fix(ai): update Google Vertex Gemini models

closes #5761
2026-06-16 01:03:12 +02:00
parent 7cfd1af395
commit b0c8f65ffa
6 changed files with 162 additions and 298 deletions
--- a/packages/ai/scripts/generate-models.ts
+++ b/packages/ai/scripts/generate-models.ts
@@ -123,6 +123,7 @@ const TOGETHER_TOGGLE_REASONING_LEVEL_MAP = {

 const AI_GATEWAY_MODELS_URL = "https://ai-gateway.vercel.sh/v1";
 const AI_GATEWAY_BASE_URL = "https://ai-gateway.vercel.sh";
+const VERTEX_BASE_URL = "https://{location}-aiplatform.googleapis.com";
 const NVIDIA_BASE_URL = "https://integrate.api.nvidia.com/v1";
 const NVIDIA_HEADERS = {
 	"NVCF-POLL-SECONDS": "3600",
@@ -270,7 +271,8 @@ function isGemini3ProModel(modelId: string): boolean {
 }

 function isGemini3FlashModel(modelId: string): boolean {
-	return /gemini-3(?:\.\d+)?-flash/.test(modelId.toLowerCase());
+	const id = modelId.toLowerCase();
+	return /gemini-3(?:\.\d+)?-flash/.test(id) || id === "gemini-flash-latest" || id === "gemini-flash-lite-latest";
 }

 function isGemma4Model(modelId: string): boolean {
@@ -624,6 +626,13 @@ async function loadModelsDevData(): Promise<Model<any>[]> {
 			for (const [modelId, model] of Object.entries(data.google.models)) {
 				const m = model as ModelsDevModel;
 				if (m.tool_call !== true) continue;
+				let source = m;
+				if (modelId === "gemini-flash-latest") {
+					source = (data.google.models["gemini-3.5-flash"] as ModelsDevModel | undefined) ?? m;
+				}
+				if (modelId === "gemini-flash-lite-latest") {
+					source = (data.google.models["gemini-3.1-flash-lite"] as ModelsDevModel | undefined) ?? m;
+				}

 				models.push({
 					id: modelId,
@@ -631,16 +640,57 @@ async function loadModelsDevData(): Promise<Model<any>[]> {
 					api: "google-generative-ai",
 					provider: "google",
 					baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-					reasoning: m.reasoning === true,
-					input: m.modalities?.input?.includes("image") ? ["text", "image"] : ["text"],
+					reasoning: source.reasoning === true,
+					input: source.modalities?.input?.includes("image") ? ["text", "image"] : ["text"],
 					cost: {
-						input: m.cost?.input || 0,
-						output: m.cost?.output || 0,
-						cacheRead: m.cost?.cache_read || 0,
-						cacheWrite: m.cost?.cache_write || 0,
+						input: source.cost?.input || 0,
+						output: source.cost?.output || 0,
+						cacheRead: source.cost?.cache_read || 0,
+						cacheWrite: source.cost?.cache_write || 0,
 					},
-					contextWindow: m.limit?.context || 4096,
-					maxTokens: m.limit?.output || 4096,
+					contextWindow: source.limit?.context || 4096,
+					maxTokens: source.limit?.output || 4096,
+				});
+			}
+		}
+
+		// Process Google Vertex Gemini models. The google-vertex models.dev catalog also includes
+		// Claude, OpenAI, and other MaaS models that do not use the @google/genai Gemini streaming
+		// path implemented by our google-vertex provider.
+		if (data["google-vertex"]?.models) {
+			for (const [modelId, model] of Object.entries(data["google-vertex"].models)) {
+				const m = model as ModelsDevModel;
+				if (m.tool_call !== true) continue;
+				if (!modelId.startsWith("gemini-")) continue;
+				if (modelId === "gemini-3.1-flash-lite-preview") continue;
+				let source = m;
+				if (modelId === "gemini-flash-latest") {
+					source = (data["google-vertex"].models["gemini-3.5-flash"] as ModelsDevModel | undefined) ?? m;
+				}
+				if (modelId === "gemini-flash-lite-latest") {
+					source = (data["google-vertex"].models["gemini-3.1-flash-lite"] as ModelsDevModel | undefined) ?? m;
+				}
+
+				// models.dev reports Vertex cache_read/cache_write values for Gemini 2.5 Flash that
+				// do not match the official Gemini API standard pricing table. pi only accounts
+				// cachedContentTokenCount as cacheRead.
+				const cacheRead = modelId === "gemini-2.5-flash" ? 0.03 : source.cost?.cache_read || 0;
+				models.push({
+					id: modelId,
+					name: m.name || modelId,
+					api: "google-vertex",
+					provider: "google-vertex",
+					baseUrl: VERTEX_BASE_URL,
+					reasoning: source.reasoning === true,
+					input: source.modalities?.input?.includes("image") ? ["text", "image"] : ["text"],
+					cost: {
+						input: source.cost?.input || 0,
+						output: source.cost?.output || 0,
+						cacheRead,
+						cacheWrite: 0,
+					},
+					contextWindow: source.limit?.context || 4096,
+					maxTokens: source.limit?.output || 4096,
 				});
 			}
 		}
@@ -1968,167 +2018,6 @@ async function generateModels() {
 		});
 	}

