Remote-Hosted Distributions

Remote-hosted distributions are Llama Stack endpoints hosted by partners that you can connect to directly.

Distribution	Endpoint	Inference
Together	https://llama-stack.together.ai	remote::together
Fireworks	https://llamastack-preview.fireworks.ai	remote::fireworks

Connecting

Point any OpenAI-compatible client at the endpoint:

from openai import OpenAI

client = OpenAI(
    base_url="https://llama-stack.together.ai/v1",
    api_key="your-together-api-key",
)

response = client.chat.completions.create(
    model="meta-llama/Llama-3.2-3B-Instruct",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Or use the CLI:

pip install llama-stack-client
llama-stack-client configure --endpoint https://llama-stack.together.ai
llama-stack-client models list

Connecting​

Connecting