Amazon Bedrock in Practice

Anthropic API Features on Bedrock: A Reference Availability Matrix

Before you commit an architecture to Bedrock, check this page. Most of the Claude API works there — but the gaps cluster in exactly the areas newer agentic designs depend on.

Claude 3P 101 · Updated July 2026 · Unofficial guide

Amazon Bedrock is an AWS-operated managed service, so Anthropic API capabilities arrive there on AWS's schedule rather than Anthropic's. As of July 2026 the pattern is clear: everything you need for request/response and client-side tool workloads is supported, while server-side tools, Anthropic-hosted infrastructure endpoints, and some newest conveniences are not. The tables below map the major capabilities; the summary reflects the official documentation as of this writing, and availability changes, so verify anything load-bearing against the sources at the end.

Supported on Bedrock

CapabilityStatusNotes
Messages API, streaming, tool useSupportedCore API; same request shape as first-party on the current surface
Vision (image input) and PDF inputSupportedBase64 content blocks; URL input sources are not supported
Prompt caching (5-minute and 1-hour)SupportedExplicit cache_control breakpoints only — automatic caching is not supported
Extended and adaptive thinkingSupportedManual budgets on older generations; adaptive on 4.7+ — see the model split
Structured outputs / strict tool useSupported
Token counting, citations, search-results blocksSupported
Fine-grained tool streamingSupported
Client-side tools: bash, text editor, memorySupportedComputer use is beta everywhere, including Bedrock
Tool searchSupported (partial)InvokeModel API only, not Converse
1M-token context windowSupportedFable 5, Opus 4.8/4.7/4.6, Sonnet 4.6; Sonnet 4.5 and older have 200K
Compaction and context editingBetaBeta across all platforms

Not supported on Bedrock

CapabilityWhat to do instead
Message Batches APIAWS's own S3-based batch inference (50% discount, no tool calling or structured output), or a queue-and-worker pattern
Files APIInline base64 content; stage files in S3
Server-side tools: web search, web fetch, code execution, advisorClient-side tool use with your own backend
Models, Admin, Compliance, Usage and Cost APIsAWS-native equivalents (console, IAM, CloudTrail, Cost Explorer)
Agent Skills (Messages API), MCP connector, programmatic tool callingOrchestrate client-side, or use 1P / Claude Platform on AWS
Claude Managed Agents, self-hosted sandboxes1P or Claude Platform on AWS (beta there)
Automatic prompt caching, cache diagnosticsExplicit breakpoints; monitor usage fields
URL input sources, mid-conversation system messages, server-side fallback (fallbacks), inference_geo, fast modeHandle client-side where applicable

How to read the gaps

Three observations help teams plan. First, nothing in the request/response core is missing — a typical enterprise workload of summarization, extraction, classification, RAG (retrieval-augmented generation), and client-executed tools ports to Bedrock without redesign. Second, the gaps are mostly Anthropic-hosted services: batches, file storage, server-side tools, and managed agent infrastructure are things Anthropic runs on its own platform, and on Bedrock the equivalent responsibilities shift to AWS services or your code. Third, each gap has a documented workaround, linked in the table above — the cost is engineering effort, not feasibility.

If a roadmap depends heavily on the missing column — particularly Managed Agents, MCP connector, or server-side web tools — consider Claude Platform on AWS, the Anthropic-operated service that runs inside AWS with typically same-day feature parity with the first-party API. Many organizations run both: Bedrock for AWS-native governed workloads, Claude Platform on AWS where feature velocity matters.

Rule of thumb: if the feature runs inside the model (thinking, vision, caching, tool use), expect it on Bedrock. If it runs on Anthropic's servers around the model (batches, files, web tools, agents), expect to build or substitute.

Where to go next

The homepage feature matrix compares all four platforms side by side; the feature-gaps overview covers Vertex AI too; and Bedrock vs. Claude Platform on AWS helps when the gaps above are decision-drivers.

Sources