lsd-pi 1.1.2 → 1.1.3

package/packages/pi-ai/src/models.generated.ts

@@ -107,6 +107,23 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 8192,
 		} satisfies Model<"bedrock-converse-stream">,
+		"anthropic.claude-3-5-sonnet-20240620-v1:0": {
+			id: "anthropic.claude-3-5-sonnet-20240620-v1:0",
+			name: "Claude Sonnet 3.5",
+			api: "bedrock-converse-stream",
+			provider: "amazon-bedrock",
+			baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 3,
+				output: 15,
+				cacheRead: 0.3,
+				cacheWrite: 3.75,
+			},
+			contextWindow: 200000,
+			maxTokens: 8192,
+		} satisfies Model<"bedrock-converse-stream">,
 		"anthropic.claude-3-5-sonnet-20241022-v2:0": {
 			id: "anthropic.claude-3-5-sonnet-20241022-v2:0",
 			name: "Claude Sonnet 3.5 v2",
@@ -141,6 +158,23 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 8192,
 		} satisfies Model<"bedrock-converse-stream">,
+		"anthropic.claude-3-haiku-20240307-v1:0": {
+			id: "anthropic.claude-3-haiku-20240307-v1:0",
+			name: "Claude Haiku 3",
+			api: "bedrock-converse-stream",
+			provider: "amazon-bedrock",
+			baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.25,
+				output: 1.25,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 4096,
+		} satisfies Model<"bedrock-converse-stream">,
 		"anthropic.claude-haiku-4-5-20251001-v1:0": {
 			id: "anthropic.claude-haiku-4-5-20251001-v1:0",
 			name: "Claude Haiku 4.5",
@@ -770,23 +804,6 @@ export const MODELS = {
 			contextWindow: 204800,
 			maxTokens: 131072,
 		} satisfies Model<"bedrock-converse-stream">,
-		"minimax.minimax-m2.5": {
-			id: "minimax.minimax-m2.5",
-			name: "MiniMax M2.5",
-			api: "bedrock-converse-stream",
-			provider: "amazon-bedrock",
-			baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.3,
-				output: 1.2,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 196608,
-			maxTokens: 98304,
-		} satisfies Model<"bedrock-converse-stream">,
 		"mistral.devstral-2-123b": {
 			id: "mistral.devstral-2-123b",
 			name: "Devstral 2 123B",
@@ -1025,23 +1042,6 @@ export const MODELS = {
 			contextWindow: 128000,
 			maxTokens: 4096,
 		} satisfies Model<"bedrock-converse-stream">,
-		"nvidia.nemotron-super-3-120b": {
-			id: "nvidia.nemotron-super-3-120b",
-			name: "NVIDIA Nemotron 3 Super 120B A12B",
-			api: "bedrock-converse-stream",
-			provider: "amazon-bedrock",
-			baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.15,
-				output: 0.65,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 262144,
-			maxTokens: 131072,
-		} satisfies Model<"bedrock-converse-stream">,
 		"openai.gpt-oss-120b-1:0": {
 			id: "openai.gpt-oss-120b-1:0",
 			name: "gpt-oss-120b",
@@ -1416,23 +1416,6 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 131072,
 		} satisfies Model<"bedrock-converse-stream">,
-		"zai.glm-5": {
-			id: "zai.glm-5",
-			name: "GLM-5",
-			api: "bedrock-converse-stream",
-			provider: "amazon-bedrock",
-			baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 1,
-				output: 3.2,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 202752,
-			maxTokens: 101376,
-		} satisfies Model<"bedrock-converse-stream">,
 	},
 	"anthropic": {
 		"claude-3-5-haiku-20241022": {
@@ -1469,6 +1452,23 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 8192,
 		} satisfies Model<"anthropic-messages">,
+		"claude-3-5-sonnet-20240620": {
+			id: "claude-3-5-sonnet-20240620",
+			name: "Claude Sonnet 3.5",
+			api: "anthropic-messages",
+			provider: "anthropic",
+			baseUrl: "https://api.anthropic.com",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 3,
+				output: 15,
+				cacheRead: 0.3,
+				cacheWrite: 3.75,
+			},
+			contextWindow: 200000,
+			maxTokens: 8192,
+		} satisfies Model<"anthropic-messages">,
 		"claude-3-5-sonnet-20241022": {
 			id: "claude-3-5-sonnet-20241022",
 			name: "Claude Sonnet 3.5 v2",
@@ -1520,6 +1520,57 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 64000,
 		} satisfies Model<"anthropic-messages">,
+		"claude-3-haiku-20240307": {
+			id: "claude-3-haiku-20240307",
+			name: "Claude Haiku 3",
+			api: "anthropic-messages",
+			provider: "anthropic",
+			baseUrl: "https://api.anthropic.com",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.25,
+				output: 1.25,
+				cacheRead: 0.03,
+				cacheWrite: 0.3,
+			},
+			contextWindow: 200000,
+			maxTokens: 4096,
+		} satisfies Model<"anthropic-messages">,
+		"claude-3-opus-20240229": {
+			id: "claude-3-opus-20240229",
+			name: "Claude Opus 3",
+			api: "anthropic-messages",
+			provider: "anthropic",
+			baseUrl: "https://api.anthropic.com",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 15,
+				output: 75,
+				cacheRead: 1.5,
+				cacheWrite: 18.75,
+			},
+			contextWindow: 200000,
