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/CHANGELOG.md
+++ b/packages/ai/CHANGELOG.md
@@ -4,6 +4,7 @@

 ### Fixed

+- Fixed Google and `google-vertex` Gemini model metadata to map `latest` aliases to the current models, add Gemini 3.5 Flash for Vertex, correct Gemini 2.5 Flash Vertex cache pricing, and remove shut-down Vertex preview models ([#5761](https://github.com/earendil-works/pi/issues/5761)).
 - Fixed Moonshot AI China model metadata to include Kimi K2.7 Code, and omitted unsupported thinking-off payloads for Kimi K2.7 Code models ([#5760](https://github.com/earendil-works/pi/issues/5760)).

 ## [0.79.4] - 2026-06-15
--- 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> = {
--- a/packages/ai/src/models.generated.ts
+++ b/packages/ai/src/models.generated.ts
@@ -4769,11 +4769,12 @@ export const MODELS = {
 			provider: "google",
 			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
 			reasoning: true,
+			thinkingLevelMap: {"off":null},
 			input: ["text", "image"],
 			cost: {
-				input: 0.3,
-				output: 2.5,
-				cacheRead: 0.075,
+				input: 1.5,
+				output: 9,
+				cacheRead: 0.15,
 				cacheWrite: 0,
 			},
 			contextWindow: 1048576,
@@ -4786,10 +4787,11 @@ export const MODELS = {
 			provider: "google",
 			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
 			reasoning: true,
+			thinkingLevelMap: {"off":null},
 			input: ["text", "image"],
 			cost: {
-				input: 0.1,
-				output: 0.4,
+				input: 0.25,
+				output: 1.5,
 				cacheRead: 0.025,
 				cacheWrite: 0,
 			},
@@ -4870,94 +4872,9 @@ export const MODELS = {
 		} satisfies Model<"google-generative-ai">,
 	},
 	"google-vertex": {
-		"gemini-1.5-flash": {
-			id: "gemini-1.5-flash",
-			name: "Gemini 1.5 Flash (Vertex)",
-			api: "google-vertex",
-			provider: "google-vertex",
-			baseUrl: "https://{location}-aiplatform.googleapis.com",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.075,
-				output: 0.3,
-				cacheRead: 0.01875,
-				cacheWrite: 0,
-			},
-			contextWindow: 1000000,
-			maxTokens: 8192,
-		} satisfies Model<"google-vertex">,
-		"gemini-1.5-flash-8b": {
-			id: "gemini-1.5-flash-8b",
-			name: "Gemini 1.5 Flash-8B (Vertex)",
-			api: "google-vertex",
-			provider: "google-vertex",
-			baseUrl: "https://{location}-aiplatform.googleapis.com",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.0375,
-				output: 0.15,
-				cacheRead: 0.01,
-				cacheWrite: 0,
-			},
-			contextWindow: 1000000,
-			maxTokens: 8192,
-		} satisfies Model<"google-vertex">,
-		"gemini-1.5-pro": {
-			id: "gemini-1.5-pro",
-			name: "Gemini 1.5 Pro (Vertex)",
-			api: "google-vertex",
-			provider: "google-vertex",
-			baseUrl: "https://{location}-aiplatform.googleapis.com",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 1.25,
-				output: 5,
-				cacheRead: 0.3125,
-				cacheWrite: 0,
-			},
-			contextWindow: 1000000,
-			maxTokens: 8192,
-		} satisfies Model<"google-vertex">,
-		"gemini-2.0-flash": {
-			id: "gemini-2.0-flash",
-			name: "Gemini 2.0 Flash (Vertex)",
-			api: "google-vertex",
-			provider: "google-vertex",
-			baseUrl: "https://{location}-aiplatform.googleapis.com",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.15,
-				output: 0.6,
-				cacheRead: 0.0375,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 8192,
-		} satisfies Model<"google-vertex">,
-		"gemini-2.0-flash-lite": {
-			id: "gemini-2.0-flash-lite",
-			name: "Gemini 2.0 Flash Lite (Vertex)",
-			api: "google-vertex",
-			provider: "google-vertex",
-			baseUrl: "https://{location}-aiplatform.googleapis.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.075,
-				output: 0.3,
-				cacheRead: 0.01875,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 65536,
-		} satisfies Model<"google-vertex">,
 		"gemini-2.5-flash": {
 			id: "gemini-2.5-flash",
-			name: "Gemini 2.5 Flash (Vertex)",
+			name: "Gemini 2.5 Flash",
 			api: "google-vertex",
 			provider: "google-vertex",
 			baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -4974,24 +4891,7 @@ export const MODELS = {
 		} satisfies Model<"google-vertex">,
 		"gemini-2.5-flash-lite": {
 			id: "gemini-2.5-flash-lite",
-			name: "Gemini 2.5 Flash Lite (Vertex)",
-			api: "google-vertex",
-			provider: "google-vertex",
-			baseUrl: "https://{location}-aiplatform.googleapis.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.1,
-				output: 0.4,
-				cacheRead: 0.01,
-				cacheWrite: 0,
-			},
-			contextWindow: 1048576,
-			maxTokens: 65536,
-		} satisfies Model<"google-vertex">,
-		"gemini-2.5-flash-lite-preview-09-2025": {
-			id: "gemini-2.5-flash-lite-preview-09-2025",
-			name: "Gemini 2.5 Flash Lite Preview 09-25 (Vertex)",
+			name: "Gemini 2.5 Flash-Lite",
 			api: "google-vertex",
 			provider: "google-vertex",
 			baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -5008,7 +4908,7 @@ export const MODELS = {
 		} satisfies Model<"google-vertex">,
 		"gemini-2.5-pro": {
 			id: "gemini-2.5-pro",
-			name: "Gemini 2.5 Pro (Vertex)",
+			name: "Gemini 2.5 Pro",
 			api: "google-vertex",
 			provider: "google-vertex",
