{"version":"2.1.295","anchor":"gateway-bedrock-on-demand-throughput-error-gets-a-clearer-hi","canonical_anchor":"gateway-bedrock-on-demand-throughput-error-gets-a-clearer-hi","heading":"Apps gateway explains Bedrock's on-demand throughput error","tier":"notice","area":"LLM Gateway","scope":"org","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.295\/e\/gateway-bedrock-on-demand-throughput-error-gets-a-clearer-hi","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.295","markdown":"### Apps gateway explains Bedrock's on-demand throughput error\n\nWhen Bedrock rejects a model for on-demand use, the gateway now logs that it needs an inference profile and suggests mapping to one\n\n**What**\n\nWhen Bedrock rejects a request because a model ID cannot be invoked with on-demand throughput, the apps gateway now logs that the model runs only through an inference profile and advises mapping it to one. An inference profile is Bedrock's way of routing a model that cannot be called directly. The response headers from Bedrock's original error are kept.\n\n**Why**\n\nThis is a common Bedrock misconfiguration, and the log now says how to fix it.\n\n- Area: LLM Gateway\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 1\/5\n- Scope: org\n- Heads-up: no"}