Question 1

How much does llama-3.1-nemotron-nano-vl-8b-v1:free cost per 1M tokens?

Accepted Answer

Input is priced at $0.00 per 1M tokens, output at $0.00 per 1M tokens. Billing is per token, no rounding to batch sizes.

Question 2

How do I access llama-3.1-nemotron-nano-vl-8b-v1:free via API?

Accepted Answer

Send requests to the UnoRouter /v1/chat/completions endpoint with model=llama-3.1-nemotron-nano-vl-8b-v1:free. Any OpenAI-compatible client library works. Authentication uses a standard Bearer token.

Question 3

What is the context window of llama-3.1-nemotron-nano-vl-8b-v1:free?

Accepted Answer

llama-3.1-nemotron-nano-vl-8b-v1:free supports a context window of 16.4K tokens, shared between your prompt and the model's response.

NVIDIA: llama-3.1-nemotron-nano-vl-8b-v1:free

Pricing

Performance

Usage & Ranking

Frequently asked questions

Similar models