 			baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -5025,7 +4925,7 @@ export const MODELS = {
 		} satisfies Model<"google-vertex">,
 		"gemini-3-flash-preview": {
 			id: "gemini-3-flash-preview",
-			name: "Gemini 3 Flash Preview (Vertex)",
+			name: "Gemini 3 Flash Preview",
 			api: "google-vertex",
 			provider: "google-vertex",
 			baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -5041,27 +4941,27 @@ export const MODELS = {
 			contextWindow: 1048576,
 			maxTokens: 65536,
 		} satisfies Model<"google-vertex">,
-		"gemini-3-pro-preview": {
-			id: "gemini-3-pro-preview",
-			name: "Gemini 3 Pro Preview (Vertex)",
+		"gemini-3.1-flash-lite": {
+			id: "gemini-3.1-flash-lite",
+			name: "Gemini 3.1 Flash Lite",
 			api: "google-vertex",
 			provider: "google-vertex",
 			baseUrl: "https://{location}-aiplatform.googleapis.com",
 			reasoning: true,
-			thinkingLevelMap: {"off":null,"minimal":null,"low":"LOW","medium":null,"high":"HIGH"},
+			thinkingLevelMap: {"off":null},
 			input: ["text", "image"],
 			cost: {
-				input: 2,
-				output: 12,
-				cacheRead: 0.2,
+				input: 0.25,
+				output: 1.5,
+				cacheRead: 0.025,
 				cacheWrite: 0,
 			},
-			contextWindow: 1000000,
-			maxTokens: 64000,
+			contextWindow: 1048576,
+			maxTokens: 65536,
 		} satisfies Model<"google-vertex">,
 		"gemini-3.1-pro-preview": {
 			id: "gemini-3.1-pro-preview",
-			name: "Gemini 3.1 Pro Preview (Vertex)",
+			name: "Gemini 3.1 Pro Preview",
 			api: "google-vertex",
 			provider: "google-vertex",
 			baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -5079,7 +4979,7 @@ export const MODELS = {
 		} satisfies Model<"google-vertex">,
 		"gemini-3.1-pro-preview-customtools": {
 			id: "gemini-3.1-pro-preview-customtools",
-			name: "Gemini 3.1 Pro Preview Custom Tools (Vertex)",
+			name: "Gemini 3.1 Pro Preview Custom Tools",
 			api: "google-vertex",
 			provider: "google-vertex",
 			baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -5095,6 +4995,60 @@ export const MODELS = {
 			contextWindow: 1048576,
 			maxTokens: 65536,
 		} satisfies Model<"google-vertex">,
+		"gemini-3.5-flash": {
+			id: "gemini-3.5-flash",
+			name: "Gemini 3.5 Flash",
+			api: "google-vertex",
+			provider: "google-vertex",
+			baseUrl: "https://{location}-aiplatform.googleapis.com",
+			reasoning: true,
+			thinkingLevelMap: {"off":null},
+			input: ["text", "image"],
+			cost: {
+				input: 1.5,
+				output: 9,
+				cacheRead: 0.15,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		} satisfies Model<"google-vertex">,
+		"gemini-flash-latest": {
+			id: "gemini-flash-latest",
+			name: "Gemini Flash Latest",
+			api: "google-vertex",
+			provider: "google-vertex",
+			baseUrl: "https://{location}-aiplatform.googleapis.com",
+			reasoning: true,
+			thinkingLevelMap: {"off":null},
+			input: ["text", "image"],
+			cost: {
+				input: 1.5,
+				output: 9,
+				cacheRead: 0.15,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		} satisfies Model<"google-vertex">,
+		"gemini-flash-lite-latest": {
+			id: "gemini-flash-lite-latest",
+			name: "Gemini Flash-Lite Latest",
+			api: "google-vertex",
+			provider: "google-vertex",
+			baseUrl: "https://{location}-aiplatform.googleapis.com",
+			reasoning: true,
+			thinkingLevelMap: {"off":null},
+			input: ["text", "image"],
+			cost: {
+				input: 0.25,
+				output: 1.5,
+				cacheRead: 0.025,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		} satisfies Model<"google-vertex">,
 	},
 	"groq": {
 		"llama-3.1-8b-instant": {
@@ -9489,13 +9443,13 @@ export const MODELS = {
 			thinkingLevelMap: {"minimal":null,"low":null,"medium":null,"high":"high","xhigh":"xhigh"},
 			input: ["text"],
 			cost: {
-				input: 0.09,
-				output: 0.18,
+				input: 0.098,
+				output: 0.196,
 				cacheRead: 0.02,
 				cacheWrite: 0,
 			},
 			contextWindow: 1048576,
-			maxTokens: 65536,
+			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
 		"deepseek/deepseek-v4-pro": {
 			id: "deepseek/deepseek-v4-pro",
@@ -12333,7 +12287,7 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
-			maxTokens: 262144,
+			maxTokens: 81920,
 		} satisfies Model<"openai-completions">,
 		"qwen/qwen3.5-397b-a17b": {
 			id: "qwen/qwen3.5-397b-a17b",
@@ -15065,6 +15019,23 @@ export const MODELS = {
 			contextWindow: 256000,
 			maxTokens: 32768,
 		} satisfies Model<"anthropic-messages">,
+		"moonshotai/kimi-k2.7-code-highspeed": {
+			id: "moonshotai/kimi-k2.7-code-highspeed",
+			name: "Kimi K2.7 Code High Speed",
+			api: "anthropic-messages",
+			provider: "vercel-ai-gateway",
+			baseUrl: "https://ai-gateway.vercel.sh",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.9,
+				output: 8,
+				cacheRead: 0.38,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 4096,
+		} satisfies Model<"anthropic-messages">,
 		"nvidia/nemotron-3-super-120b-a12b": {
 			id: "nvidia/nemotron-3-super-120b-a12b",
 			name: "NVIDIA Nemotron 3 Super 120B A12B",
--- a/packages/ai/src/providers/google-vertex.ts
+++ b/packages/ai/src/providers/google-vertex.ts
@@ -490,7 +490,8 @@ function isGemini3ProModel(model: Model<"google-generative-ai">): boolean {
 }

