Model inference¶
Select a model and generate replies, embeddings, or reranking results. Use the corresponding management task to store generation records or maintain local conversations.
Choose a task¶
Task |
Page |
Description |
|---|---|---|
Find and select a model |
Check models, capabilities, and prices available to the current credential. |
|
Generate replies with Chat Completions |
Send chat messages and read complete or streamed replies. |
|
Generate replies with Messages |
Optionally count input tokens and generate message replies. |
|
Generate and manage results with Responses |
Generate content and, when supported, store, retrieve, and delete results. |
|
Manage conversations and items |
Maintain local conversation metadata and item summaries. |
|
Generate embeddings |
Convert single or batch text inputs into vectors. |
|
Rerank documents |
Rerank existing candidates by relevance to a query. |