diff --git a/packages/ai/CHANGELOG.md b/packages/ai/CHANGELOG.md
index 1b09cd3b..cb677271 100644
--- a/packages/ai/CHANGELOG.md
+++ b/packages/ai/CHANGELOG.md
@@ -2,6 +2,10 @@
 
 ## [Unreleased]
 
+### Fixed
+
+- Fixed `google-gemini-cli` built-in model discovery to include `gemini-3.1-flash-lite-preview`, so Cloud Code Assist model lists expose it without requiring manual `--model` fallback selection ([#3545](https://github.com/badlogic/pi-mono/issues/3545))
+
 ## [0.68.1] - 2026-04-22
 
 ### Added
diff --git a/packages/ai/scripts/generate-models.ts b/packages/ai/scripts/generate-models.ts
index 95cfe1b1..29ea138d 100644
--- a/packages/ai/scripts/generate-models.ts
+++ b/packages/ai/scripts/generate-models.ts
@@ -1234,6 +1234,18 @@ async function generateModels() {
 			contextWindow: 1048576,
 			maxTokens: 65535,
 		},
+		{
+			id: "gemini-3.1-flash-lite-preview",
+			name: "Gemini 3.1 Flash Lite Preview (Cloud Code Assist)",
+			api: "google-gemini-cli",
+			provider: "google-gemini-cli",
+			baseUrl: CLOUD_CODE_ASSIST_ENDPOINT,
+			reasoning: true,
+			input: ["text", "image"],
+			cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+			contextWindow: 1048576,
+			maxTokens: 65535,
+		},
 		{
 			id: "gemini-3.1-pro-preview",
 			name: "Gemini 3.1 Pro Preview (Cloud Code Assist)",
diff --git a/packages/ai/src/models.generated.ts b/packages/ai/src/models.generated.ts
index 0fbd3a15..8e7e2433 100644
--- a/packages/ai/src/models.generated.ts
+++ b/packages/ai/src/models.generated.ts
@@ -4167,6 +4167,23 @@ export const MODELS = {
 			contextWindow: 1048576,
 			maxTokens: 65535,
 		} satisfies Model<"google-gemini-cli">,
+		"gemini-3.1-flash-lite-preview": {
+			id: "gemini-3.1-flash-lite-preview",
+			name: "Gemini 3.1 Flash Lite Preview (Cloud Code Assist)",
+			api: "google-gemini-cli",
+			provider: "google-gemini-cli",
+			baseUrl: "https://cloudcode-pa.googleapis.com",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65535,
+		} satisfies Model<"google-gemini-cli">,
 		"gemini-3.1-pro-preview": {
 			id: "gemini-3.1-pro-preview",
 			name: "Gemini 3.1 Pro Preview (Cloud Code Assist)",
@@ -7101,10 +7118,9 @@ export const MODELS = {
 		"qwen3.5-plus": {
 			id: "qwen3.5-plus",
 			name: "Qwen3.5 Plus",
-			api: "openai-completions",
+			api: "anthropic-messages",
 			provider: "opencode",
-			baseUrl: "https://opencode.ai/zen/v1",
-			compat: {"cacheControlFormat":"anthropic"},
+			baseUrl: "https://opencode.ai/zen",
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
@@ -7115,14 +7131,13 @@ export const MODELS = {
 			},
 			contextWindow: 262144,
 			maxTokens: 65536,
-		} satisfies Model<"openai-completions">,
+		} satisfies Model<"anthropic-messages">,
 		"qwen3.6-plus": {
 			id: "qwen3.6-plus",
 			name: "Qwen3.6 Plus",
-			api: "openai-completions",
+			api: "anthropic-messages",
 			provider: "opencode",
-			baseUrl: "https://opencode.ai/zen/v1",
-			compat: {"cacheControlFormat":"anthropic"},
+			baseUrl: "https://opencode.ai/zen",
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
@@ -7133,7 +7148,7 @@ export const MODELS = {
 			},
 			contextWindow: 262144,
 			maxTokens: 65536,
-		} satisfies Model<"openai-completions">,
+		} satisfies Model<"anthropic-messages">,
 	},
 	"opencode-go": {
 		"glm-5": {
@@ -7275,10 +7290,9 @@ export const MODELS = {
 		"qwen3.5-plus": {
 			id: "qwen3.5-plus",
 			name: "Qwen3.5 Plus",
-			api: "openai-completions",
+			api: "anthropic-messages",
 			provider: "opencode-go",
-			baseUrl: "https://opencode.ai/zen/go/v1",
-			compat: {"cacheControlFormat":"anthropic"},
+			baseUrl: "https://opencode.ai/zen/go",
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
@@ -7289,14 +7303,13 @@ export const MODELS = {
 			},
 			contextWindow: 262144,
 			maxTokens: 65536,
-		} satisfies Model<"openai-completions">,
+		} satisfies Model<"anthropic-messages">,
 		"qwen3.6-plus": {
 			id: "qwen3.6-plus",
 			name: "Qwen3.6 Plus",
-			api: "openai-completions",
+			api: "anthropic-messages",
 			provider: "opencode-go",
-			baseUrl: "https://opencode.ai/zen/go/v1",
-			compat: {"cacheControlFormat":"anthropic"},
+			baseUrl: "https://opencode.ai/zen/go",
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
@@ -7307,7 +7320,7 @@ export const MODELS = {
 			},
 			contextWindow: 262144,
 			maxTokens: 65536,
-		} satisfies Model<"openai-completions">,
+		} satisfies Model<"anthropic-messages">,
 	},
 	"openrouter": {
 		"ai21/jamba-large-1.7": {
diff --git a/packages/coding-agent/CHANGELOG.md b/packages/coding-agent/CHANGELOG.md
index 4c91f900..addd18b5 100644
--- a/packages/coding-agent/CHANGELOG.md
+++ b/packages/coding-agent/CHANGELOG.md
@@ -15,6 +15,7 @@
 ### Fixed
 
 - Fixed `ctx.getSystemPrompt()` inside `before_agent_start` to reflect chained system-prompt changes made by earlier `before_agent_start` handlers, and clarified the extension docs around provider-payload rewrites and what `ctx.getSystemPrompt()` does and does not report ([#3539](https://github.com/badlogic/pi-mono/issues/3539))
+- Fixed built-in `google-gemini-cli` model lists and selector entries to include `gemini-3.1-flash-lite-preview`, so Cloud Code Assist users no longer need manual `--model` fallback selection to use it ([#3545](https://github.com/badlogic/pi-mono/issues/3545))
 - Fixed extension session-replacement flows so `ctx.newSession()`, `ctx.fork()`, `ctx.switchSession()`, and imported-session replacements fully rebind before post-switch work runs, added `withSession` replacement callbacks with fresh `ReplacedSessionContext` helpers, and make stale pre-replacement `pi` / `ctx` session-bound accesses throw instead of silently targeting the wrong session ([#2860](https://github.com/badlogic/pi-mono/issues/2860))
 - Fixed `models.json` built-in provider overrides to accept `headers` without requiring `baseUrl`, so request-header-only overrides now load and apply correctly ([#3538](https://github.com/badlogic/pi-mono/issues/3538))