gsd-pi 2.72.0-dev.de4c4b3 → 2.73.0-dev.1cfd50c

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

@@ -804,6 +804,23 @@ 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",
@@ -1042,6 +1059,23 @@ 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",
@@ -1178,6 +1212,23 @@ export const MODELS = {
 			contextWindow: 131072,
 			maxTokens: 65536,
 		} satisfies Model<"bedrock-converse-stream">,
+		"qwen.qwen3-coder-next": {
+			id: "qwen.qwen3-coder-next",
+			name: "Qwen3 Coder Next",
+			api: "bedrock-converse-stream",
+			provider: "amazon-bedrock",
+			baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.22,
+				output: 1.8,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 65536,
+		} satisfies Model<"bedrock-converse-stream">,
 		"qwen.qwen3-next-80b-a3b": {
 			id: "qwen.qwen3-next-80b-a3b",
 			name: "Qwen/Qwen3-Next-80B-A3B-Instruct",
@@ -1416,6 +1467,23 @@ 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": {
@@ -1503,23 +1571,6 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 64000,
 		} satisfies Model<"anthropic-messages">,
-		"claude-3-7-sonnet-latest": {
-			id: "claude-3-7-sonnet-latest",
-			name: "Claude Sonnet 3.7 (latest)",
-			api: "anthropic-messages",
-			provider: "anthropic",
-			baseUrl: "https://api.anthropic.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 3,
-				output: 15,
-				cacheRead: 0.3,
-				cacheWrite: 3.75,
-			},
-			contextWindow: 200000,
-			maxTokens: 64000,
-		} satisfies Model<"anthropic-messages">,
 		"claude-3-haiku-20240307": {
 			id: "claude-3-haiku-20240307",
 			name: "Claude Haiku 3",
@@ -2253,6 +2304,23 @@ 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",
@@ -2967,7 +3035,7 @@ export const MODELS = {
 		} satisfies Model<"openai-responses">,
 		"gpt-5.4-mini": {
 			id: "gpt-5.4-mini",
-			name: "GPT-5.4 mini",
+			name: "GPT-5.4 Mini",
 			api: "openai-responses",
 			provider: "github-copilot",
 			baseUrl: "https://api.individual.githubcopilot.com",
@@ -3412,6 +3480,57 @@ 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">,
+		"gemma-4-26b-it": {
+			id: "gemma-4-26b-it",
+			name: "Gemma 4 26B",
+			api: "google-generative-ai",
+			provider: "google",
+			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 256000,
+			maxTokens: 8192,
+		} satisfies Model<"google-generative-ai">,
+		"gemma-4-31b-it": {
+			id: "gemma-4-31b-it",
+			name: "Gemma 4 31B",
+			api: "google-generative-ai",
+			provider: "google",
+			baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 256000,
+			maxTokens: 8192,
+		} satisfies Model<"google-generative-ai">,
 	},
 	"google-antigravity": {
 		"claude-opus-4-5-thinking": {
@@ -3913,6 +4032,40 @@ 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",
@@ -4100,6 +4253,23 @@ 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",
@@ -4132,7 +4302,7 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
-			maxTokens: 16384,
+			maxTokens: 40960,
 		} satisfies Model<"openai-completions">,
 	},
 	"huggingface": {
@@ -4460,6 +4630,24 @@ export const MODELS = {
 			contextWindow: 202752,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
+		"zai-org/GLM-5.1": {
+			id: "zai-org/GLM-5.1",
+			name: "GLM-5.1",
+			api: "openai-completions",
+			provider: "huggingface",
+			baseUrl: "https://router.huggingface.co/v1",
+			compat: {"supportsDeveloperRole":false},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 1,
+				output: 3.2,
+				cacheRead: 0.2,
+				cacheWrite: 0,
+			},
+			contextWindow: 202752,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
 	},
 	"kimi-coding": {
 		"k2p5": {
@@ -5029,22 +5217,39 @@ 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: false,
+			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 0.1,
-				output: 0.3,
+				input: 0.15,
+				output: 0.6,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 128000,
-			maxTokens: 16384,
+			contextWindow: 256000,
+			maxTokens: 256000,
 		} satisfies Model<"mistral-conversations">,
 		"open-mistral-7b": {
 			id: "open-mistral-7b",
@@ -5575,6 +5780,23 @@ 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",
@@ -6157,6 +6379,23 @@ export const MODELS = {
 			contextWindow: 204800,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
+		"glm-5.1": {
+			id: "glm-5.1",
+			name: "GLM-5.1",
+			api: "openai-completions",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 1.4,
+				output: 4.4,
+				cacheRead: 0.26,
+				cacheWrite: 0,
+			},
