Providers

Every provider implements one protocol:

public protocol LanguageModel: Sendable {
  var provider: String { get }
  var modelID: String { get }
  func stream(_ request: LanguageModelRequest) async throws
    -> AsyncThrowingStream<StreamPart, Error>
}

Higher-level functions are built on this spec, so a provider swap never touches your feature code.

Native packs

Each pack speaks its provider's real wire, mirroring the @ai-sdk/* package family. Where upstream is native, the port is native too; no lowest-common-denominator shims.

Keys come from each provider's conventional environment variable (OPENAI_API_KEY, ANTHROPIC_API_KEY, XAI_API_KEY, ...) or an explicit apiKey: argument. baseURL includes the version path, matching the AI SDK's URL semantics, so gateways and proxies drop in cleanly.

First-class compatible providers

Providers that share the OpenAI chat-completions wire still have their own model types with the right URLs and environment keys:

let together = TogetherAIModel("MiniMaxAI/MiniMax-M3")
let local = OllamaModel("gemma4")

Together, Fireworks, Cerebras, OpenRouter, DeepInfra, Baseten, Vercel (v0), Gateway, Ollama, LM Studio, and Sarvam (Indic chat) are first-class model packs. OpenAICompatibleProvider is the general initializer for custom gateways and anything else that speaks the chat-completions wire. The compatibility page has every endpoint and environment variable.

Media and retrieval models

Non-chat capabilities have their own focused protocols and first-class model types. They do not need to be wrapped as language providers:

The media provider index links every dedicated provider page.

The registry and custom providers

ProviderRegistry resolves "provider:model-id" strings; customProvider publishes friendly aliases with settings baked in and falls back to a wrapped provider for unknown ids:

let openai = ProviderRegistry.Provider { OpenAIModel($0) }
let custom = customProvider(
  languageModels: [
    "fast": OpenAIModel("gpt-5.6-luna"),
    "smart": wrapLanguageModel(model: OpenAIModel("gpt-5.6-sol"), middleware: [.extractReasoning()])
  ],
  fallback: openai
)
let registry = ProviderRegistry(providers: ["openai": custom])
let model = try registry.languageModel("openai:fast")

Live search on xAI

Grok's server-side search is a typed option, not a raw JSON blob:

let search = XaiModel.SearchParameters(
  mode: .auto,
  returnCitations: true,
  sources: [.web(), .x(), .news()]
)

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

The full surface: mode (.auto, .on, .off), returnCitations, a fromDate/toDate window (YYYY-MM-DD), maxSearchResults, and per-source filters — .web(country:excludedWebsites:allowedWebsites:safeSearch:), .x(includedHandles:excludedHandles:postFavoriteCount:postViewCount:), .news(country:excludedWebsites:safeSearch:). It serializes to xAI's search_parameters body field exactly.

Sources and citations

Search-backed providers (Perplexity and Cohere citations, OpenAI and xAI url annotations) surface as StreamPart.source and collect on result.sources.

Per-provider pages

Setup, features, and the models each pack special-cases — plus the compatibility matrix for the cross-provider view.