@oh-my-pi/pi-ai 3.20.0 → 3.34.0

package/src/models.generated.ts

@@ -415,6 +415,23 @@ export const MODELS = {
 			contextWindow: 131072,
 			maxTokens: 40960,
 		} satisfies Model<"openai-completions">,
+		"zai-glm-4.7": {
+			id: "zai-glm-4.7",
+			name: "Z.AI GLM-4.7",
+			api: "openai-completions",
+			provider: "cerebras",
+			baseUrl: "https://api.cerebras.ai/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 40000,
+		} satisfies Model<"openai-completions">,
 	},
 	"github-copilot": {
 		"claude-haiku-4.5": {
@@ -1337,6 +1354,195 @@ export const MODELS = {
 			maxTokens: 65535,
 		} satisfies Model<"google-gemini-cli">,
 	},
+	"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)",
+			api: "google-vertex",
+			provider: "google-vertex",
+			baseUrl: "https://{location}-aiplatform.googleapis.com",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.3,
+				output: 2.5,
+				cacheRead: 0.03,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		} 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)",
+			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-pro": {
+			id: "gemini-2.5-pro",
+			name: "Gemini 2.5 Pro (Vertex)",
+			api: "google-vertex",
+			provider: "google-vertex",
+			baseUrl: "https://{location}-aiplatform.googleapis.com",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.25,
+				output: 10,
+				cacheRead: 0.125,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		} satisfies Model<"google-vertex">,
+		"gemini-3-flash-preview": {
+			id: "gemini-3-flash-preview",
+			name: "Gemini 3 Flash Preview (Vertex)",
+			api: "google-vertex",
+			provider: "google-vertex",
+			baseUrl: "https://{location}-aiplatform.googleapis.com",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.5,
+				output: 3,
+				cacheRead: 0.05,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		} satisfies Model<"google-vertex">,
+		"gemini-3-pro-preview": {
+			id: "gemini-3-pro-preview",
+			name: "Gemini 3 Pro Preview (Vertex)",
+			api: "google-vertex",
+			provider: "google-vertex",
+			baseUrl: "https://{location}-aiplatform.googleapis.com",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 2,
+				output: 12,
+				cacheRead: 0.2,
+				cacheWrite: 0,
+			},
+			contextWindow: 1000000,
+			maxTokens: 64000,
+		} satisfies Model<"google-vertex">,
+	},
 	"groq": {
 		"deepseek-r1-distill-llama-70b": {
 			id: "deepseek-r1-distill-llama-70b",
@@ -2468,121 +2674,652 @@ export const MODELS = {
 			id: "o1-pro",
 			name: "o1-pro",
 			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 150,
+				output: 600,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 100000,
+		} satisfies Model<"openai-responses">,
+		"o3": {
+			id: "o3",
+			name: "o3",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 2,
+				output: 8,
+				cacheRead: 0.5,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 100000,
+		} satisfies Model<"openai-responses">,
+		"o3-deep-research": {
+			id: "o3-deep-research",
+			name: "o3-deep-research",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 10,
+				output: 40,
+				cacheRead: 2.5,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 100000,
+		} satisfies Model<"openai-responses">,
+		"o3-mini": {
+			id: "o3-mini",
+			name: "o3-mini",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 1.1,
+				output: 4.4,
+				cacheRead: 0.55,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 100000,
+		} satisfies Model<"openai-responses">,
+		"o3-pro": {
+			id: "o3-pro",
+			name: "o3-pro",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 20,
+				output: 80,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 100000,
+		} satisfies Model<"openai-responses">,
+		"o4-mini": {
+			id: "o4-mini",
+			name: "o4-mini",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.1,
+				output: 4.4,
+				cacheRead: 0.28,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 100000,
+		} satisfies Model<"openai-responses">,
+		"o4-mini-deep-research": {
+			id: "o4-mini-deep-research",
+			name: "o4-mini-deep-research",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 2,
+				output: 8,
