fix: 同步 PI_CODING_AGENT_DIR 并更新模型列表

- build.sh 导出 PI_CODING_AGENT_DIR 以对齐 pi-mcp-adapter 配置路径 - 更新 models.generated.ts - 移除 bmi-calculator.html 示例文件
2026-06-26 13:21:14 +08:00
parent 539599dbb8
commit a7fb0a4369
3 changed files with 507 additions and 528 deletions
--- a/packages/ai/src/models.generated.ts
+++ b/packages/ai/src/models.generated.ts
@@ -5155,6 +5155,24 @@ export const MODELS = {
 		} satisfies Model<"openai-completions">,
 	},
 	"huggingface": {
+		"MiniMaxAI/MiniMax-M2": {
+			id: "MiniMaxAI/MiniMax-M2",
+			name: "MiniMax-M2",
+			api: "openai-completions",
+			provider: "huggingface",
+			baseUrl: "https://router.huggingface.co/v1",
+			compat: {"supportsDeveloperRole":false},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.3,
+				output: 1.2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 204800,
+			maxTokens: 128000,
+		} satisfies Model<"openai-completions">,
 		"MiniMaxAI/MiniMax-M2.1": {
 			id: "MiniMaxAI/MiniMax-M2.1",
 			name: "MiniMax-M2.1",
@@ -5209,6 +5227,42 @@ export const MODELS = {
 			contextWindow: 204800,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
+		"MiniMaxAI/MiniMax-M3": {
+			id: "MiniMaxAI/MiniMax-M3",
+			name: "MiniMax-M3",
+			api: "openai-completions",
+			provider: "huggingface",
+			baseUrl: "https://router.huggingface.co/v1",
+			compat: {"supportsDeveloperRole":false},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.3,
+				output: 1.2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 524288,
+			maxTokens: 128000,
+		} satisfies Model<"openai-completions">,
+		"Qwen/Qwen3-235B-A22B": {
+			id: "Qwen/Qwen3-235B-A22B",
+			name: "Qwen3 235B-A22B",
+			api: "openai-completions",
+			provider: "huggingface",
+			baseUrl: "https://router.huggingface.co/v1",
+			compat: {"supportsDeveloperRole":false},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.2,
+				output: 0.8,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 40960,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
 		"Qwen/Qwen3-235B-A22B-Thinking-2507": {
 			id: "Qwen/Qwen3-235B-A22B-Thinking-2507",
 			name: "Qwen3-235B-A22B-Thinking-2507",
@@ -5227,6 +5281,42 @@ export const MODELS = {
 			contextWindow: 262144,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
+		"Qwen/Qwen3-32B": {
+			id: "Qwen/Qwen3-32B",
+			name: "Qwen3 32B",
+			api: "openai-completions",
+			provider: "huggingface",
+			baseUrl: "https://router.huggingface.co/v1",
+			compat: {"supportsDeveloperRole":false},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.29,
+				output: 0.59,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"Qwen/Qwen3-Coder-30B-A3B-Instruct": {
+			id: "Qwen/Qwen3-Coder-30B-A3B-Instruct",
+			name: "Qwen3-Coder 30B-A3B Instruct",
+			api: "openai-completions",
+			provider: "huggingface",
+			baseUrl: "https://router.huggingface.co/v1",
+			compat: {"supportsDeveloperRole":false},
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.07,
+				output: 0.26,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 65536,
+		} satisfies Model<"openai-completions">,
 		"Qwen/Qwen3-Coder-480B-A35B-Instruct": {
 			id: "Qwen/Qwen3-Coder-480B-A35B-Instruct",
 			name: "Qwen3-Coder-480B-A35B-Instruct",
@@ -5299,6 +5389,60 @@ export const MODELS = {
 			contextWindow: 262144,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
+		"Qwen/Qwen3.5-122B-A10B": {
+			id: "Qwen/Qwen3.5-122B-A10B",
+			name: "Qwen3.5 122B-A10B",
+			api: "openai-completions",
+			provider: "huggingface",
+			baseUrl: "https://router.huggingface.co/v1",
+			compat: {"supportsDeveloperRole":false},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.4,
+				output: 3.2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 65536,
+		} satisfies Model<"openai-completions">,
+		"Qwen/Qwen3.5-27B": {
+			id: "Qwen/Qwen3.5-27B",
+			name: "Qwen3.5 27B",
+			api: "openai-completions",
