Docs
Plugin HubCategoriesAIAI Lakera GuardChangelog

AI Lakera Guard Changelog

Released changes to the AI Lakera Guard plugin (`ai-lakera-guard`), newest release first.

8 released changes name ai-lakera-guard, newest release first — 3 in Apache APISIX, 5 in API7 Gateway. Each row links to the change itself.

Apache APISIX

ReleaseDateTypeChange
3.18.02026-08-18FeatureAdd ai-lakera-guard plugin
3.18.02026-08-18FeatureScan LLM responses (direction output/both, non-streaming and streaming)
3.18.02026-08-18FixUpdate alert mode behavior with the fail_open option

API7 Gateway

ReleaseDateTypeChange
3.10.3 (opens in API7 Gateway docs)2026-07-14FixFixed issue: In streaming responses with action: alert and fail_open: false, a Lakera API error or timeout could let the streamed response through instead of failing closed. Lakera errors are now handled according to… (opens in API7 Gateway docs)
3.10.2 (opens in API7 Gateway docs)2026-06-29FeatureAI Lakera Guard (new plugin): Screens AI traffic through the Lakera Guard API to detect prompt injection and other unsafe content. The direction option (input, output, or both) selects whether the plugin scans the req… (opens in API7 Gateway docs)
3.10.2 (opens in API7 Gateway docs)2026-06-29Changeai-lakera-guard: api_key (opens in API7 Gateway docs)
3.9.16 (opens in API7 Gateway docs)2026-07-10FeatureAI Lakera Guard (new plugin): Screens AI traffic through the Lakera Guard API to detect prompt injection and other unsafe content. The direction option (input, output, or both) selects whether the plugin scans request… (opens in API7 Gateway docs)
3.9.16 (opens in API7 Gateway docs)2026-07-10Changeai-lakera-guard: api_key (opens in API7 Gateway docs)

Configuration

Previous Page

AI Prompt Decorator

Next Page