+				cacheRead: 0.5,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 100000,
+		} satisfies Model<"openai-responses">,
+	},
+	"openai-codex": {
+		"gpt-5.1": {
+			id: "gpt-5.1",
+			name: "GPT-5.1",
+			api: "openai-codex-responses",
+			provider: "openai-codex",
+			baseUrl: "https://chatgpt.com/backend-api",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.25,
+				output: 10,
+				cacheRead: 0.125,
+				cacheWrite: 0,
+			},
+			contextWindow: 272000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-codex-responses">,
+		"gpt-5.1-codex-max": {
+			id: "gpt-5.1-codex-max",
+			name: "GPT-5.1 Codex Max",
+			api: "openai-codex-responses",
+			provider: "openai-codex",
+			baseUrl: "https://chatgpt.com/backend-api",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.25,
+				output: 10,
+				cacheRead: 0.125,
+				cacheWrite: 0,
+			},
+			contextWindow: 272000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-codex-responses">,
+		"gpt-5.1-codex-mini": {
+			id: "gpt-5.1-codex-mini",
+			name: "GPT-5.1 Codex Mini",
+			api: "openai-codex-responses",
+			provider: "openai-codex",
+			baseUrl: "https://chatgpt.com/backend-api",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.25,
+				output: 2,
+				cacheRead: 0.025,
+				cacheWrite: 0,
+			},
+			contextWindow: 272000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-codex-responses">,
+		"gpt-5.2": {
+			id: "gpt-5.2",
+			name: "GPT-5.2",
+			api: "openai-codex-responses",
+			provider: "openai-codex",
+			baseUrl: "https://chatgpt.com/backend-api",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.75,
+				output: 14,
+				cacheRead: 0.175,
+				cacheWrite: 0,
+			},
+			contextWindow: 272000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-codex-responses">,
+		"gpt-5.2-codex": {
+			id: "gpt-5.2-codex",
+			name: "GPT-5.2 Codex",
+			api: "openai-codex-responses",
+			provider: "openai-codex",
+			baseUrl: "https://chatgpt.com/backend-api",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.75,
+				output: 14,
+				cacheRead: 0.175,
+				cacheWrite: 0,
+			},
+			contextWindow: 272000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-codex-responses">,
+	},
+	"opencode": {
+		"alpha-gd4": {
+			id: "alpha-gd4",
+			name: "Alpha GD4",
+			api: "anthropic-messages",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.5,
+				output: 2,
+				cacheRead: 0.15,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 32768,
+		} satisfies Model<"anthropic-messages">,
+		"alpha-glm-4.7": {
+			id: "alpha-glm-4.7",
+			name: "Alpha GLM-4.7",
+			api: "openai-completions",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.6,
+				output: 2.2,
+				cacheRead: 0.6,
+				cacheWrite: 0,
+			},
+			contextWindow: 204800,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
+		"big-pickle": {
+			id: "big-pickle",
+			name: "Big Pickle",
+			api: "openai-completions",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-completions">,
+		"claude-3-5-haiku": {
+			id: "claude-3-5-haiku",
+			name: "Claude Haiku 3.5",
+			api: "anthropic-messages",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.8,
+				output: 4,
+				cacheRead: 0.08,
+				cacheWrite: 1,
+			},
+			contextWindow: 200000,
+			maxTokens: 8192,
+		} satisfies Model<"anthropic-messages">,
+		"claude-haiku-4-5": {
+			id: "claude-haiku-4-5",
+			name: "Claude Haiku 4.5",
+			api: "anthropic-messages",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1,
+				output: 5,
+				cacheRead: 0.1,
+				cacheWrite: 1.25,
+			},
+			contextWindow: 200000,
+			maxTokens: 64000,
+		} satisfies Model<"anthropic-messages">,
+		"claude-opus-4-1": {
+			id: "claude-opus-4-1",
+			name: "Claude Opus 4.1",
+			api: "anthropic-messages",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 15,
+				output: 75,
+				cacheRead: 1.5,
+				cacheWrite: 18.75,
+			},
+			contextWindow: 200000,
+			maxTokens: 32000,
+		} satisfies Model<"anthropic-messages">,
+		"claude-opus-4-5": {
+			id: "claude-opus-4-5",
+			name: "Claude Opus 4.5",
+			api: "anthropic-messages",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 5,
+				output: 25,
+				cacheRead: 0.5,
+				cacheWrite: 6.25,