-	const VERTEX_BASE_URL = "https://{location}-aiplatform.googleapis.com";
-	const vertexModels: Model<"google-vertex">[] = [
-		{
-			id: "gemini-3-pro-preview",
-			name: "Gemini 3 Pro Preview (Vertex)",
-			api: "google-vertex",
-			provider: "google-vertex",
-			baseUrl: VERTEX_BASE_URL,
-			reasoning: true,
-			input: ["text", "image"],
-			cost: { input: 2, output: 12, cacheRead: 0.2, cacheWrite: 0 },
-			contextWindow: 1000000,
-			maxTokens: 64000,
-		},
-		{
-			id: "gemini-3.1-pro-preview",
-			name: "Gemini 3.1 Pro Preview (Vertex)",
-			api: "google-vertex",
-			provider: "google-vertex",
-			baseUrl: VERTEX_BASE_URL,
-			reasoning: true,
-			input: ["text", "image"],
-			cost: { input: 2, output: 12, cacheRead: 0.2, cacheWrite: 0 },
-			contextWindow: 1048576,
-			maxTokens: 65536,
-		},
-		{
-			id: "gemini-3.1-pro-preview-customtools",
-			name: "Gemini 3.1 Pro Preview Custom Tools (Vertex)",
-			api: "google-vertex",
-			provider: "google-vertex",
-			baseUrl: VERTEX_BASE_URL,
-			reasoning: true,
-			input: ["text", "image"],
-			cost: { input: 2, output: 12, cacheRead: 0.2, cacheWrite: 0 },
-			contextWindow: 1048576,
-			maxTokens: 65536,
-		},
-		{
-			id: "gemini-3-flash-preview",
-			name: "Gemini 3 Flash Preview (Vertex)",
-			api: "google-vertex",
-			provider: "google-vertex",
-			baseUrl: VERTEX_BASE_URL,
-			reasoning: true,
-			input: ["text", "image"],
-			cost: { input: 0.5, output: 3, cacheRead: 0.05, cacheWrite: 0 },
-			contextWindow: 1048576,
-			maxTokens: 65536,
-		},
-		{
-			id: "gemini-2.0-flash",
-			name: "Gemini 2.0 Flash (Vertex)",
-			api: "google-vertex",
-			provider: "google-vertex",
-			baseUrl: VERTEX_BASE_URL,
-			reasoning: false,
-			input: ["text", "image"],
-			cost: { input: 0.15, output: 0.6, cacheRead: 0.0375, cacheWrite: 0 },
-			contextWindow: 1048576,
-			maxTokens: 8192,
-		},
-		{
-			id: "gemini-2.0-flash-lite",
-			name: "Gemini 2.0 Flash Lite (Vertex)",
-			api: "google-vertex",
-			provider: "google-vertex",
-			baseUrl: VERTEX_BASE_URL,
-			reasoning: true,
-			input: ["text", "image"],
-			cost: { input: 0.075, output: 0.3, cacheRead: 0.01875, cacheWrite: 0 },
-			contextWindow: 1048576,
-			maxTokens: 65536,
-		},
-		{
-			id: "gemini-2.5-pro",
-			name: "Gemini 2.5 Pro (Vertex)",
-			api: "google-vertex",
-			provider: "google-vertex",
-			baseUrl: VERTEX_BASE_URL,
-			reasoning: true,
-			input: ["text", "image"],