+			maxTokens: 4096,
+		} satisfies Model<"anthropic-messages">,
+		"claude-3-sonnet-20240229": {
+			id: "claude-3-sonnet-20240229",
+			name: "Claude Sonnet 3",
+			api: "anthropic-messages",
+			provider: "anthropic",
+			baseUrl: "https://api.anthropic.com",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 3,
+				output: 15,
+				cacheRead: 0.3,
+				cacheWrite: 0.3,
+			},
+			contextWindow: 200000,
+			maxTokens: 4096,
+		} satisfies Model<"anthropic-messages">,
 		"claude-haiku-4-5": {
 			id: "claude-haiku-4-5",
 			name: "Claude Haiku 4.5 (latest)",
@@ -1777,6 +1828,40 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 100000,
 		} satisfies Model<"azure-openai-responses">,
+		"gpt-4": {
+			id: "gpt-4",
+			name: "GPT-4",
+			api: "azure-openai-responses",
+			provider: "azure-openai-responses",
+			baseUrl: "",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 30,
+				output: 60,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 8192,
+			maxTokens: 8192,
+		} satisfies Model<"azure-openai-responses">,
+		"gpt-4-turbo": {
+			id: "gpt-4-turbo",
+			name: "GPT-4 Turbo",
+			api: "azure-openai-responses",
+			provider: "azure-openai-responses",
+			baseUrl: "",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 10,
+				output: 30,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 4096,
+		} satisfies Model<"azure-openai-responses">,
 		"gpt-4.1": {
 			id: "gpt-4.1",
 			name: "GPT-4.1",
@@ -1828,6 +1913,91 @@ export const MODELS = {
 			contextWindow: 1047576,
 			maxTokens: 32768,
 		} satisfies Model<"azure-openai-responses">,
+		"gpt-4o": {
+			id: "gpt-4o",
+			name: "GPT-4o",
+			api: "azure-openai-responses",
+			provider: "azure-openai-responses",
+			baseUrl: "",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 2.5,
+				output: 10,
+				cacheRead: 1.25,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16384,
+		} satisfies Model<"azure-openai-responses">,
+		"gpt-4o-2024-05-13": {
+			id: "gpt-4o-2024-05-13",
+			name: "GPT-4o (2024-05-13)",
+			api: "azure-openai-responses",
+			provider: "azure-openai-responses",
+			baseUrl: "",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 5,
+				output: 15,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 4096,
+		} satisfies Model<"azure-openai-responses">,
+		"gpt-4o-2024-08-06": {
+			id: "gpt-4o-2024-08-06",
+			name: "GPT-4o (2024-08-06)",
+			api: "azure-openai-responses",
+			provider: "azure-openai-responses",
+			baseUrl: "",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 2.5,
+				output: 10,
+				cacheRead: 1.25,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16384,
+		} satisfies Model<"azure-openai-responses">,
+		"gpt-4o-2024-11-20": {
+			id: "gpt-4o-2024-11-20",
+			name: "GPT-4o (2024-11-20)",
+			api: "azure-openai-responses",
+			provider: "azure-openai-responses",
+			baseUrl: "",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 2.5,
+				output: 10,
+				cacheRead: 1.25,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16384,
+		} satisfies Model<"azure-openai-responses">,
+		"gpt-4o-mini": {
+			id: "gpt-4o-mini",
+			name: "GPT-4o mini",
+			api: "azure-openai-responses",
+			provider: "azure-openai-responses",
+			baseUrl: "",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.15,
+				output: 0.6,
+				cacheRead: 0.08,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16384,
+		} satisfies Model<"azure-openai-responses">,
 		"gpt-5": {
 			id: "gpt-5",
 			name: "GPT-5",
@@ -2083,23 +2253,6 @@ export const MODELS = {
 			contextWindow: 400000,
 			maxTokens: 128000,
 		} satisfies Model<"azure-openai-responses">,
-		"gpt-5.3-chat-latest": {
-			id: "gpt-5.3-chat-latest",
-			name: "GPT-5.3 Chat (latest)",
-			api: "azure-openai-responses",
-			provider: "azure-openai-responses",
-			baseUrl: "",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 1.75,
-				output: 14,
-				cacheRead: 0.175,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 16384,
-		} satisfies Model<"azure-openai-responses">,
 		"gpt-5.3-codex": {
 			id: "gpt-5.3-codex",
 			name: "GPT-5.3 Codex",
@@ -2613,6 +2766,25 @@ export const MODELS = {
 			contextWindow: 128000,
 			maxTokens: 16384,
 		} satisfies Model<"openai-completions">,
+		"gpt-4o": {
+			id: "gpt-4o",
+			name: "GPT-4o",
+			api: "openai-completions",
+			provider: "github-copilot",
+			baseUrl: "https://api.individual.githubcopilot.com",
+			headers: {"User-Agent":"GitHubCopilotChat/0.35.0","Editor-Version":"vscode/1.107.0","Editor-Plugin-Version":"copilot-chat/0.35.0","Copilot-Integration-Id":"vscode-chat"},
+			compat: {"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false},
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
 		"gpt-5": {