+			},
+			contextWindow: 200000,
+			maxTokens: 64000,
+		} satisfies Model<"anthropic-messages">,
+		"claude-sonnet-4": {
+			id: "claude-sonnet-4",
+			name: "Claude Sonnet 4",
+			api: "anthropic-messages",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 3,
+				output: 15,
+				cacheRead: 0.3,
+				cacheWrite: 3.75,
+			},
+			contextWindow: 1000000,
+			maxTokens: 64000,
+		} satisfies Model<"anthropic-messages">,
+		"claude-sonnet-4-5": {
+			id: "claude-sonnet-4-5",
+			name: "Claude Sonnet 4.5",
+			api: "anthropic-messages",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 3,
+				output: 15,
+				cacheRead: 0.3,
+				cacheWrite: 3.75,
+			},
+			contextWindow: 1000000,
+			maxTokens: 64000,
+		} satisfies Model<"anthropic-messages">,
+		"gemini-3-flash": {
+			id: "gemini-3-flash",
+			name: "Gemini 3 Flash",
+			api: "google-generative-ai",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.5,
+				output: 3,
+				cacheRead: 0.05,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		} satisfies Model<"google-generative-ai">,
+		"gemini-3-pro": {
+			id: "gemini-3-pro",
+			name: "Gemini 3 Pro",
+			api: "google-generative-ai",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 2,
+				output: 12,
+				cacheRead: 0.2,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		} satisfies Model<"google-generative-ai">,
+		"glm-4.6": {
+			id: "glm-4.6",
+			name: "GLM-4.6",
+			api: "openai-completions",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.6,
+				output: 2.2,
+				cacheRead: 0.1,
+				cacheWrite: 0,
+			},
+			contextWindow: 204800,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
+		"glm-4.7-free": {
+			id: "glm-4.7-free",
+			name: "GLM-4.7",
+			api: "openai-completions",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 204800,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
+		"gpt-5": {
+			id: "gpt-5",
+			name: "GPT-5",
+			api: "openai-responses",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.07,
+				output: 8.5,
+				cacheRead: 0.107,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-responses">,
+		"gpt-5-codex": {
+			id: "gpt-5-codex",
+			name: "GPT-5 Codex",
+			api: "openai-responses",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.07,
+				output: 8.5,
+				cacheRead: 0.107,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-responses">,
+		"gpt-5-nano": {
+			id: "gpt-5-nano",
+			name: "GPT-5 Nano",
+			api: "openai-responses",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-responses">,
+		"gpt-5.1": {
+			id: "gpt-5.1",
+			name: "GPT-5.1",
+			api: "openai-responses",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.07,
+				output: 8.5,
+				cacheRead: 0.107,
+				cacheWrite: 0,
+			},
+			contextWindow: 400000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-responses">,
+		"gpt-5.1-codex": {
+			id: "gpt-5.1-codex",
+			name: "GPT-5.1 Codex",
+			api: "openai-responses",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen/v1",
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 150,
-				output: 600,
-				cacheRead: 0,
+				input: 1.07,
+				output: 8.5,
+				cacheRead: 0.107,
 				cacheWrite: 0,
 			},
-			contextWindow: 200000,
-			maxTokens: 100000,
+			contextWindow: 400000,
+			maxTokens: 128000,
 		} satisfies Model<"openai-responses">,
-		"o3": {
-			id: "o3",
-			name: "o3",
+		"gpt-5.1-codex-max": {
+			id: "gpt-5.1-codex-max",
+			name: "GPT-5.1 Codex Max",
 			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen/v1",
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 2,
-				output: 8,
-				cacheRead: 0.5,
+				input: 1.25,
+				output: 10,
+				cacheRead: 0.125,
 				cacheWrite: 0,
 			},
-			contextWindow: 200000,
-			maxTokens: 100000,
+			contextWindow: 400000,
+			maxTokens: 128000,
 		} satisfies Model<"openai-responses">,
-		"o3-deep-research": {
-			id: "o3-deep-research",
-			name: "o3-deep-research",
+		"gpt-5.1-codex-mini": {
+			id: "gpt-5.1-codex-mini",
+			name: "GPT-5.1 Codex Mini",
 			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen/v1",
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 10,
-				output: 40,
