Back to Models
meta-llama logo
meta-llama/llama-3-1-405b
Not Available

Llama 3.1 405B (base)

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This is the base 405B pre-trained version. It has demonstrated strong performance compared to leading closed-source models in human evaluations. To read more about the model release, [click here](https://ai.meta.com/blog/meta-llama-3/). Usage of this model is subject to [Meta's Acceptable Use Policy](https://llama.meta.com/llama3/use-policy/).

8/2/2024
32,768 tokens

Specifications

Modalities

Input
text
Output
text

Supported Parameters

frequency_penalty
logit_bias
max_tokens
min_p
presence_penalty
repetition_penalty
seed
stop
temperature
top_k
top_p

Max Output Tokens

32,768

Frequently asked questions

Is Llama 3.1 405B (base) available on FastMetal?
Not at the moment. GLM 5.3 Flash, from the same lab, is available on the FastMetal API today.
What is the context window of Llama 3.1 405B (base)?
32,768 tokens, shared between the prompt and the response.