FreeFree
Context window 256K
nvidia-nemotron-3.5-lightning-free
NVIDIA: Nemotron 3.5 LightningNVIDIA
Context window1Mtokens
Input priceFree
Output priceFree
Abilities
| Ability | What it means |
|---|---|
| –Image input | You send an image in the message and ask about it. |
Limits
| Item | Value | Notes |
|---|---|---|
| Context window | 1,000,000 tokens | How much text the model can take into account at once: your messages and its replies together. |
| Maximum reply length | See dashboard and docs | The most tokens the model can write in a single reply. |
| Requests per minute | See dashboard and docs | Depends on your plan. |
| Tokens per minute | See dashboard and docs | Depends on your plan. |
Sample request
In your code, use the model name shown at the top of this page as the model id. Get your key from the dashboard.
import requests BASE = "https://hoveydai.ir/v1"changedAPI_KEY = "hvd_..." reply = requests.post( f"{BASE}/chat/completions", headers={"Authorization": f"Bearer {API_KEY}"}, json={"model": "nvidia-nemotron-3.5-lightning-free", "messages": [{"role": "user", "content": "hello"}]},)print(reply.json()["choices"][0]["message"]["content"])
Related models