-				cacheRead: 2.5,
+				input: 0.25,
+				output: 2,
+				cacheRead: 0.025,
 				cacheWrite: 0,
 			},
-			contextWindow: 200000,
-			maxTokens: 100000,
+			contextWindow: 400000,
+			maxTokens: 128000,
 		} satisfies Model<"openai-responses">,
-		"o3-mini": {
-			id: "o3-mini",
-			name: "o3-mini",
+		"gpt-5.2": {
+			id: "gpt-5.2",
+			name: "GPT-5.2",
 			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen/v1",
 			reasoning: true,
-			input: ["text"],
+			input: ["text", "image"],
 			cost: {
-				input: 1.1,
-				output: 4.4,
-				cacheRead: 0.55,
+				input: 1.75,
+				output: 14,
+				cacheRead: 0.175,
 				cacheWrite: 0,
 			},
-			contextWindow: 200000,
-			maxTokens: 100000,
+			contextWindow: 400000,
+			maxTokens: 128000,
 		} satisfies Model<"openai-responses">,
-		"o3-pro": {
-			id: "o3-pro",
-			name: "o3-pro",
-			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
+		"grok-code": {
+			id: "grok-code",
+			name: "Grok Code Fast 1",
+			api: "openai-completions",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen/v1",
 			reasoning: true,
-			input: ["text", "image"],
+			input: ["text"],
 			cost: {
-				input: 20,
-				output: 80,
+				input: 0,
+				output: 0,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 200000,
-			maxTokens: 100000,
-		} satisfies Model<"openai-responses">,
-		"o4-mini": {
-			id: "o4-mini",
-			name: "o4-mini",
-			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
+			contextWindow: 256000,
+			maxTokens: 256000,
+		} satisfies Model<"openai-completions">,
+		"kimi-k2": {
+			id: "kimi-k2",
+			name: "Kimi K2",
+			api: "openai-completions",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.4,
+				output: 2.5,
+				cacheRead: 0.4,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 262144,
+		} satisfies Model<"openai-completions">,
+		"kimi-k2-thinking": {
+			id: "kimi-k2-thinking",
+			name: "Kimi K2 Thinking",
+			api: "openai-completions",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen/v1",
 			reasoning: true,
-			input: ["text", "image"],
+			input: ["text"],
 			cost: {
-				input: 1.1,
-				output: 4.4,
-				cacheRead: 0.28,
+				input: 0.4,
+				output: 2.5,
+				cacheRead: 0.4,
 				cacheWrite: 0,
 			},
-			contextWindow: 200000,
-			maxTokens: 100000,
-		} satisfies Model<"openai-responses">,
-		"o4-mini-deep-research": {
-			id: "o4-mini-deep-research",
-			name: "o4-mini-deep-research",
-			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
+			contextWindow: 262144,
+			maxTokens: 262144,
+		} satisfies Model<"openai-completions">,
+		"minimax-m2.1-free": {
+			id: "minimax-m2.1-free",
+			name: "MiniMax M2.1",
+			api: "anthropic-messages",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen",
 			reasoning: true,
-			input: ["text", "image"],
+			input: ["text"],
 			cost: {
-				input: 2,
-				output: 8,
-				cacheRead: 0.5,
+				input: 0,
+				output: 0,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 200000,
-			maxTokens: 100000,
-		} satisfies Model<"openai-responses">,
+			contextWindow: 204800,
+			maxTokens: 131072,
+		} satisfies Model<"anthropic-messages">,
+		"qwen3-coder": {
+			id: "qwen3-coder",
+			name: "Qwen3 Coder",
+			api: "openai-completions",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.45,
+				output: 1.8,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 65536,
+		} satisfies Model<"openai-completions">,
 	},
 	"openrouter": {
 		"ai21/jamba-large-1.7": {
@@ -2653,6 +3390,23 @@ export const MODELS = {
 			contextWindow: 65536,
 			maxTokens: 65536,
 		} satisfies Model<"openai-completions">,
+		"allenai/olmo-3.1-32b-instruct": {
+			id: "allenai/olmo-3.1-32b-instruct",
+			name: "AllenAI: Olmo 3.1 32B Instruct",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.19999999999999998,
+				output: 0.6,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 65536,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
 		"amazon/nova-2-lite-v1": {
 			id: "amazon/nova-2-lite-v1",
 			name: "Amazon: Nova 2 Lite",
@@ -3529,13 +4283,13 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text", "image"],
 			cost: {
-				input: 0.036,
