xAI

let model = XaiModel("grok-4.5")          // Responses API
let chat  = XaiModel.chat("grok-3")       // legacy chat wire

Key from XAI_API_KEY; base URL https://api.x.ai/v1.

Features

• Tools, structured output, vision, streamed reasoning, citations as StreamPart.source, and cached-token usage.
• Server-side live search is a typed option — XaiModel.SearchParameters serializes to the search_parameters body field:

let search = XaiModel.SearchParameters(
  mode: .auto,
  returnCitations: true,
  fromDate: "2026-07-01",
  maxSearchResults: 10,
  sources: [.web(country: "US"), .x(includedHandles: ["xai"]), .news()]
)

let result = try await generateText(
  model: XaiModel("grok-4.5"),
  prompt: "What happened in AI this week?",
  providerOptions: search.providerOptions
)

Per-source filters: .web(country:excludedWebsites:allowedWebsites:safeSearch:), .x(includedHandles:excludedHandles:postFavoriteCount:postViewCount:), .news(country:excludedWebsites:safeSearch:).

Server-side tools

On the Responses API, xAI can run tools for you. Pass the typed builders under XaiModel.Tools in tools: — the calls and results stream back as provider-executed parts, and citations as .source:

let result = try await generateText(
  model: XaiModel("grok-4.5"),
  prompt: "What did xAI announce this week?",
  tools: [
    XaiModel.Tools.webSearch(allowedDomains: ["x.ai"]),
    XaiModel.Tools.xSearch(allowedXHandles: ["xai"], fromDate: "2026-07-01"),
    XaiModel.Tools.codeExecution(),
  ]
)

Builders: webSearch, xSearch, codeExecution, fileSearch(vectorStoreIds:), mcpServer(serverUrl:), viewImage, viewXVideo. SearchParameters above is the older search_parameters knob; Tools is the provider-executed path that surfaces each call and its result.

Multi-agent

grok-4.20-multi-agent runs a research swarm server-side. It's just a model id plus the three server-side tools — pass them by whatever names you want to reference in activeTools:

let result = streamText(
  model: XaiModel("grok-4.20-multi-agent"),
  system: "You are a research assistant in multi-agent mode.",
  prompt: "What shipped across the AI labs this week?",
  tools: [
    XaiModel.Tools.webSearch(name: "xai_web_search"),
    XaiModel.Tools.xSearch(name: "xai_x_search"),
    XaiModel.Tools.codeExecution(name: "xai_code_execution"),
  ],
  toolChoice: .auto,
  activeTools: ["xai_web_search", "xai_x_search", "xai_code_execution"]
)

Each builder's name: sets the tool name the calls and results carry, so activeTools lines up with it. The agents' searches and code runs stream back as provider-executed .toolCall / .toolResult parts.

Models

• The reasoning parameter maps to reasoning.effort (.minimal coerces to low, .xhigh to high).
• grok-4.20 date-stamped -reasoning / -non-reasoning variants have behavior baked into the model id, so the parameter is not sent for them.

Current lineup

As of July 2026, newest first:

Beyond text