the documentation for request format.
3
You'll be billed $0.15/1M input, $0.45/1M output tokens. See full pricing.

API Portal Documentation Pricing Model Card

Code Examples

See OpenRouter documentation for integration details.

About OpenRouter

OpenRouter provides a unified interface for Large Language Models with better pricing, improved uptime, and no subscription requirements. Route across providers for cost optimization and reliability.

OpenRouter is a multi-provider LLM aggregator offering unified API access to 300+ models from all major labs and emerging providers, with automatic failover for reliability.

View all models on OpenRouter →

Pricing on OpenRouter

Type	Price (per 1M)
Input tokens	$0.15
Output tokens	$0.45

Capabilities

Function CallingTool 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

ArchitectureSparse Mixture of Experts (MoE)

OpenRouter, Inc.

New York, NY, USA