NVIDIA Nemotron 3 Ultra 550B

Other · 1000K token context · text

Pricing: $0.69 per 1M input tokens, $3.45 per 1M output tokens

NVIDIA Nemotron 3 Ultra 550B-A55B - NVIDIA flagship reasoning model (550B total / 55B active MoE) tuned for agentic workloads, with a 1M-token context window.

Pricing

$0.69 per 1M input tokens and $3.45 per 1M output tokens. Billing is per token: input tokens are charged at the input rate and output tokens at the output rate, from one llmka.dev balance.

Prices checked 2026-11-04

Context and limits

The context window is 1,000,000 tokens (1000K).

The maximum output is 16,384 tokens.

When to use NVIDIA Nemotron 3 Ultra 550B

NVIDIA Nemotron 3 Ultra 550B (model ID `nvidia-nemotron-3-ultra-550b-a55b`) takes text input and returns text output.

Supported features in the catalog: function calling (tools), streamed responses over SSE, JSON-schema structured output.

Use NVIDIA Nemotron 3 Ultra 550B for text generation and chat.

FAQ

How much does NVIDIA Nemotron 3 Ultra 550B cost?

$0.69 per 1M input tokens and $3.45 per 1M output tokens. Billing is per token: input tokens are charged at the input rate and output tokens at the output rate, from one llmka.dev balance.

What is the context window and output limit of NVIDIA Nemotron 3 Ultra 550B?

The context window is 1,000,000 tokens (1000K). The maximum output is 16,384 tokens.

How do I get access to NVIDIA Nemotron 3 Ultra 550B?

Create an API key in the llmka.dev dashboard and send requests to model "nvidia-nemotron-3-ultra-550b-a55b" at https://api.llmka.dev/v1. The endpoint is OpenAI-compatible. One key and one balance cover all models on the gateway.

Links

All models and prices · API documentation · Quick start

Available through the llmka.dev gateway: OpenAI- and Anthropic-compatible endpoints, one key, USDT top-up.