Anthropic

let model = AnthropicModel("claude-fable-5")     // or claude-sonnet-5

Key from ANTHROPIC_API_KEY; base URL https://api.anthropic.com/v1.

Features

• Tools, vision, and PDF documents as message parts.
• Structured output rides a forced tool call — Claude has no JSON mode, so generateObject defines a tool whose arguments are your schema and forces the model to call it.
• Thinking streams as .reasoningDelta; the reasoning parameter translates per model tier (below).
• usage.cachedInputTokens is populated on prompt-cache hits.
• Anthropic-native fields (thinking, cache-control blocks) go through providerOptions and win over anything the library sets.

Server-side tools

Anthropic's built-in tools have typed builders under AnthropicModel.Tools — webSearch, webFetch, codeExecution, bash, textEditor, computer(displayWidthPx:displayHeightPx:), and memory. Pass them in tools:; the required anthropic-beta flags are added to the request for you:

let result = try await generateText(
  model: AnthropicModel("claude-sonnet-5"),
  prompt: "Search the web and summarize what's new.",
  tools: [AnthropicModel.Tools.webSearch(maxUses: 3)]
)

Each builder takes a version: for the dated tool variants (web_search_20250305, computer_20250124, ...); the defaults track the current stable release.

Models

.none sends thinking.type: "disabled" explicitly, and max_tokens is raised automatically when a budget would not fit.

Current lineup

Snapshot from July 2026, newest first. Anthropic's native ids use dashes (claude-opus-4-8); date-stamped variants (claude-sonnet-4-5-20250929) work too.

Files and skills

These resource clients are documented in Files and skills.

let upload = try await AnthropicFiles().upload(
  data: pdf, filename: "report.pdf", mediaType: "application/pdf"
)

let skill = try await AnthropicSkills().upload(
  files: [SkillFile(path: "brand-guide/SKILL.md", data: skillMD)],
  displayTitle: "Brand guide"
)

Beta headers are handled for you on both.