+			contextWindow: 204800,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
 		"gpt-5": {
 			id: "gpt-5",
 			name: "GPT-5",
@@ -6412,56 +6651,22 @@ export const MODELS = {
 			contextWindow: 262144,
 			maxTokens: 65536,
 		} satisfies Model<"openai-completions">,
-		"mimo-v2-omni-free": {
-			id: "mimo-v2-omni-free",
-			name: "MiMo V2 Omni Free",
+		"minimax-m2.5": {
+			id: "minimax-m2.5",
+			name: "MiniMax M2.5",
 			api: "openai-completions",
 			provider: "opencode",
 			baseUrl: "https://opencode.ai/zen/v1",
 			reasoning: true,
-			input: ["text", "image"],
+			input: ["text"],
 			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
+				input: 0.3,
+				output: 1.2,
+				cacheRead: 0.06,
 				cacheWrite: 0,
 			},
-			contextWindow: 262144,
-			maxTokens: 64000,
-		} satisfies Model<"openai-completions">,
-		"mimo-v2-pro-free": {
-			id: "mimo-v2-pro-free",
-			name: "MiMo V2 Pro 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">,
-		"minimax-m2.5": {
-			id: "minimax-m2.5",
-			name: "MiniMax M2.5",
-			api: "openai-completions",
-			provider: "opencode",
-			baseUrl: "https://opencode.ai/zen/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.3,
-				output: 1.2,
-				cacheRead: 0.06,
-				cacheWrite: 0,
-			},
-			contextWindow: 204800,
-			maxTokens: 131072,
+			contextWindow: 204800,
+			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
 		"minimax-m2.5-free": {
 			id: "minimax-m2.5-free",
@@ -6494,7 +6699,7 @@ export const MODELS = {
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 1000000,
+			contextWindow: 204800,
 			maxTokens: 128000,
 		} satisfies Model<"openai-completions">,
 	},
@@ -6516,6 +6721,23 @@ export const MODELS = {
 			contextWindow: 204800,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
+		"glm-5.1": {
+			id: "glm-5.1",
+			name: "GLM-5.1",
+			api: "openai-completions",
+			provider: "opencode-go",
+			baseUrl: "https://opencode.ai/zen/go/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 1.4,
+				output: 4.4,
+				cacheRead: 0.26,
+				cacheWrite: 0,
+			},
+			contextWindow: 204800,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
 		"kimi-k2.5": {
 			id: "kimi-k2.5",
 			name: "Kimi K2.5",
@@ -6533,6 +6755,40 @@ export const MODELS = {
 			contextWindow: 262144,
 			maxTokens: 65536,
 		} satisfies Model<"openai-completions">,
+		"mimo-v2-omni": {
+			id: "mimo-v2-omni",
+			name: "MiMo V2 Omni",
+			api: "openai-completions",
+			provider: "opencode-go",
+			baseUrl: "https://opencode.ai/zen/go/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.4,
+				output: 2,
+				cacheRead: 0.08,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 64000,
+		} satisfies Model<"openai-completions">,
+		"mimo-v2-pro": {
+			id: "mimo-v2-pro",
+			name: "MiMo V2 Pro",
+			api: "openai-completions",
+			provider: "opencode-go",
+			baseUrl: "https://opencode.ai/zen/go/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 1,
+				output: 3,
+				cacheRead: 0.2,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 64000,
+		} satisfies Model<"openai-completions">,
 		"minimax-m2.5": {
 			id: "minimax-m2.5",
 			name: "MiniMax M2.5",
@@ -6739,23 +6995,6 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 8192,
 		} satisfies Model<"openai-completions">,
-		"anthropic/claude-3.5-sonnet": {
-			id: "anthropic/claude-3.5-sonnet",
-			name: "Anthropic: Claude 3.5 Sonnet",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 6,
-				output: 30,
-				cacheRead: 0.6,
-				cacheWrite: 7.5,
-			},
-			contextWindow: 200000,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
 		"anthropic/claude-3.7-sonnet": {
 			id: "anthropic/claude-3.7-sonnet",
 			name: "Anthropic: Claude 3.7 Sonnet",
@@ -6771,7 +7010,7 @@ export const MODELS = {
 				cacheWrite: 3.75,
 			},
 			contextWindow: 200000,
-			maxTokens: 64000,
+			maxTokens: 128000,
 		} satisfies Model<"openai-completions">,
 		"anthropic/claude-3.7-sonnet:thinking": {
 			id: "anthropic/claude-3.7-sonnet:thinking",
@@ -6875,6 +7114,23 @@ export const MODELS = {
 			contextWindow: 1000000,
 			maxTokens: 128000,
 		} satisfies Model<"openai-completions">,
+		"anthropic/claude-opus-4.6-fast": {
+			id: "anthropic/claude-opus-4.6-fast",
+			name: "Anthropic: Claude Opus 4.6 (Fast)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 30,
+				output: 150,
+				cacheRead: 3,
+				cacheWrite: 37.5,
+			},
+			contextWindow: 1000000,
+			maxTokens: 128000,