+			provider: "huggingface",
+			baseUrl: "https://router.huggingface.co/v1",
+			compat: {"supportsDeveloperRole":false},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.3,
+				output: 2.4,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 65536,
+		} satisfies Model<"openai-completions">,
+		"Qwen/Qwen3.5-35B-A3B": {
+			id: "Qwen/Qwen3.5-35B-A3B",
+			name: "Qwen3.5 35B-A3B",
+			api: "openai-completions",
+			provider: "huggingface",
+			baseUrl: "https://router.huggingface.co/v1",
+			compat: {"supportsDeveloperRole":false},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.25,
+				output: 2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 65536,
+		} satisfies Model<"openai-completions">,
 		"Qwen/Qwen3.5-397B-A17B": {
 			id: "Qwen/Qwen3.5-397B-A17B",
 			name: "Qwen3.5-397B-A17B",
@@ -5317,6 +5461,42 @@ export const MODELS = {
 			contextWindow: 262144,
 			maxTokens: 32768,
 		} satisfies Model<"openai-completions">,
+		"Qwen/Qwen3.5-9B": {
+			id: "Qwen/Qwen3.5-9B",
+			name: "Qwen3.5 9B",
+			api: "openai-completions",
+			provider: "huggingface",
+			baseUrl: "https://router.huggingface.co/v1",
+			compat: {"supportsDeveloperRole":false},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.17,
+				output: 0.25,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 65536,
+		} satisfies Model<"openai-completions">,
+		"Qwen/Qwen3.6-35B-A3B": {
+			id: "Qwen/Qwen3.6-35B-A3B",
+			name: "Qwen3.6 35B-A3B",
+			api: "openai-completions",
+			provider: "huggingface",
+			baseUrl: "https://router.huggingface.co/v1",
+			compat: {"supportsDeveloperRole":false},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.15,
+				output: 0.95,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 65536,
+		} satisfies Model<"openai-completions">,
 		"XiaomiMiMo/MiMo-V2-Flash": {
 			id: "XiaomiMiMo/MiMo-V2-Flash",
 			name: "MiMo-V2-Flash",
@@ -5335,6 +5515,24 @@ export const MODELS = {
 			contextWindow: 262144,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
+		"deepseek-ai/DeepSeek-R1": {
+			id: "deepseek-ai/DeepSeek-R1",
+			name: "DeepSeek-R1",
+			api: "openai-completions",
+			provider: "huggingface",
+			baseUrl: "https://router.huggingface.co/v1",
+			compat: {"supportsDeveloperRole":false},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.7,
+				output: 2.5,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 64000,
+			maxTokens: 32768,
+		} satisfies Model<"openai-completions">,
 		"deepseek-ai/DeepSeek-R1-0528": {
 			id: "deepseek-ai/DeepSeek-R1-0528",
 			name: "DeepSeek-R1-0528",
@@ -5371,6 +5569,24 @@ export const MODELS = {
 			contextWindow: 163840,
 			maxTokens: 65536,
 		} satisfies Model<"openai-completions">,
+		"deepseek-ai/DeepSeek-V4-Flash": {
+			id: "deepseek-ai/DeepSeek-V4-Flash",
+			name: "DeepSeek V4 Flash",
+			api: "openai-completions",
+			provider: "huggingface",
+			baseUrl: "https://router.huggingface.co/v1",
+			compat: {"supportsDeveloperRole":false},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.14,
+				output: 0.28,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 384000,
+		} satisfies Model<"openai-completions">,
 		"deepseek-ai/DeepSeek-V4-Pro": {
 			id: "deepseek-ai/DeepSeek-V4-Pro",
 			name: "DeepSeek V4 Pro",
@@ -5389,6 +5605,60 @@ export const MODELS = {
 			contextWindow: 1048576,
 			maxTokens: 393216,
 		} satisfies Model<"openai-completions">,
+		"google/gemma-4-26B-A4B-it": {
+			id: "google/gemma-4-26B-A4B-it",
+			name: "Gemma 4 26B A4B IT",
+			api: "openai-completions",
+			provider: "huggingface",
+			baseUrl: "https://router.huggingface.co/v1",
+			compat: {"supportsDeveloperRole":false},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.13,
+				output: 0.4,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 32768,
+		} satisfies Model<"openai-completions">,
+		"google/gemma-4-31B-it": {
+			id: "google/gemma-4-31B-it",