 			id: "gpt-5",
 			name: "GPT-5",
@@ -2832,7 +3004,58 @@ export const MODELS = {
 		} satisfies Model<"openai-completions">,
 	},
 	"google": {
-		"gemini-2.0-flash": {
+		"gemini-1.5-flash": {
+			id: "gemini-1.5-flash",
+			name: "Gemini 1.5 Flash",
+			api: "google-generative-ai",
+			provider: "google",
+			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.075,
+				output: 0.3,
+				cacheRead: 0.01875,
+				cacheWrite: 0,
+			},
+			contextWindow: 1000000,
+			maxTokens: 8192,
+		} satisfies Model<"google-generative-ai">,
+		"gemini-1.5-flash-8b": {
+			id: "gemini-1.5-flash-8b",
+			name: "Gemini 1.5 Flash-8B",
+			api: "google-generative-ai",
+			provider: "google",
+			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.0375,
+				output: 0.15,
+				cacheRead: 0.01,
+				cacheWrite: 0,
+			},
+			contextWindow: 1000000,
+			maxTokens: 8192,
+		} satisfies Model<"google-generative-ai">,
+		"gemini-1.5-pro": {
+			id: "gemini-1.5-pro",
+			name: "Gemini 1.5 Pro",
+			api: "google-generative-ai",
+			provider: "google",
+			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 1.25,
+				output: 5,
+				cacheRead: 0.3125,
+				cacheWrite: 0,
+			},
+			contextWindow: 1000000,
+			maxTokens: 8192,
+		} satisfies Model<"google-generative-ai">,
+		"gemini-2.0-flash": {
 			id: "gemini-2.0-flash",
 			name: "Gemini 2.0 Flash",
 			api: "google-generative-ai",
@@ -3189,23 +3412,6 @@ export const MODELS = {
 			contextWindow: 131072,
 			maxTokens: 65536,
 		} satisfies Model<"google-generative-ai">,
-		"gemma-3-27b-it": {
-			id: "gemma-3-27b-it",
-			name: "Gemma 3 27B",
-			api: "google-generative-ai",
-			provider: "google",
-			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 8192,
-		} satisfies Model<"google-generative-ai">,
 	},
 	"google-antigravity": {
 		"claude-opus-4-5-thinking": {
@@ -3467,6 +3673,57 @@ export const MODELS = {
 		} 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)",
@@ -3656,40 +3913,6 @@ export const MODELS = {
 			contextWindow: 8192,
 			maxTokens: 8192,
 		} satisfies Model<"openai-completions">,
-		"groq/compound": {
-			id: "groq/compound",
-			name: "Compound",
-			api: "openai-completions",
-			provider: "groq",
-			baseUrl: "https://api.groq.com/openai/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
-		"groq/compound-mini": {
-			id: "groq/compound-mini",
-			name: "Compound Mini",
-			api: "openai-completions",
-			provider: "groq",
-			baseUrl: "https://api.groq.com/openai/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
 		"llama-3.1-8b-instant": {
 			id: "llama-3.1-8b-instant",
 			name: "Llama 3.1 8B Instant",
@@ -3877,23 +4100,6 @@ export const MODELS = {
 			contextWindow: 131072,
 			maxTokens: 65536,
 		} satisfies Model<"openai-completions">,
-		"openai/gpt-oss-safeguard-20b": {
-			id: "openai/gpt-oss-safeguard-20b",
-			name: "Safety GPT OSS 20B",
-			api: "openai-completions",
-			provider: "groq",
-			baseUrl: "https://api.groq.com/openai/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.075,
-				output: 0.3,
-				cacheRead: 0.037,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 65536,
-		} satisfies Model<"openai-completions">,
 		"qwen-qwq-32b": {
 			id: "qwen-qwq-32b",
 			name: "Qwen QwQ 32B",
@@ -3926,7 +4132,7 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
-			maxTokens: 40960,
+			maxTokens: 16384,
 		} satisfies Model<"openai-completions">,
 	},
 	"huggingface": {
@@ -4823,39 +5029,22 @@ export const MODELS = {
 			contextWindow: 128000,
 			maxTokens: 16384,
 		} satisfies Model<"mistral-conversations">,
-		"mistral-small-2603": {
-			id: "mistral-small-2603",
-			name: "Mistral Small 4",
-			api: "mistral-conversations",
-			provider: "mistral",
-			baseUrl: "https://api.mistral.ai",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 0.15,
-				output: 0.6,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 256000,
-			maxTokens: 256000,
-		} satisfies Model<"mistral-conversations">,
 		"mistral-small-latest": {
 			id: "mistral-small-latest",
 			name: "Mistral Small (latest)",
 			api: "mistral-conversations",
 			provider: "mistral",
 			baseUrl: "https://api.mistral.ai",
-			reasoning: true,
+			reasoning: false,
 			input: ["text", "image"],
 			cost: {
-				input: 0.15,
-				output: 0.6,
+				input: 0.1,
+				output: 0.3,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 256000,
-			maxTokens: 256000,
+			contextWindow: 128000,
+			maxTokens: 16384,
 		} satisfies Model<"mistral-conversations">,
 		"open-mistral-7b": {
 			id: "open-mistral-7b",
@@ -4940,77 +5129,196 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 128000,
-			maxTokens: 128000,
-		} satisfies Model<"mistral-conversations">,
-	},
-	"openai": {
