Google

let model = GoogleModel("gemini-3.5-flash")

Key from GOOGLE_GENERATIVE_AI_API_KEY; base URL https://generativelanguage.googleapis.com/v1beta.

Features

• Tools, vision, and file parts on the native generateContent wire.
• Structured output uses constrained decoding (responseSchema + responseMimeType), not prompt tricks.
• The reasoning parameter maps to thinkingConfig (below); thinking streams as .reasoningDelta.
• usage.cachedInputTokens reports context-cache hits.
• Native fields (safetySettings, cachedContent, ...) pass through providerOptions at the top level.
• Grounding tools have typed builders under GoogleModel.Tools — googleSearch, urlContext, codeExecution, fileSearch, enterpriseWebSearch, googleMaps (Gemini 2.0 and newer). Pass them in tools: and they run server-side:

let result = try await generateText(
  model: GoogleModel("gemini-3.5-flash"),
  prompt: "Ground this in current sources.",
  tools: [GoogleModel.Tools.googleSearch(), GoogleModel.Tools.urlContext()]
)

Models

• gemini-3* takes thinkingLevel — .none and .minimal both map to minimal (thinking can't be fully disabled), .xhigh caps at high. Exception: gemini-3-pro-image stays on budgets.
• Everything else takes thinkingBudget: 0 for .none, otherwise a fraction of the 65,536-token ceiling capped at 32,768 (2.5 Pro, gemini-3-pro-image) or 24,576 (the rest).

Current lineup

Language models as of July 2026, newest first:

Vertex AI

let vertex = GoogleVertexModel(
  "gemini-3.5-flash",
  project: "my-project",      // or GOOGLE_VERTEX_PROJECT
  location: "us-central1"     // or GOOGLE_VERTEX_LOCATION
)

Express-mode API keys and bearer accessToken: auth both work; the request body is identical to the Gemini wire.

Gemini Live

GoogleRealtimeModel connects to the Live API for realtime voice: tokens mint against v1alpha/auth_tokens and the session config rides in the token request. See Realtime voice for connection, session, audio, and tool-call events.