
Amazon Bedrock now supports Service Quotas for the bedrock-mantle endpoint, allowing customers to view and track inference limits for input and output tokens per minute across supported models in the AWS Service Quotas console.


<div><p>This article announces that Amazon Bedrock now expands Service Quotas support to include the bedrock-mantle endpoint, providing customers with visibility into inference limits.</p><ul><li>Bedrock-mantle endpoint quotas now visible through AWS Service Quotas console</li><li>Supports OpenAI Responses API, Chat Completions API, and Anthropic Messages API</li><li>Exposes per-model input and output tokens-per-minute quotas</li><li>Enables proactive production scaling and limit planning</li><li>Available across all AWS regions where bedrock-mantle is offered</li></ul><p>This expansion provides customers with consistent quota tracking for bedrock-mantle, matching existing bedrock-runtime visibility and simplifying limit management.</p></div>


Amazon Bedrock expands support for Service Quotas

Related articles

Related articles

Jul 1
2026
Amazon Bedrock AgentCore increases default runtime quota limits

Nov 26
2025
Amazon Bedrock introduces Reserved Service tier

Feb 25
2025
Amazon Bedrock Guardrails announces an increase in service quota limits

Mar 10
2026
Amazon Bedrock now supports observability of First Token Latency and Quota Consumption