Post v1chatcompletions
Creates a model response for the given chat conversation. Supports streaming with SSE, documentation here.
Authorizations
Body
The ID of the project to use.
The ID of the session to use. It helps to track the chat history.
Options for Retrieval Augmented Generation (RAG). Will override launched model settings
A list of messages comprising the conversation so far.
ID of the model to use. See the model endpoint compatibility table for details.
The system prompt to use.
The maximum number of tokens to generate in the chat completion.
If set, partial message deltas will be sent, like in ChatGPT.
What sampling temperature to use, between 0 and 2.
The tools to use in the completion.
Response
A list of chat completion choices. Can be more than one if n is greater than 1.
The Unix timestamp (in seconds) of when the chat completion was created. Each chunk has the same timestamp.
The model to generate the completion.
The name of the provider that generated the completion.
The ID of the provider that generated the completion.
Chunks used to improve the completion
The usage statistics for the completion.
The trace ID of the completion.