-				output: 0.064,
+				input: 0.04,
+				output: 0.15,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 131072,
-			maxTokens: 4096,
+			contextWindow: 96000,
+			maxTokens: 96000,
 		} satisfies Model<"openai-completions">,
 		"google/gemma-3-27b-it:free": {
 			id: "google/gemma-3-27b-it:free",
@@ -3792,57 +4546,6 @@ export const MODELS = {
 			contextWindow: 327680,
 			maxTokens: 16384,
 		} satisfies Model<"openai-completions">,
-		"microsoft/phi-3-medium-128k-instruct": {
-			id: "microsoft/phi-3-medium-128k-instruct",
-			name: "Microsoft: Phi-3 Medium 128K Instruct",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 1,
-				output: 1,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"microsoft/phi-3-mini-128k-instruct": {
-			id: "microsoft/phi-3-mini-128k-instruct",
-			name: "Microsoft: Phi-3 Mini 128K Instruct",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.09999999999999999,
-				output: 0.09999999999999999,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
-		"microsoft/phi-3.5-mini-128k-instruct": {
-			id: "microsoft/phi-3.5-mini-128k-instruct",
-			name: "Microsoft: Phi-3.5 Mini 128K Instruct",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.09999999999999999,
-				output: 0.09999999999999999,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
 		"minimax/minimax-m1": {
 			id: "minimax/minimax-m1",
 			name: "MiniMax: MiniMax M1",
@@ -3886,9 +4589,9 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.12,
-				output: 0.48,
-				cacheRead: 0,
+				input: 0.28,
+				output: 1.2,
+				cacheRead: 0.14,
 				cacheWrite: 0,
 			},
 			contextWindow: 196608,
@@ -4481,13 +5184,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.32,
-				output: 0.48,
+				input: 0.39999999999999997,
+				output: 1.75,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
-			maxTokens: 4096,
+			maxTokens: 65535,
 		} satisfies Model<"openai-completions">,
 		"nex-agi/deepseek-v3.1-nex-n1:free": {
 			id: "nex-agi/deepseek-v3.1-nex-n1:free",
@@ -5263,8 +5966,8 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.02,
-				output: 0.09999999999999999,
+				input: 0.039,
+				output: 0.19,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
@@ -5314,13 +6017,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.016,
-				output: 0.06,
+				input: 0.02,
+				output: 0.09999999999999999,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
-			maxTokens: 4096,
+			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
 		"openai/gpt-oss-20b:free": {
 			id: "openai/gpt-oss-20b:free",
@@ -5560,6 +6263,23 @@ export const MODELS = {
 			contextWindow: 32768,
 			maxTokens: 16384,
 		} satisfies Model<"openai-completions">,
+		"qwen/qwen-2.5-7b-instruct": {
+			id: "qwen/qwen-2.5-7b-instruct",
+			name: "Qwen: Qwen2.5 7B Instruct",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.04,
+				output: 0.09999999999999999,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 32768,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
 		"qwen/qwen-max": {
 			id: "qwen/qwen-max",
 			name: "Qwen: Qwen-Max ",
@@ -5960,8 +6680,8 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0.06,
-				output: 0.6,
+				input: 0.09,
+				output: 1.1,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
@@ -5994,8 +6714,8 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text", "image"],
 			cost: {
-				input: 0.12,
-				output: 0.56,
+				input: 0.19999999999999998,
+				output: 1.2,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
@@ -6540,11 +7260,11 @@ export const MODELS = {
 			cost: {
 				input: 0.3,
 				output: 0.8999999999999999,
-				cacheRead: 0.049999999999999996,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
-			maxTokens: 24000,
+			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
 		"z-ai/glm-4.7": {
 			id: "z-ai/glm-4.7",
@@ -6555,13 +7275,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.16,
-				output: 0.7999999999999999,
+				input: 0.39999999999999997,
+				output: 1.5,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 202752,
-			maxTokens: 4096,
+			maxTokens: 65535,
 		} satisfies Model<"openai-completions">,
 	},
 	"xai": {