AI Cache Changelog
Released changes to the AI Cache plugin (`ai-cache`), newest release first.
14 released changes name ai-cache, newest release first — 4 in Apache APISIX, 10 in API7 Gateway. Each row links to the change itself.
| Release | Date | Type | Change |
|---|
| 3.10.7 (opens in API7 Gateway docs) | 2026-09-08 | Fix | Fixed issue: Under the passthrough protocol, requests with the same body but a different method, path or query string shared one cache entry, so a request to /v1/images/generations on a wildcard route could be served… (opens in API7 Gateway docs) |
| 3.10.4 (opens in API7 Gateway docs) | 2026-07-27 | Feature | Added Redis connection keepalive settings (redis_keepalive_timeout and redis_keepalive_pool) to the Redis and Redis Cluster policies in Limit Conn, Limit Req, and AI Cache, so operators can tune idle timeout and conne… (opens in API7 Gateway docs) |
| 3.10.3 (opens in API7 Gateway docs) | 2026-07-14 | Feature | Added a semantic (L2) cache layer that matches prompts by embedding similarity through RediSearch, in addition to exact-match caching. Streaming LLM responses can now be cached and replayed instead of being bypassed.… (opens in API7 Gateway docs) |
| 3.10.3 (opens in API7 Gateway docs) | 2026-07-14 | Change | ai-cache: semantic.embedding.openai.api_key, semantic.embedding.azure_openai.api_key (opens in API7 Gateway docs) |
| 3.10.2 (opens in API7 Gateway docs) | 2026-06-29 | Feature | AI Cache (new plugin): Caches LLM responses so that identical requests are served from a cache instead of calling the upstream model again. Exact-match caching is keyed on the normalized request body and stored in Red… (opens in API7 Gateway docs) |
| 3.10.2 (opens in API7 Gateway docs) | 2026-06-29 | Change | ai-cache: redis_password (opens in API7 Gateway docs) |
| 3.9.20 (opens in API7 Gateway docs) | 2026-09-03 | Fix | Fixed issue: Under the passthrough protocol, requests with the same body but a different method, path or query string shared one cache entry, so a request to /v1/images/generations on a wildcard route could be served… (opens in API7 Gateway docs) |
| 3.9.17 (opens in API7 Gateway docs) | 2026-07-28 | Feature | Added Redis connection keepalive settings (redis_keepalive_timeout and redis_keepalive_pool) to the Redis and Redis Cluster policies in Limit Conn, Limit Req, and AI Cache, so operators can tune idle timeout and conne… (opens in API7 Gateway docs) |
| 3.9.16 (opens in API7 Gateway docs) | 2026-07-10 | Feature | AI Cache (new plugin): Caches LLM responses in Redis so repeated prompts can be served without calling the upstream model again. It supports exact-match caching, optional semantic (L2) matching through embeddings and… (opens in API7 Gateway docs) |
| 3.9.16 (opens in API7 Gateway docs) | 2026-07-10 | Change | ai-cache: redis_password, semantic.embedding.openai.api_key, semantic.embedding.azure_openai.api_key (opens in API7 Gateway docs) |
