--- title: "AWS Bedrock Integration for Rig: Query AWS Bedrock Data in Plain English" description: "Connect AWS Bedrock to Rig and query your AWS Bedrock data in plain English, or ask it in Claude, ChatGPT and Cursor. Governed, validated answers from your warehouse." canonical: "https://rig.so/integrations/aws-bedrock" format: markdown --- Browse integrations ![AWS Bedrock logo](https://img.logo.dev/aws.amazon.com?token=pk_AdkTbLWDS1iunmvTK2qm1g&size=112&format=png&retina=true) Engineering & product ops Supported # AWS Bedrock integration for Rig ## The easiest way to connect AWS Bedrock to Claude and other AI tools Amazon Bedrock is the AWS service that hosts foundation models, and AWS Cost Explorer reports what each model costs per day. [Try Rig](https://app.rig.so/signup)[Book a demo](https://rig.so/book-demo) ## What Rig syncs from AWS Bedrock Once connected, Rig models these objects so questions resolve to the right tables and joins: - Daily cost per model and usage type - Input, output and cache token usage - Unblended and net unblended cost - Usage quantity and unit ## How AWS Bedrock connects to Rig Rig Ingest reads AWS Cost Explorer into your warehouse on a schedule, using an IAM access key from the account that pays the bill. Recent days are re-read until AWS closes the month's bill. [Read the step-by-step AWS Bedrock setup guide](https://rig.so/guides/connect-aws-bedrock) ## Track Bedrock spend by model Bedrock spend is what AWS bills for each model and usage type. Rig reads one row per day, per service and usage type, so you can see which models cost most, including third-party models sold through the AWS Marketplace. Ask Rig - What did Bedrock cost last month by model? - Which model's cost grew fastest this quarter? - Show daily Bedrock cost for the last 30 days ## Split cost by token type Usage types name the model and the kind of token, which is input, output, cache read or cache write. Rig keeps them as separate rows, so you can see how much comes from output tokens against input and cache. Ask Rig - What share of cost is output tokens? - How much do we spend on cache reads and writes? - Show tokens used per model for last week ## Reconcile model spend with the bill Reconciliation is checking that your own usage estimates match what AWS charged. Rig reads cost and quantity for each day, so you can set them against your gateway or application records. Ask Rig - What did AWS charge per day for Bedrock this month? - How do billed tokens compare with our application logs? - Which days have estimated costs that may still change? ## Ask your AWS Bedrock data in Claude, ChatGPT or Cursor Rig serves your AWS Bedrock data to AI assistants over MCP. Once AWS Bedrock is synced into your warehouse, you can ask questions in plain English from the tool you already use, and every answer is backed by validated, governed SQL. - [Claude](https://rig.so/integrations/claude) - [Claude Code](https://rig.so/integrations/claude-code) - [Cursor](https://rig.so/integrations/cursor) - [ChatGPT](https://rig.so/integrations/chatgpt) - [Codex](https://rig.so/integrations/codex) - [Gemini](https://rig.so/integrations/gemini) ## Frequently asked questions Can I see cost per person? No. Cost Explorer has no caller dimension, so the data is spend per model per day. Per-person use comes from the records of a gateway in front of Bedrock, if you run one. Does it cost anything to read? Each Cost Explorer request costs $0.01 on your AWS bill. A sync makes a few requests, and the first year-long read makes more. Which AWS account should the keys come from? The account that pays the bill. In an AWS Organization that is the management account, because a member account's keys only see that account's spend. ## Related integrations [![Anthropic logo](https://img.logo.dev/anthropic.com?token=pk_AdkTbLWDS1iunmvTK2qm1g&size=72&format=png&retina=true)AnthropicClaude API token usage, cost and Claude Code usage by person.](https://rig.so/integrations/anthropic)[![Asana logo](https://img.logo.dev/asana.com?token=pk_AdkTbLWDS1iunmvTK2qm1g&size=72&format=png&retina=true)AsanaTask throughput, cycle time and project health analytics from your Asana workspace.](https://rig.so/integrations/asana)[![Claude Compliance logo](https://img.logo.dev/anthropic.com?token=pk_AdkTbLWDS1iunmvTK2qm1g&size=72&format=png&retina=true)Claude ComplianceThe Claude Enterprise audit log, users, roles, projects and spend limits.](https://rig.so/integrations/anthropic-compliance)[![Claude Enterprise logo](https://img.logo.dev/anthropic.com?token=pk_AdkTbLWDS1iunmvTK2qm1g&size=72&format=png&retina=true)Claude EnterpriseClaude Enterprise cost, tokens and per-person activity across chat, Claude Code and Cowork.](https://rig.so/integrations/anthropic-enterprise)[![ClickUp logo](https://img.logo.dev/clickup.com?token=pk_AdkTbLWDS1iunmvTK2qm1g&size=72&format=png&retina=true)ClickUpTask throughput, workload and goal progress from your ClickUp workspace.](https://rig.so/integrations/clickup)[![Datadog logo](https://img.logo.dev/datadoghq.com?token=pk_AdkTbLWDS1iunmvTK2qm1g&size=72&format=png&retina=true)DatadogService Level Objectives and daily SLI history from Datadog.](https://rig.so/integrations/datadog) ## Connect AWS Bedrock data to AI tools like Claude Rig builds a governed context layer over your data so every team, and every AI tool, asks questions and gets answers they can trust. [Try Rig](https://app.rig.so/signup)[Book a demo](https://rig.so/book-demo) --- - [This page as HTML](https://rig.so/integrations/aws-bedrock) - [Site map for language models](https://rig.so/llms.txt) - [API and agent documentation](https://rig.so/developers)