-		"codex-mini-latest": {
-			id: "codex-mini-latest",
-			name: "Codex Mini",
+			maxTokens: 128000,
+		} satisfies Model<"mistral-conversations">,
+	},
+	"openai": {
+		"codex-mini-latest": {
+			id: "codex-mini-latest",
+			name: "Codex Mini",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 1.5,
+				output: 6,
+				cacheRead: 0.375,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 100000,
+		} satisfies Model<"openai-responses">,
+		"gpt-4": {
+			id: "gpt-4",
+			name: "GPT-4",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 30,
+				output: 60,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 8192,
+			maxTokens: 8192,
+		} satisfies Model<"openai-responses">,
+		"gpt-4-turbo": {
+			id: "gpt-4-turbo",
+			name: "GPT-4 Turbo",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 10,
+				output: 30,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-responses">,
+		"gpt-4.1": {
+			id: "gpt-4.1",
+			name: "GPT-4.1",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 2,
+				output: 8,
+				cacheRead: 0.5,
+				cacheWrite: 0,
+			},
+			contextWindow: 1047576,
+			maxTokens: 32768,
+		} satisfies Model<"openai-responses">,
+		"gpt-4.1-mini": {
+			id: "gpt-4.1-mini",
+			name: "GPT-4.1 mini",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.4,
+				output: 1.6,
+				cacheRead: 0.1,
+				cacheWrite: 0,
+			},
+			contextWindow: 1047576,
+			maxTokens: 32768,
+		} satisfies Model<"openai-responses">,
+		"gpt-4.1-nano": {
+			id: "gpt-4.1-nano",
+			name: "GPT-4.1 nano",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.1,
+				output: 0.4,
+				cacheRead: 0.03,
+				cacheWrite: 0,
+			},
+			contextWindow: 1047576,
+			maxTokens: 32768,
+		} satisfies Model<"openai-responses">,
+		"gpt-4o": {
+			id: "gpt-4o",
+			name: "GPT-4o",
+			api: "openai-responses",
+			provider: "openai",
+			baseUrl: "https://api.openai.com/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 2.5,
+				output: 10,
+				cacheRead: 1.25,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16384,
+		} satisfies Model<"openai-responses">,
+		"gpt-4o-2024-05-13": {
+			id: "gpt-4o-2024-05-13",
+			name: "GPT-4o (2024-05-13)",
 			api: "openai-responses",
 			provider: "openai",
 			baseUrl: "https://api.openai.com/v1",
-			reasoning: true,
-			input: ["text"],
+			reasoning: false,
+			input: ["text", "image"],
 			cost: {
-				input: 1.5,
-				output: 6,
-				cacheRead: 0.375,
+				input: 5,
+				output: 15,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 200000,
-			maxTokens: 100000,
+			contextWindow: 128000,
+			maxTokens: 4096,
 		} satisfies Model<"openai-responses">,
-		"gpt-4.1": {
-			id: "gpt-4.1",
-			name: "GPT-4.1",
+		"gpt-4o-2024-08-06": {
+			id: "gpt-4o-2024-08-06",
+			name: "GPT-4o (2024-08-06)",
 			api: "openai-responses",
 			provider: "openai",
 			baseUrl: "https://api.openai.com/v1",
 			reasoning: false,
 			input: ["text", "image"],
 			cost: {
-				input: 2,
-				output: 8,
-				cacheRead: 0.5,
+				input: 2.5,
+				output: 10,
+				cacheRead: 1.25,
 				cacheWrite: 0,
 			},
-			contextWindow: 1047576,
-			maxTokens: 32768,
+			contextWindow: 128000,
+			maxTokens: 16384,
 		} satisfies Model<"openai-responses">,
-		"gpt-4.1-mini": {
-			id: "gpt-4.1-mini",
-			name: "GPT-4.1 mini",
+		"gpt-4o-2024-11-20": {
+			id: "gpt-4o-2024-11-20",
+			name: "GPT-4o (2024-11-20)",
 			api: "openai-responses",
 			provider: "openai",
 			baseUrl: "https://api.openai.com/v1",
 			reasoning: false,
 			input: ["text", "image"],
 			cost: {
-				input: 0.4,
-				output: 1.6,
-				cacheRead: 0.1,
+				input: 2.5,
+				output: 10,
+				cacheRead: 1.25,
 				cacheWrite: 0,
 			},
-			contextWindow: 1047576,
-			maxTokens: 32768,
+			contextWindow: 128000,
+			maxTokens: 16384,
 		} satisfies Model<"openai-responses">,
-		"gpt-4.1-nano": {
-			id: "gpt-4.1-nano",
-			name: "GPT-4.1 nano",
+		"gpt-4o-mini": {
+			id: "gpt-4o-mini",
+			name: "GPT-4o mini",
 			api: "openai-responses",
 			provider: "openai",
 			baseUrl: "https://api.openai.com/v1",
 			reasoning: false,
 			input: ["text", "image"],
 			cost: {
-				input: 0.1,
-				output: 0.4,
-				cacheRead: 0.03,
+				input: 0.15,
+				output: 0.6,
+				cacheRead: 0.08,
 				cacheWrite: 0,
 			},
-			contextWindow: 1047576,
-			maxTokens: 32768,
+			contextWindow: 128000,
+			maxTokens: 16384,
 		} satisfies Model<"openai-responses">,
 		"gpt-5": {
 			id: "gpt-5",
@@ -5267,23 +5575,6 @@ export const MODELS = {
 			contextWindow: 400000,
 			maxTokens: 128000,
 		} satisfies Model<"openai-responses">,
-		"gpt-5.3-chat-latest": {
-			id: "gpt-5.3-chat-latest",
-			name: "GPT-5.3 Chat (latest)",
-			api: "openai-responses",
-			provider: "openai",
