Meta Llama API

Use Meta's hosted Llama models with LlamaAPIModel. Requires the llamaapi optional extra on elsai-model.

For standalone invoke / stream usage, see LLM Models — Meta Llama API.

Install

pip install --extra-index-url https://core-packages.elsai.ai/root/ "elsai-model[llama-api]==2.1.0"
pip install --extra-index-url https://elsai-agents.elsai.ai/root/ elsai-agents==0.3.1

Setup

1. Create a Meta Llama API key.
2. Export credentials and your model ID:

export LLAMA_API_KEY=...
export LLAMA_API_MODEL_ID=Llama-4-Maverick-17B-128E-Instruct-FP8

Agent — basic

import os
from elsai import Agent
from elsai_model import LLM, Provider

model = LLM(
    provider=Provider.LLAMA_API,
    model=os.environ["LLAMA_API_MODEL_ID"],
    api_key=os.environ["LLAMA_API_KEY"],
    temperature=0.2,
)
agent = Agent(
    model=model,
    system_prompt="You are a concise assistant.",
)
result = agent("Summarize what an AI agent is in two sentences.")
print(result)