+		} satisfies Model<"openai-completions">,
 		"anthropic/claude-sonnet-4": {
 			id: "anthropic/claude-sonnet-4",
 			name: "Anthropic: Claude Sonnet 4",
@@ -6889,7 +7145,7 @@ export const MODELS = {
 				cacheRead: 0.3,
 				cacheWrite: 3.75,
 			},
-			contextWindow: 200000,
+			contextWindow: 1000000,
 			maxTokens: 64000,
 		} satisfies Model<"openai-completions">,
 		"anthropic/claude-sonnet-4.5": {
@@ -6943,39 +7199,39 @@ export const MODELS = {
 			contextWindow: 131000,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
-		"arcee-ai/trinity-mini": {
-			id: "arcee-ai/trinity-mini",
-			name: "Arcee AI: Trinity Mini",
+		"arcee-ai/trinity-large-thinking": {
+			id: "arcee-ai/trinity-large-thinking",
+			name: "Arcee AI: Trinity Large Thinking",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.045,
-				output: 0.15,
+				input: 0.22,
+				output: 0.85,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 131072,
-			maxTokens: 131072,
+			contextWindow: 262144,
+			maxTokens: 262144,
 		} satisfies Model<"openai-completions">,
-		"arcee-ai/trinity-mini:free": {
-			id: "arcee-ai/trinity-mini:free",
-			name: "Arcee AI: Trinity Mini (free)",
+		"arcee-ai/trinity-mini": {
+			id: "arcee-ai/trinity-mini",
+			name: "Arcee AI: Trinity Mini",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0,
-				output: 0,
+				input: 0.045,
+				output: 0.15,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
-			maxTokens: 4096,
+			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
 		"arcee-ai/virtuoso-large": {
 			id: "arcee-ai/virtuoso-large",
@@ -7224,13 +7480,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.44999999999999996,
+				input: 0.5,
 				output: 2.1500000000000004,
-				cacheRead: 0.22499999999999998,
+				cacheRead: 0.35,
 				cacheWrite: 0,
 			},
 			contextWindow: 163840,
-			maxTokens: 65536,
+			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
 		"deepseek/deepseek-v3.1-terminus": {
 			id: "deepseek/deepseek-v3.1-terminus",
@@ -7383,7 +7639,7 @@ export const MODELS = {
 				cacheWrite: 0.08333333333333334,
 			},
 			contextWindow: 1048576,
-			maxTokens: 65536,
+			maxTokens: 65535,
 		} satisfies Model<"openai-completions">,
 		"google/gemini-2.5-pro": {
 			id: "google/gemini-2.5-pro",
@@ -7453,23 +7709,6 @@ 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",
@@ -7521,6 +7760,74 @@ export const MODELS = {
 			contextWindow: 1048576,
 			maxTokens: 65536,
 		} satisfies Model<"openai-completions">,
+		"google/gemma-4-26b-a4b-it": {
+			id: "google/gemma-4-26b-a4b-it",
+			name: "Google: Gemma 4 26B A4B ",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.12,
+				output: 0.39999999999999997,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 262144,
+		} satisfies Model<"openai-completions">,
+		"google/gemma-4-26b-a4b-it:free": {
+			id: "google/gemma-4-26b-a4b-it:free",
+			name: "Google: Gemma 4 26B A4B  (free)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 32768,
+		} satisfies Model<"openai-completions">,
+		"google/gemma-4-31b-it": {
+			id: "google/gemma-4-31b-it",
+			name: "Google: Gemma 4 31B",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.14,
+				output: 0.39999999999999997,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
+		"google/gemma-4-31b-it:free": {
+			id: "google/gemma-4-31b-it:free",
+			name: "Google: Gemma 4 31B (free)",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 32768,
+		} satisfies Model<"openai-completions">,
 		"inception/mercury": {
 			id: "inception/mercury",
 			name: "Inception: Mercury",
@@ -7572,22 +7879,22 @@ export const MODELS = {
 			contextWindow: 128000,
 			maxTokens: 32000,
 		} satisfies Model<"openai-completions">,
-		"kwaipilot/kat-coder-pro": {
-			id: "kwaipilot/kat-coder-pro",
-			name: "Kwaipilot: KAT-Coder-Pro V1",
+		"kwaipilot/kat-coder-pro-v2": {
+			id: "kwaipilot/kat-coder-pro-v2",
+			name: "Kwaipilot: KAT-Coder-Pro V2",
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0.207,
-				output: 0.828,
-				cacheRead: 0.0414,
+				input: 0.3,
+				output: 1.2,
+				cacheRead: 0.06,
 				cacheWrite: 0,
 			},
 			contextWindow: 256000,
-			maxTokens: 128000,
+			maxTokens: 80000,
 		} satisfies Model<"openai-completions">,
 		"meituan/longcat-flash-chat": {
 			id: "meituan/longcat-flash-chat",
@@ -7768,13 +8075,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.27,
+				input: 0.29,
 				output: 0.95,
-				cacheRead: 0.0290000007,
+				cacheRead: 0.03,