+			name: "Gemma 4 31B IT",
+			api: "openai-completions",
+			provider: "huggingface",
+			baseUrl: "https://router.huggingface.co/v1",
+			compat: {"supportsDeveloperRole":false},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.14,
+				output: 0.4,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 32768,
+		} satisfies Model<"openai-completions">,
+		"meta-llama/Llama-3.3-70B-Instruct": {
+			id: "meta-llama/Llama-3.3-70B-Instruct",
+			name: "Llama-3.3-70B-Instruct",
+			api: "openai-completions",
+			provider: "huggingface",
+			baseUrl: "https://router.huggingface.co/v1",
+			compat: {"supportsDeveloperRole":false},
+			reasoning: false,
+			input: ["text"],
+			cost: {
+				input: 0.59,
+				output: 0.79,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 4096,
+		} satisfies Model<"openai-completions">,
 		"moonshotai/Kimi-K2-Instruct": {
 			id: "moonshotai/Kimi-K2-Instruct",
 			name: "Kimi-K2-Instruct",
@@ -5479,6 +5749,114 @@ export const MODELS = {
 			contextWindow: 262144,
 			maxTokens: 262144,
 		} satisfies Model<"openai-completions">,
+		"moonshotai/Kimi-K2.7-Code": {
+			id: "moonshotai/Kimi-K2.7-Code",
+			name: "Kimi K2.7 Code",
+			api: "openai-completions",
+			provider: "huggingface",
+			baseUrl: "https://router.huggingface.co/v1",
+			compat: {"supportsDeveloperRole":false},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.95,
+				output: 4,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 262144,
+		} satisfies Model<"openai-completions">,
+		"stepfun-ai/Step-3.5-Flash": {
+			id: "stepfun-ai/Step-3.5-Flash",
+			name: "Step 3.5 Flash",
+			api: "openai-completions",
+			provider: "huggingface",
+			baseUrl: "https://router.huggingface.co/v1",
+			compat: {"supportsDeveloperRole":false},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.1,
+				output: 0.3,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 256000,
+		} satisfies Model<"openai-completions">,
+		"zai-org/GLM-4.5": {
+			id: "zai-org/GLM-4.5",
+			name: "GLM-4.5",
+			api: "openai-completions",
+			provider: "huggingface",
+			baseUrl: "https://router.huggingface.co/v1",
+			compat: {"supportsDeveloperRole":false},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.6,
+				output: 2.2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 98304,
+		} satisfies Model<"openai-completions">,
+		"zai-org/GLM-4.5-Air": {
+			id: "zai-org/GLM-4.5-Air",
+			name: "GLM-4.5-Air",
+			api: "openai-completions",
+			provider: "huggingface",
+			baseUrl: "https://router.huggingface.co/v1",
+			compat: {"supportsDeveloperRole":false},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.13,
+				output: 0.85,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 131072,
+			maxTokens: 98304,
+		} satisfies Model<"openai-completions">,
+		"zai-org/GLM-4.5V": {
+			id: "zai-org/GLM-4.5V",
+			name: "GLM-4.5V",
+			api: "openai-completions",
+			provider: "huggingface",
+			baseUrl: "https://router.huggingface.co/v1",
+			compat: {"supportsDeveloperRole":false},
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0.6,
+				output: 1.8,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 65536,
+			maxTokens: 16384,
+		} satisfies Model<"openai-completions">,
+		"zai-org/GLM-4.6": {
+			id: "zai-org/GLM-4.6",
+			name: "GLM-4.6",
+			api: "openai-completions",
+			provider: "huggingface",
+			baseUrl: "https://router.huggingface.co/v1",
+			compat: {"supportsDeveloperRole":false},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0.55,
+				output: 2.2,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 204800,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
 		"zai-org/GLM-4.7": {
 			id: "zai-org/GLM-4.7",
 			name: "GLM-4.7",
@@ -5551,6 +5929,24 @@ export const MODELS = {
 			contextWindow: 202752,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
+		"zai-org/GLM-5.2": {
+			id: "zai-org/GLM-5.2",
