nemotron-3-ultra-550b-a55b

Name: nvidia/nemotron-3-ultra-550b-a55b
Brand: NVIDIA
Price: 0.7999999999999999 USD
Availability: InStock

NVIDIAAdded Jul 11, 2026

Get API key Read the docs

Model idnvidia/nemotron-3-ultra-550b-a55b

NVIDIA's open model for high-throughput reasoning and long-running agent workflows, 550B parameters with 55B active. Tuned for agent orchestration and coding agents, with NVIDIA claiming up to 30% lower cost than other leading open models.

Cost /1M tokens

$0.80input

$0.20cached

$3.00output

Context

256Ktokens

Live speed

365 tok/s · 0.45s to first token

Speed

Throughput users got on nemotron-3-ultra-550b-a55b with Keln API in the last 24 hours.

Latency

Time to first token users got on nemotron-3-ultra-550b-a55b with Keln API in the last 24 hours.

Capabilities

Input

Text

Tool calling

Yes

JSON output

Yes

Reasoning

Yes

Web search

With opt-in

Data retention

Zero

Use the API

Create an API key, save it to KELN_API_KEY, then call the endpoint below.

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.keln.ai/v1/",
    api_key=os.environ.get("KELN_API_KEY"),
)

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