Receipts

Primary sources behind the magic

MagicClaude cites official Anthropic documentation for capability claims and keeps demo claims narrower than the source material.

Editorial rules

  1. Capability claims cite official Anthropic docs or Claude Help Center pages.
  2. Demo output is described as expected behavior, not a guaranteed transcript. No page on this site reproduces a Claude transcript it did not actually produce.
  3. Every demo names the model it is cast on, and a superseded model name is treated as a defect rather than a dated detail.
  4. Model capability claims come from Anthropic's own documentation or announcements. MagicClaude does not run its own evaluations and does not publish scores.
  5. Risky surfaces, especially computer use and private documents, include guardrails.
  6. Adjacent territories link to sibling sites instead of duplicating their coverage.

Retired sources

On September 19, 2026 the Claude Opus 4.8 record was removed, because Claude Opus 5 has been the current Opus since July 24, 2026 and citing the older page implied a lineup that no longer exists. Retirements are logged onthe freshness page rather than deleted silently.

Keep the act moving

Related source-backed pages

Demo

PDF Evidence Table

See source anchoring applied to document analysis.

Demo

Live Research Brief

Use current web sources while separating facts from unknowns.

About

Methodology

Read the independent-publication disclaimer and lane boundaries.

Primary Sources

These demos cite official Anthropic docs or help-center pages for capability claims. They do not claim identical output across accounts, plans, models, or dates.

Claude Help Center

Publish and share artifacts

Free, Pro, and Max users can publish artifacts publicly; Team and Enterprise sharing is organization-scoped.

Claude Code Docs

Claude Code overview

Claude Code is an agentic coding tool available in terminal, IDE, desktop app, and browser surfaces.

Claude Platform Docs

Code execution tool

The code execution tool runs Bash and Python in a sandbox to analyze data, generate files, and manipulate files.

Claude Platform Docs

Vision

Claude can receive image inputs through Claude.ai, Workbench, and API image content blocks.

Claude Platform Docs

PDF support

Claude can process PDFs and answer questions about text, pictures, charts, and tables in those documents.

Claude Help Center

Enable and use web search

Claude web search can be enabled in chat and grounds responses with current web content and source links.

Claude Platform Docs

Web search tool

The API web search tool can retrieve current information, supports domain controls, and can use dynamic filtering.

Claude Help Center

Use research on Claude

Claude Research is a paid-plan feature that explores a question through multiple searches and citation-backed synthesis.

Claude Help Center

Let Claude use your computer in Cowork

Computer use lets Claude interact with permitted apps and files, but Anthropic warns users to avoid sensitive apps and monitor behavior.

Claude Platform Docs

Prompting best practices

Anthropic guidance emphasizes explicit instructions, output formats, tool-use direction, and model-specific prompt updates.

Claude Platform Docs

Increase output consistency

When exact JSON conformance matters, Anthropic recommends structured outputs rather than prompt-only formatting.

Claude Platform Docs

Citations

Claude citations can reference text from provided documents, including text extracted from PDFs.

Claude Platform Docs

Context windows

The context window is the text a model can reference for a response, and long contexts require deliberate management.

Anthropic Docs

Claude model overview

The model overview is the canonical list of generally available Claude models, API IDs, context limits, and retirement dates.

Claude Platform Docs

Choosing a model

Anthropic guidance is to start with Claude Opus 5 for most work, move to Claude Fable 5.1 for demanding reasoning and long-horizon agentic tasks, use Sonnet 5 for the speed/intelligence balance, and Haiku 4.5 for the fastest and cheapest runs.

Claude Platform Docs

Claude Fable 5.1 overview

Claude Fable 5.1 (`claude-fable-5-1`) has a 1M-token context window, 128K max output, always-on adaptive thinking, and a default effort level of high in Claude Code and medium on Claude.ai and Cowork.

Anthropic

Claude Fable 5.1 and Mythos 5.1

The September 1, 2026 announcement introduces Fable 5.1 as Anthropic’s most capable generally available model and describes cheaper cache reads for agentic workloads.

Claude Platform Docs

Claude Opus 5 overview

Claude Opus 5 (`claude-opus-5`) launched July 24, 2026 with a 1M-token context window, 128K max output, adaptive thinking, and an optional fast mode.

Claude Platform Docs

What's new in Claude Sonnet 5

Claude Sonnet 5 (`claude-sonnet-5`) supports a 1M-token context window by default and 128K max output tokens.

Claude Platform Docs

Text editor tool

The text editor tool lets Claude inspect and modify text files for debugging, refactoring, documentation, and tests.