{
  "id": 19704208,
  "title": "Four Amazon Bedrock inference choices that affect cost",
  "url": "https://urgent.news/2026/11/12/four-amazon-bedrock-inference-choices-that-affect-cost",
  "topic": "ai",
  "section": "AI",
  "published": "2026-11-12T20:51:55.000Z",
  "source": {
    "name": "AWS Machine Learning",
    "slug": "aws-machine-learning",
    "url": "https://aws.amazon.com/blogs/machine-learning/four-amazon-bedrock-inference-choices-that-affect-cost/"
  },
  "original_language": "en",
  "account": null,
  "summary": "Amazon Bedrock inference costs can be influenced by various request-level choices, including cache duration, service tier, reasoning effort, and maxTokens. These factors can affect the number of tokens processed and the rate applied to them, without changing the model or prompt. The guide provides information on testing these options and verifying their impact through response metadata, logs, and billing data. To explore these settings, users can refer to the Amazon Bedrock Samples notebooks and GitHub repositories for sample codes that set specific model IDs and inference parameters. By adjusting the model ID and inference parameters, users can optimize their Amazon Bedrock inference costs according to their workload and desired performance.",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}