-			baseUrl: "https://api.openai.com/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 1.75,
-				output: 14,
-				cacheRead: 0.175,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 16384,
-		} satisfies Model<"openai-responses">,
 		"gpt-5.3-codex": {
 			id: "gpt-5.3-codex",
 			name: "GPT-5.3 Codex",
@@ -6206,23 +6497,6 @@ export const MODELS = {
 			contextWindow: 1000000,
 			maxTokens: 128000,
 		} satisfies Model<"openai-completions">,
-		"qwen3.6-plus-free": {
-			id: "qwen3.6-plus-free",
-			name: "Qwen3.6 Plus Free",
-			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: 1048576,
-			maxTokens: 64000,
-		} satisfies Model<"openai-completions">,
 	},
 	"opencode-go": {
 		"glm-5": {
@@ -6431,6 +6705,23 @@ export const MODELS = {
 			contextWindow: 300000,
 			maxTokens: 5120,
 		} satisfies Model<"openai-completions">,
+		"anthropic/claude-3-haiku": {
+			id: "anthropic/claude-3-haiku",
+			name: "Anthropic: Claude 3 Haiku",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.25,
+				output: 1.25,
+				cacheRead: 0.03,
+				cacheWrite: 0.3,
+			},
+			contextWindow: 200000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
 		"anthropic/claude-3.5-haiku": {
 			id: "anthropic/claude-3.5-haiku",
 			name: "Anthropic: Claude 3.5 Haiku",
@@ -7162,6 +7453,23 @@ export const MODELS = {
 			contextWindow: 1048576,
 			maxTokens: 65536,
 		} satisfies Model<"openai-completions">,
+		"google/gemini-3-pro-preview": {
+			id: "google/gemini-3-pro-preview",
+			name: "Google: Gemini 3 Pro Preview",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 2,
+				output: 12,
+				cacheRead: 0.19999999999999998,
+				cacheWrite: 0.375,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65536,
+		} satisfies Model<"openai-completions">,
 		"google/gemini-3.1-flash-lite-preview": {
 			id: "google/gemini-3.1-flash-lite-preview",
 			name: "Google: Gemini 3.1 Flash Lite Preview",
@@ -7264,22 +7572,22 @@ export const MODELS = {
 			contextWindow: 128000,
 			maxTokens: 32000,
 		} satisfies Model<"openai-completions">,
-		"kwaipilot/kat-coder-pro-v2": {
-			id: "kwaipilot/kat-coder-pro-v2",
-			name: "Kwaipilot: KAT-Coder-Pro V2",
+		"kwaipilot/kat-coder-pro": {
+			id: "kwaipilot/kat-coder-pro",
+			name: "Kwaipilot: KAT-Coder-Pro V1",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0.3,
-				output: 1.2,
-				cacheRead: 0.06,
+				input: 0.207,
+				output: 0.828,
+				cacheRead: 0.0414,
 				cacheWrite: 0,
 			},
 			contextWindow: 256000,
-			maxTokens: 80000,
+			maxTokens: 128000,
 		} satisfies Model<"openai-completions">,
 		"meituan/longcat-flash-chat": {
 			id: "meituan/longcat-flash-chat",
@@ -7477,9 +7785,9 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.16,
-				output: 1.1,
-				cacheRead: 0.08,
+				input: 0.19999999999999998,
+				output: 1.17,
+				cacheRead: 0.09999999999999999,
 				cacheWrite: 0,
 			},
 			contextWindow: 196608,
@@ -7808,6 +8116,23 @@ export const MODELS = {
 			contextWindow: 262144,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
+		"mistralai/mistral-small-3.1-24b-instruct:free": {
+			id: "mistralai/mistral-small-3.1-24b-instruct:free",
+			name: "Mistral: Mistral Small 3.1 24B (free)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
 		"mistralai/mistral-small-3.2-24b-instruct": {
 			id: "mistralai/mistral-small-3.2-24b-instruct",
 			name: "Mistral: Mistral Small 3.2 24B",
@@ -7919,13 +8244,13 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0.5700000000000001,
-				output: 2.3,
+				input: 0.55,
+				output: 2.2,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 131072,
-			maxTokens: 131072,
+			contextWindow: 131000,
+			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
 		"moonshotai/kimi-k2-0905": {
 			id: "moonshotai/kimi-k2-0905",
@@ -7987,8 +8312,8 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0.135,
-				output: 0.5,
+				input: 0.27,
+				output: 1,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
@@ -8074,7 +8399,7 @@ export const MODELS = {
 			cost: {
 				input: 0.09999999999999999,
 				output: 0.5,
-				cacheRead: 0.09999999999999999,
+				cacheRead: 0.04,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
@@ -8148,6 +8473,57 @@ export const MODELS = {
 			contextWindow: 128000,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
+		"openai/gpt-3.5-turbo": {
+			id: "openai/gpt-3.5-turbo",
+			name: "OpenAI: GPT-3.5 Turbo",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.5,
+				output: 1.5,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 16385,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-3.5-turbo-0613": {
+			id: "openai/gpt-3.5-turbo-0613",
+			name: "OpenAI: GPT-3.5 Turbo (older v0613)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 1,
