feat(ai): add gpt-5.3-codex-spark model definition

Added to both OpenAI API and OpenAI Codex (ChatGPT OAuth) providers.
128k context window, text-only, research preview with zero cost.
Not yet functional via pi, may become available in the next few hours or days.

packages/ai/CHANGELOG.md

@@ -5,6 +5,7 @@
 ### Added
 
 - Added optional `metadata` field to `StreamOptions` for passing provider-specific metadata (e.g. Anthropic `user_id` for abuse tracking/rate limiting) ([#1384](https://github.com/badlogic/pi-mono/pull/1384) by [@7Sageer](https://github.com/7Sageer))
+- Added `gpt-5.3-codex-spark` model definition for OpenAI and OpenAI Codex providers (128k context, text-only, research preview). Not yet functional, may become available in the next few hours or days.
 
 ### Changed
 

packages/ai/scripts/generate-models.ts

@@ -769,6 +769,26 @@ async function generateModels() {
 		});
 	}
 
+	if (!allModels.some(m => m.provider === "openai" && m.id === "gpt-5.3-codex-spark")) {
+		allModels.push({
+			id: "gpt-5.3-codex-spark",
+			name: "GPT-5.3 Codex Spark",
+			api: "openai-responses",
+			baseUrl: "https://api.openai.com/v1",
+			provider: "openai",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16384,
+		});
+	}
+
 	// OpenAI Codex (ChatGPT OAuth) models
 	// NOTE: These are not fetched from models.dev; we keep a small, explicit list to avoid aliases.
 	// Context window is based on observed server limits (400s above ~272k), not marketing numbers.
@@ -848,6 +868,18 @@ async function generateModels() {
 			contextWindow: CODEX_CONTEXT,
 			maxTokens: CODEX_MAX_TOKENS,
 		},
+		{
+			id: "gpt-5.3-codex-spark",
+			name: "GPT-5.3 Codex Spark",
+			api: "openai-codex-responses",
+			provider: "openai-codex",
+			baseUrl: CODEX_BASE_URL,
+			reasoning: true,
+			input: ["text"],
+			cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+			contextWindow: 128000,
+			maxTokens: CODEX_MAX_TOKENS,
+		},
 	];
 	allModels.push(...codexModels);