 function isGemini3FlashModel(model: Model<"google-generative-ai">): boolean {
-	return /gemini-3(?:\.\d+)?-flash/.test(model.id.toLowerCase());
+	const id = model.id.toLowerCase();
+	return /gemini-3(?:\.\d+)?-flash/.test(id) || id === "gemini-flash-latest" || id === "gemini-flash-lite-latest";
 }

 function getDisabledThinkingConfig(model: Model<"google-vertex">): ThinkingConfig {
--- a/packages/ai/src/providers/google.ts
+++ b/packages/ai/src/providers/google.ts
@@ -406,7 +406,8 @@ function isGemini3ProModel(model: Model<"google-generative-ai">): boolean {
 }

 function isGemini3FlashModel(model: Model<"google-generative-ai">): boolean {
-	return /gemini-3(?:\.\d+)?-flash/.test(model.id.toLowerCase());
+	const id = model.id.toLowerCase();
+	return /gemini-3(?:\.\d+)?-flash/.test(id) || id === "gemini-flash-latest" || id === "gemini-flash-lite-latest";
 }

 function getDisabledThinkingConfig(model: Model<"google-generative-ai">): ThinkingConfig {
--- a/packages/coding-agent/CHANGELOG.md
+++ b/packages/coding-agent/CHANGELOG.md
@@ -4,6 +4,7 @@

 ### Fixed

+- Fixed inherited Google and `google-vertex` Gemini model metadata to map `latest` aliases to the current models, add Gemini 3.5 Flash for Vertex, correct Gemini 2.5 Flash Vertex cache pricing, and remove shut-down Vertex preview models ([#5761](https://github.com/earendil-works/pi/issues/5761)).
 - Fixed the session selector to stay open and show the all-sessions empty state when both current-folder and all-scope session lists are empty ([#5747](https://github.com/earendil-works/pi/issues/5747)).
 - Fixed inherited Moonshot AI China model metadata to include Kimi K2.7 Code, and omitted unsupported thinking-off payloads for Kimi K2.7 Code models ([#5760](https://github.com/earendil-works/pi/issues/5760)).