nvidia/nemotron-3-ultra-550b-a55b idA 550B parameter (55B active) open reasoning model from NVIDIA, built for long-running agent workflows. It uses a hybrid Mamba-Transformer MoE architecture and supports a 1M token context window.
# Drop-in OpenAI-compatible client$ import { generateText } from 'ai'$$ const { text } = await generateText({$ model: 'nvidia/nemotron-3-ultra-550b-a55b',$ baseURL: 'https://synapse.garden/api/v1',$ apiKey: process.env.MG_KEY,$ prompt: 'Why is the sky blue?',$ })
| Rate | Per million tokens · USD |
|---|---|
| Input | $0.660/M |
| Output | $2.64/M |
| Cache read | $0.132/M |
Use the OpenAI or Anthropic SDK and point baseURL at https://synapse.garden/api/v1. Set model: ‘nvidia/nemotron-3-ultra-550b-a55b’ and supply your Synapse Garden API key. No code changes beyond the base URL.
Input: $0.660/M per million tokens. Output: $2.64/M per million tokens. The free tier includes a million tokens every month at no cost.
nemotron-3-ultra-550b-a55b supports a context window of 1M tokens, with a maximum output of 65K 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.