 				cacheWrite: 0,
 			},
 			contextWindow: 196608,
-			maxTokens: 4096,
+			maxTokens: 196608,
 		} satisfies Model<"openai-completions">,
 		"minimax/minimax-m2.5": {
 			id: "minimax/minimax-m2.5",
@@ -7785,9 +8092,9 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.19999999999999998,
-				output: 1.17,
-				cacheRead: 0.09999999999999999,
+				input: 0.118,
+				output: 0.9900000000000001,
+				cacheRead: 0.059,
 				cacheWrite: 0,
 			},
 			contextWindow: 196608,
@@ -7808,7 +8115,7 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 196608,
-			maxTokens: 196608,
+			maxTokens: 8192,
 		} satisfies Model<"openai-completions">,
 		"minimax/minimax-m2.7": {
 			id: "minimax/minimax-m2.7",
@@ -7821,11 +8128,11 @@ export const MODELS = {
 			cost: {
 				input: 0.3,
 				output: 1.2,
-				cacheRead: 0.06,
+				cacheRead: 0.059,
 				cacheWrite: 0,
 			},
-			contextWindow: 204800,
-			maxTokens: 131072,
+			contextWindow: 196608,
+			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
 		"mistralai/codestral-2508": {
 			id: "mistralai/codestral-2508",
@@ -8082,23 +8389,6 @@ export const MODELS = {
 			contextWindow: 32768,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
-		"mistralai/mistral-small-24b-instruct-2501": {
-			id: "mistralai/mistral-small-24b-instruct-2501",
-			name: "Mistral: Mistral Small 3",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.049999999999999996,
-				output: 0.08,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 32768,
-			maxTokens: 16384,
-		} satisfies Model<"openai-completions">,
 		"mistralai/mistral-small-2603": {
 			id: "mistralai/mistral-small-2603",
 			name: "Mistral: Mistral Small 4",
@@ -8116,23 +8406,6 @@ 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",
@@ -8244,13 +8517,13 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0.55,
-				output: 2.2,
+				input: 0.5700000000000001,
+				output: 2.3,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 131000,
-			maxTokens: 4096,
+			contextWindow: 131072,
+			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
 		"moonshotai/kimi-k2-0905": {
 			id: "moonshotai/kimi-k2-0905",
@@ -8263,11 +8536,11 @@ export const MODELS = {
 			cost: {
 				input: 0.39999999999999997,
 				output: 2,
-				cacheRead: 0.15,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 131072,
-			maxTokens: 4096,
+			contextWindow: 262144,
+			maxTokens: 262144,
 		} satisfies Model<"openai-completions">,
 		"moonshotai/kimi-k2-thinking": {
 			id: "moonshotai/kimi-k2-thinking",
@@ -8278,12 +8551,12 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.47,
-				output: 2,
-				cacheRead: 0.14100000000000001,
+				input: 0.6,
+				output: 2.5,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 131072,
+			contextWindow: 262144,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
 		"moonshotai/kimi-k2.5": {
@@ -8312,8 +8585,8 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0.27,
-				output: 1,
+				input: 0.135,
+				output: 0.5,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
@@ -8399,7 +8672,7 @@ export const MODELS = {
 			cost: {
 				input: 0.09999999999999999,
 				output: 0.5,
-				cacheRead: 0.04,
+				cacheRead: 0.09999999999999999,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
@@ -8624,7 +8897,7 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 1047576,
-			maxTokens: 32768,
+			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
 		"openai/gpt-4.1-mini": {
 			id: "openai/gpt-4.1-mini",
@@ -8671,7 +8944,7 @@ export const MODELS = {
 			cost: {
 				input: 2.5,
 				output: 10,
-				cacheRead: 1.25,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 128000,
@@ -8892,11 +9165,11 @@ export const MODELS = {
 			cost: {
 				input: 0.049999999999999996,
 				output: 0.39999999999999997,
-				cacheRead: 0.005,
+				cacheRead: 0.01,
 				cacheWrite: 0,
 			},
 			contextWindow: 400000,
-			maxTokens: 128000,
+			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
 		"openai/gpt-5-pro": {
 			id: "openai/gpt-5-pro",
@@ -8926,7 +9199,7 @@ export const MODELS = {
 			cost: {
 				input: 1.25,
 				output: 10,
-				cacheRead: 0.125,
+				cacheRead: 0.13,
 				cacheWrite: 0,
 			},
 			contextWindow: 400000,
@@ -8994,11 +9267,11 @@ export const MODELS = {
 			cost: {
 				input: 0.25,
 				output: 2,
-				cacheRead: 0.024999999999999998,
+				cacheRead: 0.03,
 				cacheWrite: 0,
 			},
 			contextWindow: 400000,
-			maxTokens: 100000,
