Together AI

Together AI: Nemotron 3 Ultra 550B A55B (Together)

stable

Nemotron 3 Ultra 550B A55B (Together) is available through Everstack's OpenAI-compatible gateway with routing, fallback, retries, and observability.

nvidia__nemotron-3-ultra-550b-a55bnemotronreleased Jun 4, 2026
ProviderQuick start
Context
512.3K
tokens
Max output
512.3K
tokens
Input
$0.60
per 1M
Output
$3.60
per 1M

Activity

Daily period usage
Aggregated managed Everstack traffic. Buckets below 5 tenants or 100 requests are withheld.

Providers

ProviderContextInput /MOutput /M
NVIDIA NIM
NVIDIA NIM
1M$0.50$2.50
OpenRouter
OpenRouter
512.3K$0.60$3.60
Together AI
Together AI
512.3K$0.60$3.60

Pricing

ItemPriceUnit
Input$0.60per 1M tokens
Output$3.60per 1M tokens
Cache read$0.20per 1M tokens

Performance

Reliability

Compare

Compare usage and performance
Place this model beside up to three other catalog models.

Capabilities

Capabilities
Modalities
Input
Output
Details
Model ID
nvidia__nemotron-3-ultra-550b-a55b
Family
nemotron
Status
stable
Knowledge
-
Released
Jun 4, 2026
Gateway Config
API
2024-01-01
Auth
TOGETHER_API_KEY
Discovery
static
Provider type
meta

Quick Start

index.ts
import Everstack from "@everstack/node";const client = new Everstack({  apiKey: process.env.EVERSTACK_API_KEY!,  baseUrl: "https://{instance}.{region}.everstack.ai",});const completion = await client.chat.completions.create({  model: "@together/nvidia__nemotron-3-ultra-550b-a55b",  messages: [{ role: "user", content: "Explain vector cache routing." }],});console.log(completion.choices[0]?.message?.content);

Endpoint

Base URL
https://api.together.xyz/v1
Chat completions
https://api.together.xyz/v1/chat/completions
Model
nvidia__nemotron-3-ultra-550b-a55b
Auth env
TOGETHER_API_KEY

Nemotron 3 Ultra 550B A55B (Together) FAQ

How much does the Nemotron 3 Ultra 550B A55B (Together) API cost?

Through Together AI, Nemotron 3 Ultra 550B A55B (Together) costs $0.60 per 1M input tokens and $3.60 per 1M output tokens. The lowest input price in the catalog is $0.50 per 1M tokens on NVIDIA NIM.

What is the context window of Nemotron 3 Ultra 550B A55B (Together)?

Nemotron 3 Ultra 550B A55B (Together) accepts up to 512.3K tokens of context and returns up to 512.3K output tokens on Together AI.

Which providers offer Nemotron 3 Ultra 550B A55B (Together)?

Nemotron 3 Ultra 550B A55B (Together) is available from NVIDIA NIM, OpenRouter and Together AI. Everstack can route between them with automatic fallback when one is unavailable.

What can Nemotron 3 Ultra 550B A55B (Together) do?

Nemotron 3 Ultra 550B A55B (Together) supports chat, function calling and reasoning. It accepts text input.

How do I call Nemotron 3 Ultra 550B A55B (Together) through Everstack?

Point any OpenAI-compatible SDK at your Everstack gateway and set the model to @together/nvidia__nemotron-3-ultra-550b-a55b. Everstack adds retries, provider fallback, caching, per-tenant budgets and OpenTelemetry traces for every request.