-			cost: { input: 1.25, output: 10, cacheRead: 0.125, cacheWrite: 0 },
-			contextWindow: 1048576,
-			maxTokens: 65536,
-		},
-		{
-			id: "gemini-2.5-flash",
-			name: "Gemini 2.5 Flash (Vertex)",
-			api: "google-vertex",
-			provider: "google-vertex",
-			baseUrl: VERTEX_BASE_URL,
-			reasoning: true,
-			input: ["text", "image"],
-			cost: { input: 0.3, output: 2.5, cacheRead: 0.03, cacheWrite: 0 },
-			contextWindow: 1048576,
-			maxTokens: 65536,
-		},
-		{
-			id: "gemini-2.5-flash-lite-preview-09-2025",
-			name: "Gemini 2.5 Flash Lite Preview 09-25 (Vertex)",
-			api: "google-vertex",
-			provider: "google-vertex",
-			baseUrl: VERTEX_BASE_URL,
-			reasoning: true,
-			input: ["text", "image"],
-			cost: { input: 0.1, output: 0.4, cacheRead: 0.01, cacheWrite: 0 },
-			contextWindow: 1048576,
-			maxTokens: 65536,
-		},
-		{
-			id: "gemini-2.5-flash-lite",
-			name: "Gemini 2.5 Flash Lite (Vertex)",
-			api: "google-vertex",
-			provider: "google-vertex",
-			baseUrl: VERTEX_BASE_URL,
-			reasoning: true,
-			input: ["text", "image"],
-			cost: { input: 0.1, output: 0.4, cacheRead: 0.01, cacheWrite: 0 },
-			contextWindow: 1048576,
-			maxTokens: 65536,
-		},
-		{
-			id: "gemini-1.5-pro",
-			name: "Gemini 1.5 Pro (Vertex)",
-			api: "google-vertex",
-			provider: "google-vertex",
-			baseUrl: VERTEX_BASE_URL,
-			reasoning: false,
-			input: ["text", "image"],
-			cost: { input: 1.25, output: 5, cacheRead: 0.3125, cacheWrite: 0 },
-			contextWindow: 1000000,
-			maxTokens: 8192,
-		},
-		{
-			id: "gemini-1.5-flash",
-			name: "Gemini 1.5 Flash (Vertex)",
-			api: "google-vertex",
-			provider: "google-vertex",
-			baseUrl: VERTEX_BASE_URL,
-			reasoning: false,
-			input: ["text", "image"],
-			cost: { input: 0.075, output: 0.3, cacheRead: 0.01875, cacheWrite: 0 },
-			contextWindow: 1000000,
-			maxTokens: 8192,
-		},
-		{
-			id: "gemini-1.5-flash-8b",
-			name: "Gemini 1.5 Flash-8B (Vertex)",
-			api: "google-vertex",
-			provider: "google-vertex",
-			baseUrl: VERTEX_BASE_URL,
-			reasoning: false,
-			input: ["text", "image"],
-			cost: { input: 0.0375, output: 0.15, cacheRead: 0.01, cacheWrite: 0 },
-			contextWindow: 1000000,
-			maxTokens: 8192,
-		},
-	];
-	allModels.push(...vertexModels);
-
 	// Azure Foundry deploys these with larger context windows than OpenAI's own API,
 	// which caps gpt-5.4/gpt-5.5 at 272k. See models-sold-directly-by-azure docs.
 	const AZURE_CONTEXT_WINDOW_OVERRIDES: Record<string, number> = {