NVIDIA Nemotron 3 Ultra 550B API
nvidia/nemotron-3-ultra-550b-a55b
Call NVIDIA Nemotron 3 Ultra 550B through UberLLM’s OpenAI-compatible API — from $0.0055/M input and $0.0275/M output, routed automatically to the cheapest healthy seller. NVIDIA · 1,000,000 token context. Fee included.
NVIDIA Nemotron 3 Ultra 550B pricing
- Input
- $0.0055
- Output
- $0.0275
- Cached input
- $0.000825
- Input
- $0.6875
- Output
- $3.4375
- Cached input
- $0.2063
| Provider | Input | Output |
|---|---|---|
| Fireworks AI | $0.50 | $2.50 |
| Jatevo | $0.50 | $2.50 |
UberLLM routes every request to the cheapest healthy seller for this model. The price shown includes UberLLM’s 10% fee.
How to use NVIDIA Nemotron 3 Ultra 550B with the OpenAI SDK
Already using the OpenAI SDK? Change one line — the base URL — and call NVIDIA Nemotron 3 Ultra 550B with your existing code. Anthropic SDKs work against https://api.uberllm.dev/v1/messages.
from openai import OpenAI
client = OpenAI(
base_url="https://api.uberllm.dev/v1",
api_key="ull_your_key_here",
)
resp = client.chat.completions.create(
model="nvidia/nemotron-3-ultra-550b-a55b",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)NVIDIA Nemotron 3 Ultra 550B API — FAQ
How much does the NVIDIA Nemotron 3 Ultra 550B API cost?
NVIDIA Nemotron 3 Ultra 550B is listed from $0.0055 per million input tokens and $0.0275 per million output tokens through UberLLM, which routes each request to the cheapest healthy seller on a live marketplace and bills the price shown, which includes UberLLM's 10% fee.
How do I call NVIDIA Nemotron 3 Ultra 550B via API?
Use any OpenAI-compatible SDK: set the base URL to https://api.uberllm.dev/v1, your UberLLM API key, and model "nvidia/nemotron-3-ultra-550b-a55b". Anthropic SDKs work via https://api.uberllm.dev/v1/messages.
Is NVIDIA Nemotron 3 Ultra 550B OpenAI-compatible on UberLLM?
Yes. Every model on UberLLM — including NVIDIA Nemotron 3 Ultra 550B — is served through one OpenAI-compatible endpoint, so you change only the base URL and key.