+			maxTokens: 128000,
 		} satisfies Model<"openai-completions">,
 		"openai/gpt-5.2": {
 			id: "openai/gpt-5.2",
@@ -9032,7 +9305,7 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 128000,
-			maxTokens: 16384,
+			maxTokens: 32000,
 		} satisfies Model<"openai-completions">,
 		"openai/gpt-5.2-codex": {
 			id: "openai/gpt-5.2-codex",
@@ -9170,6 +9443,40 @@ export const MODELS = {
 			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",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.6,
+				output: 2.4,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 128000,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
 		"openai/gpt-oss-120b": {
 			id: "openai/gpt-oss-120b",
 			name: "OpenAI: gpt-oss-120b",
@@ -9214,12 +9521,12 @@ export const MODELS = {
 			input: ["text"],
 			cost: {
 				input: 0.03,
-				output: 0.11,
-				cacheRead: 0.015,
+				output: 0.14,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
-			maxTokens: 131072,
+			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
 		"openai/gpt-oss-20b:free": {
 			id: "openai/gpt-oss-20b:free",
@@ -9236,7 +9543,7 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
-			maxTokens: 131072,
+			maxTokens: 8192,
 		} satisfies Model<"openai-completions">,
 		"openai/gpt-oss-safeguard-20b": {
 			id: "openai/gpt-oss-safeguard-20b",
@@ -9491,7 +9798,7 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 32768,
-			maxTokens: 4096,
+			maxTokens: 32768,
 		} satisfies Model<"openai-completions">,
 		"qwen/qwen-max": {
 			id: "qwen/qwen-max",
@@ -9731,23 +10038,6 @@ 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",
@@ -9825,13 +10115,13 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0.12,
-				output: 0.75,
-				cacheRead: 0.06,
+				input: 0.15,
+				output: 0.7999999999999999,
+				cacheRead: 0.12,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
-			maxTokens: 65536,
+			maxTokens: 262144,
 		} satisfies Model<"openai-completions">,
 		"qwen/qwen3-coder-plus": {
 			id: "qwen/qwen3-coder-plus",
@@ -10154,7 +10444,7 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 256000,
-			maxTokens: 4096,
+			maxTokens: 32768,
 		} satisfies Model<"openai-completions">,
 		"qwen/qwen3.5-flash-02-23": {
 			id: "qwen/qwen3.5-flash-02-23",
@@ -10190,6 +10480,23 @@ export const MODELS = {
 			contextWindow: 1000000,
 			maxTokens: 65536,
 		} satisfies Model<"openai-completions">,
+		"qwen/qwen3.6-plus": {
+			id: "qwen/qwen3.6-plus",
+			name: "Qwen: Qwen3.6 Plus",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.325,
+				output: 1.95,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 1000000,
+			maxTokens: 65536,
+		} satisfies Model<"openai-completions">,
 		"qwen/qwq-32b": {
 			id: "qwen/qwq-32b",
 			name: "Qwen: QwQ 32B",
@@ -10207,6 +10514,23 @@ export const MODELS = {
 			contextWindow: 131072,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
+		"rekaai/reka-edge": {
+			id: "rekaai/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",
@@ -10269,28 +10593,11 @@ export const MODELS = {
 			cost: {
 				input: 0.09999999999999999,
 				output: 0.3,
-				cacheRead: 0.02,
-				cacheWrite: 0,
-			},
-			contextWindow: 256000,
-			maxTokens: 256000,
-		} satisfies Model<"openai-completions">,
-		"stepfun/step-3.5-flash:free": {
-			id: "stepfun/step-3.5-flash:free",
-			name: "StepFun: Step 3.5 Flash (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: 256000,
-			maxTokens: 256000,
+			contextWindow: 262144,
+			maxTokens: 65536,
 		} satisfies Model<"openai-completions">,
 		"thedrummer/rocinante-12b": {
 			id: "thedrummer/rocinante-12b",
@@ -10479,9 +10786,9 @@ export const MODELS = {
 			contextWindow: 2000000,
 			maxTokens: 30000,
 		} satisfies Model<"openai-completions">,
-		"x-ai/grok-4.20-beta": {
-			id: "x-ai/grok-4.20-beta",
-			name: "xAI: Grok 4.20 Beta",
+		"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",
@@ -10743,9 +11050,43 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.96,
-				output: 3.1999999999999997,
-				cacheRead: 0.192,
+				input: 1.2,
+				output: 4,
+				cacheRead: 0.24,
+				cacheWrite: 0,
+			},
+			contextWindow: 202752,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
+		"z-ai/glm-5.1": {
+			id: "z-ai/glm-5.1",
+			name: "Z.ai: GLM 5.1",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.95,
+				output: 3.15,
+				cacheRead: 0.475,
+				cacheWrite: 0,
+			},
+			contextWindow: 202752,
+			maxTokens: 65535,