+				output: 2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 4095,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-3.5-turbo-16k": {
+			id: "openai/gpt-3.5-turbo-16k",
+			name: "OpenAI: GPT-3.5 Turbo 16k",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 3,
+				output: 4,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 16385,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
 		"openai/gpt-4": {
 			id: "openai/gpt-4",
 			name: "OpenAI: GPT-4",
@@ -8199,6 +8575,40 @@ export const MODELS = {
 			contextWindow: 128000,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
+		"openai/gpt-4-turbo": {
+			id: "openai/gpt-4-turbo",
+			name: "OpenAI: GPT-4 Turbo",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 10,
+				output: 30,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
+		"openai/gpt-4-turbo-preview": {
+			id: "openai/gpt-4-turbo-preview",
+			name: "OpenAI: GPT-4 Turbo Preview",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 10,
+				output: 30,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
 		"openai/gpt-4.1": {
 			id: "openai/gpt-4.1",
 			name: "OpenAI: GPT-4.1",
@@ -8744,55 +9154,21 @@ export const MODELS = {
 			maxTokens: 128000,
 		} satisfies Model<"openai-completions">,
 		"openai/gpt-5.4-pro": {
-			id: "openai/gpt-5.4-pro",
-			name: "OpenAI: GPT-5.4 Pro",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 30,
-				output: 180,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 1050000,
-			maxTokens: 128000,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-audio": {
-			id: "openai/gpt-audio",
-			name: "OpenAI: GPT Audio",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 2.5,
-				output: 10,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
-		"openai/gpt-audio-mini": {
-			id: "openai/gpt-audio-mini",
-			name: "OpenAI: GPT Audio Mini",
+			id: "openai/gpt-5.4-pro",
+			name: "OpenAI: GPT-5.4 Pro",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
+			reasoning: true,
+			input: ["text", "image"],
 			cost: {
-				input: 0.6,
-				output: 2.4,
+				input: 30,
+				output: 180,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 128000,
-			maxTokens: 16384,
+			contextWindow: 1050000,
+			maxTokens: 128000,
 		} satisfies Model<"openai-completions">,
 		"openai/gpt-oss-120b": {
 			id: "openai/gpt-oss-120b",
@@ -9115,7 +9491,7 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 32768,
-			maxTokens: 32768,
+			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
 		"qwen/qwen-max": {
 			id: "qwen/qwen-max",
@@ -9355,6 +9731,23 @@ export const MODELS = {
 			contextWindow: 40960,
 			maxTokens: 40960,
 		} satisfies Model<"openai-completions">,
+		"qwen/qwen3-4b:free": {
+			id: "qwen/qwen3-4b:free",
+			name: "Qwen: Qwen3 4B (free)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 40960,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
 		"qwen/qwen3-8b": {
 			id: "qwen/qwen3-8b",
 			name: "Qwen: Qwen3 8B",
@@ -9761,7 +10154,7 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 256000,
-			maxTokens: 65536,
+			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
 		"qwen/qwen3.5-flash-02-23": {
 			id: "qwen/qwen3.5-flash-02-23",
@@ -9797,23 +10190,6 @@ export const MODELS = {
 			contextWindow: 1000000,
 			maxTokens: 65536,
 		} satisfies Model<"openai-completions">,
-		"qwen/qwen3.6-plus-preview:free": {
-			id: "qwen/qwen3.6-plus-preview:free",
-			name: "Qwen: Qwen3.6 Plus Preview (free)",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 1000000,
-			maxTokens: 32000,
-		} satisfies Model<"openai-completions">,
 		"qwen/qwq-32b": {
 			id: "qwen/qwq-32b",
 			name: "Qwen: QwQ 32B",
@@ -9831,23 +10207,6 @@ export const MODELS = {
 			contextWindow: 131072,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
-		"reka/reka-edge": {
-			id: "reka/reka-edge",
-			name: "Reka Edge",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.09999999999999999,
-				output: 0.09999999999999999,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 16384,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
 		"relace/relace-search": {
 			id: "relace/relace-search",
 			name: "Relace: Relace Search",
@@ -9910,11 +10269,11 @@ export const MODELS = {
 			cost: {
 				input: 0.09999999999999999,
 				output: 0.3,
-				cacheRead: 0,
+				cacheRead: 0.02,
 				cacheWrite: 0,
 			},
-			contextWindow: 262144,
-			maxTokens: 65536,
+			contextWindow: 256000,
+			maxTokens: 256000,
 		} satisfies Model<"openai-completions">,
 		"stepfun/step-3.5-flash:free": {
 			id: "stepfun/step-3.5-flash:free",
@@ -10120,23 +10479,6 @@ export const MODELS = {
 			contextWindow: 2000000,
 			maxTokens: 30000,
