Backend & Runtime / Knowledge library
Function Calling
connect model outputs to external tools and systems
Why learn Function Calling?
Useful when a model needs to trigger APIs, database queries or application logic instead of only returning prose.
Where it came from
Function calling lets AI applications ask a model to emit structured arguments for developer-defined tools and integrations.
Build your understanding
Work through these exercises in order. Try the task before opening a reference.
- Summarize the official positioning for Function Calling in one paragraph.
- Identify the buyer, developer, or user workflow Function Calling is built for.
- Compare Function Calling with a neighboring catalog topic and name the boundary.
- List two implementation risks or adoption questions for Function Calling.
- Design a five-question evaluation that would test whether someone understands Function Calling.
Documentation and sources
- OpenAI function calling help (help.openai.com)
Catalog research notes
- Research snapshot: September 20, 2026. This entry summarizes the linked public documentation and should be refreshed before making version-specific claims.