NVIDIA models Call them through one OpenAI-compatible API, billed at base per-token rates.
Last updated June 5, 2026
Per 1M tokens, billed from your credit balance — no markup on usage. Prices load live from our catalogue.
| Model | Provider | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
| Nemotron 3 Super | NVIDIA | 1M | $0.09 | $0.45 |
| Nemotron 3 Nano 30B A3B | NVIDIA | 262K | $0.05 | $0.20 |
Keep the OpenAI SDK; set base_url to Zylo and pick a NVIDIA model id.
from openai import OpenAI
client = OpenAI(api_key="ZYLO_KEY", base_url="https://api.zyloai.net/v1")
response = client.chat.completions.create(
model="nemotron",
messages=[{"role": "user", "content": "Hello from Zylo!"}],
)
print(response.choices[0].message.content)
Zylo currently offers 2 NVIDIA text models, including Nemotron 3 Super, Nemotron 3 Nano 30B A3B. See the table above for live per-1M-token pricing.
Each NVIDIA model is billed at its base per-token rate, deducted from prepaid credits — no markup on usage. Zylo's 25% platform fee applies only when you add credits.
Yes. Point any OpenAI SDK at https://api.zyloai.net/v1, use your Zylo key, and set the model id (e.g. nemotron).
Free API key, OpenAI-compatible, local payments.
Get free API key