arcee-ai/trinity-large-preview idTrinity Large (Preview) is a 400B-parameter (13B active) sparse mixture-of-experts language model, engineered to scale model capacity while maintaining inference efficiency over long contexts, with strong performance in reasoning-heavy workloads including math, coding-related tasks, and multi-step agent workflows.
# Drop-in OpenAI-compatible client$ import { generateText } from 'ai'$$ const { text } = await generateText({$ model: 'arcee-ai/trinity-large-preview',$ baseURL: 'https://synapse.garden/api/v1',$ apiKey: process.env.MG_KEY,$ prompt: 'Why is the sky blue?',$ })
| Rate | Per million tokens · USD |
|---|---|
| Input | $0.275/M |
| Output | $1.10/M |
Use the OpenAI or Anthropic SDK and point baseURL at https://synapse.garden/api/v1. Set model: ‘arcee-ai/trinity-large-preview’ and supply your Synapse Garden API key. No code changes beyond the base URL.
Input: $0.275/M per million tokens. Output: $1.10/M per million tokens. The free tier includes a million tokens every month at no cost.
trinity-large-preview supports a context window of 131K tokens, with a maximum output of 131K tokens.
No. Synapse Garden is the single API surface — one key gives you OpenAI, Anthropic, Google, Meta, Mistral, DeepSeek, xAI, Cohere, and more. Billing, rate limits, and audit logs are unified.
Sign up, create a key, drop our base URL into your existing client. The free tier includes a million tokens every month — no credit card.