+		} satisfies Model<"openai-completions">,
+		"z-ai/glm-5v-turbo": {
+			id: "z-ai/glm-5v-turbo",
+			name: "Z.ai: GLM 5V Turbo",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.2,
+				output: 4,
+				cacheRead: 0.24,
 				cacheWrite: 0,
 			},
 			contextWindow: 202752,
@@ -10772,20 +11113,20 @@ export const MODELS = {
 		} satisfies Model<"anthropic-messages">,
 		"alibaba/qwen-3-235b": {
 			id: "alibaba/qwen-3-235b",
-			name: "Qwen3-235B-A22B",
+			name: "Qwen3 235B A22b Instruct 2507",
 			api: "anthropic-messages",
 			provider: "vercel-ai-gateway",
 			baseUrl: "https://ai-gateway.vercel.sh",
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0.071,
-				output: 0.463,
-				cacheRead: 0,
+				input: 0.6,
+				output: 1.2,
+				cacheRead: 0.6,
 				cacheWrite: 0,
 			},
-			contextWindow: 40960,
-			maxTokens: 16384,
+			contextWindow: 131000,
+			maxTokens: 40000,
 		} satisfies Model<"anthropic-messages">,
 		"alibaba/qwen-3-30b": {
 			id: "alibaba/qwen-3-30b",
@@ -10813,13 +11154,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.29,
-				output: 0.59,
-				cacheRead: 0.145,
+				input: 0.16,
+				output: 0.64,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 131072,
-			maxTokens: 40960,
+			contextWindow: 128000,
+			maxTokens: 8192,
 		} satisfies Model<"anthropic-messages">,
 		"alibaba/qwen3-235b-a22b-thinking": {
 			id: "alibaba/qwen3-235b-a22b-thinking",
@@ -10847,13 +11188,13 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0.39999999999999997,
-				output: 1.5999999999999999,
-				cacheRead: 0.022,
+				input: 1.5,
+				output: 7.5,
+				cacheRead: 0.3,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
-			maxTokens: 66536,
+			maxTokens: 65536,
 		} satisfies Model<"anthropic-messages">,
 		"alibaba/qwen3-coder-30b-a3b": {
 			id: "alibaba/qwen3-coder-30b-a3b",
@@ -10966,13 +11307,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 0.22,
-				output: 0.88,
+				input: 0.39999999999999997,
+				output: 4,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 256000,
-			maxTokens: 256000,
+			contextWindow: 131072,
+			maxTokens: 32768,
 		} satisfies Model<"anthropic-messages">,
 		"alibaba/qwen3.5-flash": {
 			id: "alibaba/qwen3.5-flash",
@@ -11008,6 +11349,23 @@ export const MODELS = {
 			contextWindow: 1000000,
 			maxTokens: 64000,
 		} satisfies Model<"anthropic-messages">,
+		"alibaba/qwen3.6-plus": {
+			id: "alibaba/qwen3.6-plus",
+			name: "Qwen 3.6 Plus",
+			api: "anthropic-messages",
+			provider: "vercel-ai-gateway",
+			baseUrl: "https://ai-gateway.vercel.sh",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.5,
+				output: 3,
+				cacheRead: 0.09999999999999999,
+				cacheWrite: 0,
+			},
+			contextWindow: 1000000,
+			maxTokens: 64000,
+		} satisfies Model<"anthropic-messages">,
 		"anthropic/claude-3-haiku": {
 			id: "anthropic/claude-3-haiku",
 			name: "Claude 3 Haiku",
@@ -11031,47 +11389,13 @@ export const MODELS = {
 			api: "anthropic-messages",
 			provider: "vercel-ai-gateway",
 			baseUrl: "https://ai-gateway.vercel.sh",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.7999999999999999,
-				output: 4,
-				cacheRead: 0.08,
-				cacheWrite: 1,
-			},
-			contextWindow: 200000,
-			maxTokens: 8192,
-		} satisfies Model<"anthropic-messages">,
-		"anthropic/claude-3.5-sonnet": {
-			id: "anthropic/claude-3.5-sonnet",
-			name: "Claude 3.5 Sonnet",
-			api: "anthropic-messages",
-			provider: "vercel-ai-gateway",
-			baseUrl: "https://ai-gateway.vercel.sh",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 3,
-				output: 15,
-				cacheRead: 0.3,
-				cacheWrite: 3.75,
-			},
-			contextWindow: 200000,
-			maxTokens: 8192,
-		} satisfies Model<"anthropic-messages">,
-		"anthropic/claude-3.5-sonnet-20240620": {
-			id: "anthropic/claude-3.5-sonnet-20240620",
-			name: "Claude 3.5 Sonnet (2024-06-20)",
-			api: "anthropic-messages",
-			provider: "vercel-ai-gateway",
-			baseUrl: "https://ai-gateway.vercel.sh",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 3,
-				output: 15,
-				cacheRead: 0.3,
-				cacheWrite: 3.75,
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.7999999999999999,
+				output: 4,
+				cacheRead: 0.08,
+				cacheWrite: 1,
 			},
 			contextWindow: 200000,
 			maxTokens: 8192,
@@ -11246,6 +11570,23 @@ export const MODELS = {
 			contextWindow: 131000,
 			maxTokens: 131000,
 		} satisfies Model<"anthropic-messages">,
+		"arcee-ai/trinity-large-thinking": {
