Opper home page
Search...
⌘K
Documentation
API Reference
List of models
API Reference
API Reference
Authentication
Errors
Task API
Introduction
POST
Call LLM
POST
Stream LLM Call
Platform APIs
Models
Functions
Observability
Knowledge base
Datasets
Analytics
Other
Support
Discord
Login
Version 2.x
Opper home page
Version 2.x
Search...
⌘K
Ask AI
Support
Discord
Login
Login
Search...
Navigation
Task API
Call
Task API
Call
Copy page
Endpoint for issuing a task to an LLM
The
call endpoint
is a declarative endpoint for completing tasks with AI. It supports declaring tasks in a highly model agnostic way focusing on input and output schemas.
Common operations
Specify your task with small instruction, input schema and output schema.
Optionally specify one or more models to utilize to complete the task
Optionally specify examples for the model to understand successful completions.
Optionally specify few shot configuration to enable automatic retrieval of examples from a dataset. See
functions
.
Optionally specify caching configuration to avoid repeating generations for repeating tasks.
Optionally add tags to be able to do comprehensive analytics
Previous
Call LLM
The Call endpoint is a simple interface to issue a task to an LLM. It is a declarative interface with input and output schemas that supports text, image, audio inputs and outputs and is highly model agnostic.
Next
On this page
Common operations
Assistant
Responses are generated using AI and may contain mistakes.