ModelRefs / API Versioning — AI Glossary
API Versioning — AI Glossary
The practice of releasing backward-compatible and breaking-change API versions, enabling callers to upgrade on their own timeline.
Overview
LLM APIs handle versioning differently: OpenAI uses model string versioning (the API endpoint is stable); Anthropic uses anthropic-version header (2023-06-01 current). Breaking changes include: message format changes, tool call schema updates, or deprecated endpoints. API version pinning is critical for production stability.
Reference details
| Topic | ecosystem |
|---|---|
| Last reviewed | 2026-06-24 |
Related terms
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to API Versioning — AI Glossary.
Frequently asked questions
What is API Versioning?
The practice of releasing backward-compatible and breaking-change API versions, enabling callers to upgrade on their own timeline.
What concepts are related to API Versioning?
Closely related concepts include model version, openai api, anthropic api.