NVIDIA logo

NVIDIA Nemotron 3 Nano 30B API

nvidia/nemotron-3-nano-30b-a3b

Call NVIDIA Nemotron 3 Nano 30B through UberLLM’s OpenAI-compatible API — from $0.0008/M input and $0.0033/M output, routed automatically to the cheapest healthy seller. NVIDIA · 128,000 token context. Fee included.

Try it live — no signup
Demo · a few prompts a day, no sign-up

NVIDIA Nemotron 3 Nano 30B pricing

Price now · per 1M tokens
Input
$0.000817
Output
$0.00327
Cached input
$0.000122
% off list
99% off
List price · per 1M tokens
Input
$0.0825
Output
$0.33
Cached input
$0.0123
Providers and their list prices, per 1M tokens
ProviderInputOutputCached input
Venice AI$0.075$0.30$0.0113
Amazon Bedrock$0.075$0.30

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 Nano 30B with the OpenAI SDK

Already using the OpenAI SDK? Change one line — the base URL — and call NVIDIA Nemotron 3 Nano 30B with your existing code. Anthropic SDKs work against https://api.uberllm.dev/v1/messages.

python
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-nano-30b-a3b",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

NVIDIA Nemotron 3 Nano 30B API — FAQ

How much does the NVIDIA Nemotron 3 Nano 30B API cost?

NVIDIA Nemotron 3 Nano 30B is listed from $0.0008 per million input tokens and $0.0033 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 Nano 30B 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-nano-30b-a3b". Anthropic SDKs work via https://api.uberllm.dev/v1/messages.

Is NVIDIA Nemotron 3 Nano 30B OpenAI-compatible on UberLLM?

Yes. Every model on UberLLM — including NVIDIA Nemotron 3 Nano 30B — is served through one OpenAI-compatible endpoint, so you change only the base URL and key.

More NVIDIA models