Authorizations
JWT token for authentication
Headers
Model UUID for the request (e.g., f49b2e20-fef3-4441-9358-897f946b8ae2 for Llama 8B)
Body
application/json
Array of messages in the conversation
Model identifier
Available options:
llama3_1 Whether to stream the response
Sampling temperature
Required range:
0 <= x <= 2Maximum number of tokens to generate
Required range:
1 <= x <= 4096Nucleus sampling parameter
Required range:
0 <= x <= 1Sequences where the API will stop generating