 		} satisfies Model<"openai-completions">,
-		"x-ai/grok-4.20": {
-			id: "x-ai/grok-4.20",
-			name: "xAI: Grok 4.20",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 2,
-				output: 6,
-				cacheRead: 0.19999999999999998,
-				cacheWrite: 0,
-			},
-			contextWindow: 2000000,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
 		"x-ai/grok-4.20-beta": {
 			id: "x-ai/grok-4.20-beta",
 			name: "xAI: Grok 4.20 Beta",
@@ -10401,9 +10743,9 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 1.2,
-				output: 4,
-				cacheRead: 0.24,
+				input: 0.96,
+				output: 3.1999999999999997,
+				cacheRead: 0.192,
 				cacheWrite: 0,
 			},
 			contextWindow: 202752,
@@ -10437,12 +10779,12 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0.22,
-				output: 0.88,
-				cacheRead: 0.11,
+				input: 0.071,
+				output: 0.463,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 32768,
+			contextWindow: 40960,
 			maxTokens: 16384,
 		} satisfies Model<"anthropic-messages">,
 		"alibaba/qwen-3-30b": {
@@ -10471,13 +10813,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.16,
-				output: 0.64,
-				cacheRead: 0,
+				input: 0.29,
+				output: 0.59,
+				cacheRead: 0.145,
 				cacheWrite: 0,
 			},
-			contextWindow: 128000,
-			maxTokens: 8192,
+			contextWindow: 131072,
+			maxTokens: 40960,
 		} satisfies Model<"anthropic-messages">,
 		"alibaba/qwen3-235b-a22b-thinking": {
 			id: "alibaba/qwen3-235b-a22b-thinking",
@@ -10505,13 +10847,13 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 1.5,
-				output: 7.5,
-				cacheRead: 0.3,
+				input: 0.39999999999999997,
+				output: 1.5999999999999999,
+				cacheRead: 0.022,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
-			maxTokens: 65536,
+			maxTokens: 66536,
 		} satisfies Model<"anthropic-messages">,
 		"alibaba/qwen3-coder-30b-a3b": {
 			id: "alibaba/qwen3-coder-30b-a3b",
@@ -10666,6 +11008,23 @@ export const MODELS = {
 			contextWindow: 1000000,
 			maxTokens: 64000,
 		} satisfies Model<"anthropic-messages">,
+		"anthropic/claude-3-haiku": {
+			id: "anthropic/claude-3-haiku",
+			name: "Claude 3 Haiku",
+			api: "anthropic-messages",
+			provider: "vercel-ai-gateway",
+			baseUrl: "https://ai-gateway.vercel.sh",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.25,
+				output: 1.25,
+				cacheRead: 0.03,
+				cacheWrite: 0.3,
+			},
+			contextWindow: 200000,
+			maxTokens: 4096,
+		} satisfies Model<"anthropic-messages">,
 		"anthropic/claude-3.5-haiku": {
 			id: "anthropic/claude-3.5-haiku",
 			name: "Claude 3.5 Haiku",
@@ -10964,13 +11323,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.56,
-				output: 1.68,
-				cacheRead: 0.28,
+				input: 0.5,
+				output: 1.5,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 163840,
-			maxTokens: 8192,
+			maxTokens: 16384,
 		} satisfies Model<"anthropic-messages">,
 		"deepseek/deepseek-v3.1-terminus": {
 			id: "deepseek/deepseek-v3.1-terminus",
@@ -11210,23 +11569,6 @@ export const MODELS = {
 			contextWindow: 32000,
 			maxTokens: 16384,
 		} satisfies Model<"anthropic-messages">,
-		"kwaipilot/kat-coder-pro-v2": {
-			id: "kwaipilot/kat-coder-pro-v2",
-			name: "Kat Coder Pro V2",
-			api: "anthropic-messages",
-			provider: "vercel-ai-gateway",
-			baseUrl: "https://ai-gateway.vercel.sh",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.3,
-				output: 1.2,
-				cacheRead: 0.06,
-				cacheWrite: 0,
-			},
-			contextWindow: 256000,
-			maxTokens: 256000,
-		} satisfies Model<"anthropic-messages">,
 		"meituan/longcat-flash-chat": {
 			id: "meituan/longcat-flash-chat",
 			name: "LongCat Flash Chat",
@@ -11242,7 +11584,7 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 128000,
-			maxTokens: 8192,
+			maxTokens: 100000,
 		} satisfies Model<"anthropic-messages">,
 		"meituan/longcat-flash-thinking": {
 			id: "meituan/longcat-flash-thinking",
@@ -11287,13 +11629,13 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0.22,
-				output: 0.22,
-				cacheRead: 0,
+				input: 0.09999999999999999,
+				output: 0.09999999999999999,
+				cacheRead: 0.09999999999999999,
 				cacheWrite: 0,
 			},
 			contextWindow: 128000,
-			maxTokens: 8192,
+			maxTokens: 16384,
 		} satisfies Model<"anthropic-messages">,
 		"meta/llama-3.2-11b": {
 			id: "meta/llama-3.2-11b",
@@ -11355,12 +11697,12 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text", "image"],
 			cost: {
-				input: 0.35,
-				output: 1.15,
+				input: 0.24,
+				output: 0.9700000000000001,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 524288,
+			contextWindow: 128000,
 			maxTokens: 8192,
 		} satisfies Model<"anthropic-messages">,
 		"meta/llama-4-scout": {
@@ -11805,6 +12147,23 @@ export const MODELS = {
 			contextWindow: 131072,
