AI Rate Limiting Changelog
Released changes to the AI Rate Limiting plugin (`ai-rate-limiting`), newest release first.
23 released changes name ai-rate-limiting, newest release first — 7 in Apache APISIX, 16 in API7 Gateway. Each row links to the change itself.
| Release | Date | Type | Change |
|---|
| 3.10.3 (opens in API7 Gateway docs) | 2026-07-14 | Feature | Added Redis connection keepalive settings (redis_keepalive_timeout and redis_keepalive_pool) for the Redis and Redis Cluster policies in Limit Count, Limit Count Advanced, GraphQL Limit Count, and AI Rate Limiting, so… (opens in API7 Gateway docs) |
| 3.10.3 (opens in API7 Gateway docs) | 2026-07-14 | Fix | Fixed issue: Some configured Redis fields were dropped and replaced with defaults — redis_username/redis_password for the redis-sentinel policy and redis_keepalive_timeout/redis_keepalive_pool for the redis and redis-… (opens in API7 Gateway docs) |
| 3.10.2 (opens in API7 Gateway docs) | 2026-06-29 | Change | ai-rate-limiting: redis_password, sentinel_password (opens in API7 Gateway docs) |
| 3.9.16 (opens in API7 Gateway docs) | 2026-07-10 | Feature | Added Redis connection keepalive settings (redis_keepalive_timeout and redis_keepalive_pool) for the Redis and Redis Cluster policies in Limit Count, Limit Count Advanced, GraphQL Limit Count, and AI Rate Limiting, so… (opens in API7 Gateway docs) |
| 3.9.16 (opens in API7 Gateway docs) | 2026-07-10 | Change | ai-rate-limiting: redis_password, sentinel_password (opens in API7 Gateway docs) |
| 3.9.11 (opens in API7 Gateway docs) | 2026-04-30 | Fix | Fixed issue: AI instance names containing dots (such as Qwen3.5-397B-10.249.238.157) caused HTTP 500 errors because the name was incorrectly interpreted as a ctx.var path expression instead of a constant key. (opens in API7 Gateway docs) |
| 3.9.10 (opens in API7 Gateway docs) | 2026-04-22 | Fix | Fixed issue: Upstream-provided usage keys (from LLM response usage data) that collided with reserved expression environment names (such as math or abs) could shadow built-in functions, potentially breaking rate limiti… (opens in API7 Gateway docs) |
| 3.9.8 (opens in API7 Gateway docs) | 2026-04-07 | Feature | Added a new expression limit strategy with the cost_expr field, allowing dynamic token cost calculation using custom Lua arithmetic expressions. For example, input_tokens + cache_creation_input_tokens enables cache-aw… (opens in API7 Gateway docs) |
| 3.9.8 (opens in API7 Gateway docs) | 2026-04-07 | Fix | AI Rate Limiting, Limit Conn, Limit Req: Fixed issue: $env:// and $secret:// references in Redis host configuration were passed as literal strings instead of being resolved to their actual values, causing Redis connec… (opens in API7 Gateway docs) |
| 3.8.21 (opens in API7 Gateway docs) | 2025-12-23 | Fix | Limit Conn/Limit Count Advanced/AI Rate Limiting: Fixed issue: The rules.key field did not support the variable default value syntax. (opens in API7 Gateway docs) |
| 3.8.19 (opens in API7 Gateway docs) | 2025-12-09 | Fix | AI Rate Limiting/Limit Count Advanced: Fixed issue: When multiple rules were matched simultaneously, the rate-limiting headers could not be distinguished. By default, they are now distinguished by the index of the mat… (opens in API7 Gateway docs) |
| 3.8.19 (opens in API7 Gateway docs) | 2025-12-09 | Fix | AI Rate Limiting/Limit Count Advanced: Fixed issue: When variables were used in the limit field, the rate-limiting status was not updated in real-time after the variable's value changed. (opens in API7 Gateway docs) |
| 3.8.19 (opens in API7 Gateway docs) | 2025-12-09 | Feature | Supported using Redis, Redis Cluster, and Redis Sentinel as storage backends. (opens in API7 Gateway docs) |
| 3.8.17 (opens in API7 Gateway docs) | 2025-11-10 | Feature | Added a rules field for configuring multiple rate-limiting rules simultaneously. (opens in API7 Gateway docs) |
| 3.8.17 (opens in API7 Gateway docs) | 2025-11-10 | Feature | Supported variable syntax in the limit and time_window fields. (opens in API7 Gateway docs) |
| 3.7.0 (opens in API7 Gateway docs) | 2025-03-10 | Feature | Introduced new AI plugin which enforces token-based rate limiting for requests sent to LLM services. It helps manage API usage by controlling the number of tokens consumed within a specified time frame, ensuring fair… (opens in API7 Gateway docs) |