+			id: "arcee-ai/trinity-large-thinking",
+			name: "Trinity Large Thinking",
+			api: "anthropic-messages",
+			provider: "vercel-ai-gateway",
+			baseUrl: "https://ai-gateway.vercel.sh",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.25,
+				output: 0.8999999999999999,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262100,
+			maxTokens: 80000,
+		} satisfies Model<"anthropic-messages">,
 		"bytedance/seed-1.6": {
 			id: "bytedance/seed-1.6",
 			name: "Seed 1.6",
@@ -11323,13 +11664,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.5,
-				output: 1.5,
-				cacheRead: 0,
+				input: 0.56,
+				output: 1.68,
+				cacheRead: 0.28,
 				cacheWrite: 0,
 			},
 			contextWindow: 163840,
-			maxTokens: 16384,
+			maxTokens: 8192,
 		} satisfies Model<"anthropic-messages">,
 		"deepseek/deepseek-v3.1-terminus": {
 			id: "deepseek/deepseek-v3.1-terminus",
@@ -11512,7 +11853,7 @@ export const MODELS = {
 			cost: {
 				input: 0.25,
 				output: 1.5,
-				cacheRead: 0,
+				cacheRead: 0.03,
 				cacheWrite: 0,
 			},
 			contextWindow: 1000000,
@@ -11535,6 +11876,40 @@ export const MODELS = {
 			contextWindow: 1000000,
 			maxTokens: 64000,
 		} satisfies Model<"anthropic-messages">,
+		"google/gemma-4-26b-a4b-it": {
+			id: "google/gemma-4-26b-a4b-it",
+			name: "Gemma 4 26B A4B IT",
+			api: "anthropic-messages",
+			provider: "vercel-ai-gateway",
+			baseUrl: "https://ai-gateway.vercel.sh",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.13,
+				output: 0.39999999999999997,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 131072,
+		} satisfies Model<"anthropic-messages">,
+		"google/gemma-4-31b-it": {
+			id: "google/gemma-4-31b-it",
+			name: "Gemma 4 31B IT",
+			api: "anthropic-messages",
+			provider: "vercel-ai-gateway",
+			baseUrl: "https://ai-gateway.vercel.sh",
+			reasoning: false,
+			input: ["text", "image"],
+			cost: {
+				input: 0.14,
+				output: 0.39999999999999997,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 131072,
+		} satisfies Model<"anthropic-messages">,
 		"inception/mercury-2": {
 			id: "inception/mercury-2",
 			name: "Mercury 2",
@@ -11569,39 +11944,39 @@ export const MODELS = {
 			contextWindow: 32000,
 			maxTokens: 16384,
 		} satisfies Model<"anthropic-messages">,
-		"meituan/longcat-flash-chat": {
-			id: "meituan/longcat-flash-chat",
-			name: "LongCat Flash Chat",
+		"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: false,
+			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0,
-				output: 0,
-				cacheRead: 0,
+				input: 0.3,
+				output: 1.2,
+				cacheRead: 0.06,
 				cacheWrite: 0,
 			},
-			contextWindow: 128000,
-			maxTokens: 100000,
+			contextWindow: 256000,
+			maxTokens: 256000,
 		} satisfies Model<"anthropic-messages">,
-		"meituan/longcat-flash-thinking": {
-			id: "meituan/longcat-flash-thinking",
-			name: "LongCat Flash Thinking",
+		"meituan/longcat-flash-chat": {
+			id: "meituan/longcat-flash-chat",
+			name: "LongCat Flash Chat",
 			api: "anthropic-messages",
 			provider: "vercel-ai-gateway",
 			baseUrl: "https://ai-gateway.vercel.sh",
-			reasoning: true,
+			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0.15,
-				output: 1.5,
+				input: 0,
+				output: 0,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 128000,
-			maxTokens: 8192,
+			maxTokens: 100000,
 		} satisfies Model<"anthropic-messages">,
 		"meta/llama-3.1-70b": {
 			id: "meta/llama-3.1-70b",
@@ -11629,13 +12004,13 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0.09999999999999999,
-				output: 0.09999999999999999,
-				cacheRead: 0.09999999999999999,
+				input: 0.22,
+				output: 0.22,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 128000,
-			maxTokens: 16384,
+			maxTokens: 8192,
 		} satisfies Model<"anthropic-messages">,
 		"meta/llama-3.2-11b": {
 			id: "meta/llama-3.2-11b",
@@ -12013,20 +12388,20 @@ export const MODELS = {
 		} satisfies Model<"anthropic-messages">,
 		"moonshotai/kimi-k2": {
 			id: "moonshotai/kimi-k2",
-			name: "Kimi K2",
+			name: "Kimi K2 Instruct",
 			api: "anthropic-messages",
 			provider: "vercel-ai-gateway",
 			baseUrl: "https://ai-gateway.vercel.sh",
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0.6,
-				output: 2.5,
-				cacheRead: 0.15,
+				input: 0.5700000000000001,
+				output: 2.3,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
-			maxTokens: 16384,
+			maxTokens: 131072,
 		} satisfies Model<"anthropic-messages">,
