Model Inference API

Atmos provides an OpenAI-compatible API for interacting with deployed models.

Base URL

All API requests should be made to:

https://api.atmos.dev/v1

Authentication

Authenticate your requests by including your API key in the Authorization header:

Authorization: Bearer YOUR_API_KEY

Chat Completions

To generate text using a chat model, use the /chat/completions endpoint.

Request Example

curl https://api.atmos.dev/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $ATMOS_API_KEY" \
-d '{
"model": "meta-llama/Llama-3-8b-chat-hf",
"messages": [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Hello!"
}
]
}'