 			maxTokens: 131072,
 		} satisfies Model<"anthropic-messages">,
+		"openai/gpt-4-turbo": {
+			id: "openai/gpt-4-turbo",
+			name: "GPT-4 Turbo",
+			api: "anthropic-messages",
+			provider: "vercel-ai-gateway",
+			baseUrl: "https://ai-gateway.vercel.sh",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 10,
+				output: 30,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 4096,
+		} satisfies Model<"anthropic-messages">,
 		"openai/gpt-4.1": {
 			id: "openai/gpt-4.1",
 			name: "GPT-4.1",
@@ -12247,23 +12606,6 @@ export const MODELS = {
 			contextWindow: 1050000,
 			maxTokens: 128000,
 		} satisfies Model<"anthropic-messages">,
-		"openai/gpt-oss-120b": {
-			id: "openai/gpt-oss-120b",
-			name: "gpt-oss-120b",
-			api: "anthropic-messages",
-			provider: "vercel-ai-gateway",
-			baseUrl: "https://ai-gateway.vercel.sh",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.15,
-				output: 0.6,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 128000,
-			maxTokens: 8192,
-		} satisfies Model<"anthropic-messages">,
 		"openai/gpt-oss-20b": {
 			id: "openai/gpt-oss-20b",
 			name: "gpt-oss-20b",
@@ -12409,8 +12751,8 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text", "image"],
 			cost: {
-				input: 0,
-				output: 0,
+				input: 1,
+				output: 1,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
@@ -12426,8 +12768,8 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text", "image"],
 			cost: {
-				input: 0,
-				output: 0,
+				input: 3,
+				output: 15,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
@@ -12621,23 +12963,6 @@ export const MODELS = {
 			contextWindow: 2000000,
 			maxTokens: 30000,
 		} satisfies Model<"anthropic-messages">,
-		"xai/grok-4.20-multi-agent": {
-			id: "xai/grok-4.20-multi-agent",
-			name: "Grok 4.20 Multi-Agent",
-			api: "anthropic-messages",
-			provider: "vercel-ai-gateway",
-			baseUrl: "https://ai-gateway.vercel.sh",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 2,
-				output: 6,
-				cacheRead: 0.19999999999999998,
-				cacheWrite: 0,
-			},
-			contextWindow: 2000000,
-			maxTokens: 2000000,
-		} satisfies Model<"anthropic-messages">,
 		"xai/grok-4.20-multi-agent-beta": {
 			id: "xai/grok-4.20-multi-agent-beta",
 			name: "Grok 4.20 Multi Agent Beta",
@@ -12655,23 +12980,6 @@ export const MODELS = {
 			contextWindow: 2000000,
 			maxTokens: 2000000,
 		} satisfies Model<"anthropic-messages">,
-		"xai/grok-4.20-non-reasoning": {
-			id: "xai/grok-4.20-non-reasoning",
-			name: "Grok 4.20 Non-Reasoning",
-			api: "anthropic-messages",
-			provider: "vercel-ai-gateway",
-			baseUrl: "https://ai-gateway.vercel.sh",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 2,
-				output: 6,
-				cacheRead: 0.19999999999999998,
-				cacheWrite: 0,
-			},
-			contextWindow: 2000000,
-			maxTokens: 2000000,
-		} satisfies Model<"anthropic-messages">,
 		"xai/grok-4.20-non-reasoning-beta": {
 			id: "xai/grok-4.20-non-reasoning-beta",
 			name: "Grok 4.20 Beta Non-Reasoning",
@@ -12689,23 +12997,6 @@ export const MODELS = {
 			contextWindow: 2000000,
 			maxTokens: 2000000,
 		} satisfies Model<"anthropic-messages">,
-		"xai/grok-4.20-reasoning": {
-			id: "xai/grok-4.20-reasoning",
-			name: "Grok 4.20 Reasoning",
-			api: "anthropic-messages",
-			provider: "vercel-ai-gateway",
-			baseUrl: "https://ai-gateway.vercel.sh",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 2,
-				output: 6,
-				cacheRead: 0.19999999999999998,
-				cacheWrite: 0,
-			},
-			contextWindow: 2000000,
-			maxTokens: 2000000,
-		} satisfies Model<"anthropic-messages">,
 		"xai/grok-4.20-reasoning-beta": {
 			id: "xai/grok-4.20-reasoning-beta",
 			name: "Grok 4.20 Beta Reasoning",
@@ -12749,9 +13040,9 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.09,
-				output: 0.29,
-				cacheRead: 0.045,
+				input: 0.09999999999999999,
+				output: 0.3,
+				cacheRead: 0.02,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
@@ -12887,7 +13178,7 @@ export const MODELS = {
 			cost: {
 				input: 0.6,
 				output: 2.2,
-				cacheRead: 0.11,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 200000,
@@ -13517,24 +13808,6 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
-		"glm-4.7-flashx": {
-			id: "glm-4.7-flashx",
-			name: "GLM-4.7-FlashX",
-			api: "openai-completions",
-			provider: "zai",
-			baseUrl: "https://api.z.ai/api/coding/paas/v4",
-			compat: {"supportsDeveloperRole":false,"thinkingFormat":"zai"},
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.07,
-				output: 0.4,
-				cacheRead: 0.01,
-				cacheWrite: 0,
-			},
-			contextWindow: 200000,
-			maxTokens: 131072,
-		} satisfies Model<"openai-completions">,
 		"glm-5": {
 			id: "glm-5",
 			name: "GLM-5",