 		"moonshotai/kimi-k2-0905": {
 			id: "moonshotai/kimi-k2-0905",
@@ -12039,11 +12414,11 @@ export const MODELS = {
 			cost: {
 				input: 0.6,
 				output: 2.5,
-				cacheRead: 0.15,
+				cacheRead: 0.3,
 				cacheWrite: 0,
 			},
 			contextWindow: 256000,
-			maxTokens: 16384,
+			maxTokens: 128000,
 		} satisfies Model<"anthropic-messages">,
 		"moonshotai/kimi-k2-thinking": {
 			id: "moonshotai/kimi-k2-thinking",
@@ -12615,12 +12990,12 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.07,
-				output: 0.3,
+				input: 0.049999999999999996,
+				output: 0.19999999999999998,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 128000,
+			contextWindow: 131072,
 			maxTokens: 8192,
 		} satisfies Model<"anthropic-messages">,
 		"openai/gpt-oss-safeguard-20b": {
@@ -12751,8 +13126,8 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text", "image"],
 			cost: {
-				input: 1,
-				output: 1,
+				input: 0,
+				output: 0,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
@@ -12768,8 +13143,8 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text", "image"],
 			cost: {
-				input: 3,
-				output: 15,
+				input: 0,
+				output: 0,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
@@ -12793,23 +13168,6 @@ export const MODELS = {
 			contextWindow: 131072,
 			maxTokens: 131072,
 		} satisfies Model<"anthropic-messages">,
-		"xai/grok-2-vision": {
-			id: "xai/grok-2-vision",
-			name: "Grok 2 Vision",
-			api: "anthropic-messages",
-			provider: "vercel-ai-gateway",
-			baseUrl: "https://ai-gateway.vercel.sh",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 2,
-				output: 10,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 32768,
-			maxTokens: 32768,
-		} satisfies Model<"anthropic-messages">,
 		"xai/grok-3": {
 			id: "xai/grok-3",
 			name: "Grok 3 Beta",
@@ -12963,6 +13321,23 @@ 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",
@@ -12980,6 +13355,23 @@ 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",
@@ -12997,6 +13389,23 @@ 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",
@@ -13040,9 +13449,9 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.09999999999999999,
-				output: 0.3,
-				cacheRead: 0.02,
+				input: 0.09,
+				output: 0.29,
+				cacheRead: 0.045,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
@@ -13176,13 +13585,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.6,
-				output: 2.2,
-				cacheRead: 0,
+				input: 2.25,
+				output: 2.75,
+				cacheRead: 2.25,
 				cacheWrite: 0,
 			},
-			contextWindow: 200000,
-			maxTokens: 120000,
+			contextWindow: 131000,
+			maxTokens: 40000,
 		} satisfies Model<"anthropic-messages">,
 		"zai/glm-4.7-flash": {
 			id: "zai/glm-4.7-flash",
@@ -13252,6 +13661,40 @@ export const MODELS = {
 			contextWindow: 202800,
 			maxTokens: 131100,
 		} satisfies Model<"anthropic-messages">,
+		"zai/glm-5.1": {
+			id: "zai/glm-5.1",
+			name: "GLM 5.1",
+			api: "anthropic-messages",
+			provider: "vercel-ai-gateway",
+			baseUrl: "https://ai-gateway.vercel.sh",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 1.4,
+				output: 4.4,
+				cacheRead: 0.26,
+				cacheWrite: 0,
+			},
+			contextWindow: 202800,
+			maxTokens: 64000,
+		} satisfies Model<"anthropic-messages">,
+		"zai/glm-5v-turbo": {
+			id: "zai/glm-5v-turbo",
+			name: "GLM 5V Turbo",
+			api: "anthropic-messages",
+			provider: "vercel-ai-gateway",
+			baseUrl: "https://ai-gateway.vercel.sh",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.2,
+				output: 4,
+				cacheRead: 0.24,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 128000,
+		} satisfies Model<"anthropic-messages">,
 	},
 	"xai": {
 		"grok-2": {
@@ -13808,6 +14251,24 @@ 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",
@@ -13844,5 +14305,41 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
+		"glm-5.1": {
+			id: "glm-5.1",
+			name: "GLM-5.1",
+			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: 1.4,
+				output: 4.4,
+				cacheRead: 0.26,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
+		"glm-5v-turbo": {
+			id: "glm-5v-turbo",
+			name: "glm-5v-turbo",
+			api: "openai-completions",
+			provider: "zai",
+			baseUrl: "https://api.z.ai/api/coding/paas/v4",
+			compat: {"supportsDeveloperRole":false,"thinkingFormat":"zai"},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 1.2,
+				output: 4,
+				cacheRead: 0.24,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
 	},
 } as const;