Nemotron Nano 12B v2 VL
NVIDIA Nemotron Nano 12B v2 VL multimodal vision-language model.
API Model ID
nemotron-nano-12b-v2
Developer
NVIDIA
Context Window
131K tokens
Median Latency (TTFT)
—
Capabilities & Features
Vision Tools Structured Output
Pricing & Access
Current price
| Tier | Input / 1M | Cache Read / 1M | Cache Write / 1M | Output / 1M |
|---|---|---|---|---|
| Tier 1 | $0.1 | $0.01 | — | $0.3 |
Rates above are current PAYG prices; promotions and context tiers may apply. PAYG billing is separate from monthly plan allowances.
API Usage Example (/v1/chat/completions)
BotConnector provides an OpenAI-compatible chat completions endpoint.
cURL
curl https://api.botconnector.id/v1/chat/completions \
-H "Authorization: Bearer $BOTCONNECTOR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nemotron-nano-12b-v2",
"messages": [
{"role": "user", "content": "Hello from BotConnector!"}
]
}'Python (OpenAI SDK)
from openai import OpenAI
import os
client = OpenAI(
base_url="https://api.botconnector.id/v1",
api_key=os.environ.get("BOTCONNECTOR_API_KEY")
)
response = client.chat.completions.create(
model="nemotron-nano-12b-v2",
messages=[
{"role": "user", "content": "Explain machine learning concisely."}
]
)
print(response.choices[0].message.content)Provider & Infrastructure Disclaimer
This model was developed by NVIDIA. BotConnector accesses models via official developer APIs or verified large-scale cloud providers. BotConnector does not rebrand or alter original developer attributions.