Speka
Start free
All models
chatNVIDIA

Nemotron 3 Ultra 550B

NVIDIA's flagship open model: 550B parameters with 55B active per token. Frontier quality for demanding generation, analysis and agentic work.

nvidia/nemotron-3-ultra-550b-a55b
Running· verified 11 min ago · 971ms

What is Nemotron 3 Ultra 550B?

Nemotron 3 Ultra 550B is NVIDIA's chat model. NVIDIA's flagship open model: 550B parameters with 55B active per token. Frontier quality for demanding generation, analysis and agentic work. It runs on Speka's OpenAI-compatible /v1/chat/completions endpoint at $0.90 / 1M input and $2.70 / 1M output tokens, using the model ID nvidia/nemotron-3-ultra-550b-a55b.

Test it live

Live playgroundNemotron 3 Ultra 550Bin-browser demo

Test Nemotron 3 Ultra 550B live

Send a message and watch the model respond. Multi-turn — it remembers the conversation.

How to call Nemotron 3 Ultra 550B via the API

Speka exposes Nemotron 3 Ultra 550B on an OpenAI-compatible /v1/chat/completions endpoint. Point any OpenAI SDK at https://speka.me/v1, set model to nvidia/nemotron-3-ultra-550b-a55b, and your existing code runs unchanged.

quickstart.py
from openai import OpenAI

client = OpenAI(
    base_url="https://speka.me/v1",
    api_key="sk-speka-live-...",  # your Speka key
)

resp = client.chat.completions.create(
    model="nvidia/nemotron-3-ultra-550b-a55b",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)
FAQ

Frequently asked questions

Nemotron 3 Ultra 550B is NVIDIA's chat model. NVIDIA's flagship open model: 550B parameters with 55B active per token. Frontier quality for demanding generation, analysis and agentic work. It is available on Speka's OpenAI-compatible API using the model ID nvidia/nemotron-3-ultra-550b-a55b.
On Speka, Nemotron 3 Ultra 550B is priced at $0.90 / 1M input and $2.70 / 1M output tokens. Pricing is per-token with no subscription or seat fee — usage is billed against your plan's monthly allowance, then at the same rate with no overage penalty. Rates are current as of June 2026; check the pricing page for updates.
Speka exposes Nemotron 3 Ultra 550B on an OpenAI-compatible /v1/chat/completions endpoint. Set base_url to https://speka.me/v1, supply your Speka key, and set model to "nvidia/nemotron-3-ultra-550b-a55b" in any OpenAI SDK — no other code changes are required.
Nemotron 3 Ultra 550B supports a 128,000-token context window — roughly 96,000 words of input, suitable for long documents, multi-turn agents, and large-context tasks.
Yes. Nemotron 3 Ultra 550B is served through Speka's OpenAI-compatible endpoint, so any application built on the OpenAI Python or Node.js SDK, LangChain, or LlamaIndex can call it by changing only the base URL and model ID.

More chat models

Meta logo

Llama 3.3 70B Instruct

Meta
chat

Meta's flagship 70B instruct model — 405B-class quality at a fraction of the cost. A dependable default for production chat.

meta/llama-3.3-70b-instruct
Input / 1M
$0.20
Output / 1M
$0.20
Open model
Meta logo

Llama 3.1 8B Instruct

Meta
chat

Fast, cheap and capable. Ideal for high-volume classification, routing and lightweight chat.

meta/llama-3.1-8b-instruct
Input / 1M
$0.05
Output / 1M
$0.05
Open model
Meta logo

Llama 3.2 3B Instruct

Meta
chat

The smallest Llama instruct model — the cheapest way to run classification, routing and short replies at scale.

meta/llama-3.2-3b-instruct
Input / 1M
$0.03
Output / 1M
$0.03
Open model