Question 1

What is the cost of Llama-Guard-3-8B by Nebius Token Factory?

Accepted Answer

Llama-Guard-3-8B by Nebius Token Factory costs $0.02 per 1M input tokens and $0.06 per 1M output tokens. Cached reads cost $0.0020 per 1M tokens. Cache writes cost $0.03 per 1M tokens.

Question 2

What is the context window of Llama-Guard-3-8B by Nebius Token Factory?

Accepted Answer

Llama-Guard-3-8B by Nebius Token Factory has a context window of 8K tokens. It supports up to 8K input tokens and can generate up to 1K output tokens.

Question 3

What are the capabilities of Llama-Guard-3-8B by Nebius Token Factory?

Accepted Answer

Llama-Guard-3-8B by Nebius Token Factory supports structured output. It has open weights.

Question 4

What input and output types does Llama-Guard-3-8B support?

Accepted Answer

Llama-Guard-3-8B by Nebius Token Factory accepts text as input and can generate text as output.

Question 5

Is Llama-Guard-3-8B by Nebius Token Factory open source?

Accepted Answer

Yes, Llama-Guard-3-8B by Nebius Token Factory has open weights, meaning the model weights are publicly available for download and self-hosting.

Question 6

What is the knowledge cutoff date for Llama-Guard-3-8B?

Accepted Answer

Llama-Guard-3-8B by Nebius Token Factory has a knowledge cutoff date of 2024-04. This means the model was trained on data available up until that date.

Llama-Guard-3-8B API

Input Modalities

Output Modalities

Standard (per 1M tokens)

Caching (per 1M tokens)