+			name: "GLM-5.2",
+			api: "openai-completions",
+			provider: "huggingface",
+			baseUrl: "https://router.huggingface.co/v1",
+			compat: {"supportsDeveloperRole":false},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 1.4,
+				output: 4.4,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 262144,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
 	},
 	"kimi-coding": {
 		"k2p7": {
@@ -8061,6 +8457,24 @@ export const MODELS = {
 			contextWindow: 204800,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
+		"glm-5.2": {
+			id: "glm-5.2",
+			name: "GLM-5.2",
+			api: "openai-completions",
+			provider: "opencode",
+			baseUrl: "https://opencode.ai/zen/v1",
+			compat: {"maxTokensField":"max_tokens"},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 1.4,
+				output: 4.4,
+				cacheRead: 0.26,
+				cacheWrite: 0,
+			},
+			contextWindow: 1000000,
+			maxTokens: 131072,
+		} satisfies Model<"openai-completions">,
 		"gpt-5": {
 			id: "gpt-5",
 			name: "GPT-5",
@@ -8885,23 +9299,6 @@ export const MODELS = {
 			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",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text", "image"],
-			cost: {
-				input: 0.8,
-				output: 4,
-				cacheRead: 0.08,
-				cacheWrite: 1,
-			},
-			contextWindow: 200000,
-			maxTokens: 8192,
-		} satisfies Model<"openai-completions">,
 		"anthropic/claude-fable-5": {
 			id: "anthropic/claude-fable-5",
 			name: "Anthropic: Claude Fable 5",
@@ -9507,23 +9904,6 @@ export const MODELS = {
 			contextWindow: 1048576,
 			maxTokens: 384000,
 		} satisfies Model<"openai-completions">,
-		"essentialai/rnj-1-instruct": {
-			id: "essentialai/rnj-1-instruct",
-			name: "EssentialAI: Rnj 1 Instruct",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.15,
-				output: 0.15,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 32768,
-			maxTokens: 4096,
-		} satisfies Model<"openai-completions">,
 		"google/gemini-2.5-flash": {
 			id: "google/gemini-2.5-flash",
 			name: "Google: Gemini 2.5 Flash",
@@ -9657,7 +10037,7 @@ export const MODELS = {
 				cacheRead: 0.2,
 				cacheWrite: 0.375,
 			},
-			contextWindow: 131072,
+			contextWindow: 65536,
 			maxTokens: 32768,
 		} satisfies Model<"openai-completions">,
 		"google/gemini-3.1-flash-lite": {
@@ -9845,7 +10225,7 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
-			maxTokens: 32768,
+			maxTokens: 8192,
 		} satisfies Model<"openai-completions">,
 		"ibm-granite/granite-4.1-8b": {
 			id: "ibm-granite/granite-4.1-8b",
@@ -9947,8 +10327,8 @@ export const MODELS = {
 				cacheRead: 0.06,
 				cacheWrite: 0,
 			},
-			contextWindow: 262144,
-			maxTokens: 144000,
+			contextWindow: 256000,
+			maxTokens: 80000,
 		} satisfies Model<"openai-completions">,
 		"liquid/lfm-2.5-1.2b-thinking:free": {
 			id: "liquid/lfm-2.5-1.2b-thinking:free",
@@ -10146,13 +10526,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.25,
-				output: 1,
-				cacheRead: 0.05,
+				input: 0.24,
+				output: 0.96,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 204800,
-			maxTokens: 131072,
+			maxTokens: 196608,
 		} satisfies Model<"openai-completions">,
 		"minimax/minimax-m3": {
 			id: "minimax/minimax-m3",
@@ -10169,7 +10549,7 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 1048576,
-			maxTokens: 4096,
+			maxTokens: 512000,
 		} satisfies Model<"openai-completions">,
 		"mistralai/codestral-2508": {
 			id: "mistralai/codestral-2508",
@@ -10505,7 +10885,7 @@ export const MODELS = {
 			cost: {
 				input: 0.6,
 				output: 2.5,
-				cacheRead: 0.6,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
@@ -10539,12 +10919,12 @@ export const MODELS = {
 			input: ["text", "image"],
 			cost: {
 				input: 0.66,
-				output: 3.5,
-				cacheRead: 0.33,
+				output: 3.41,
+				cacheRead: 0.144,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
-			maxTokens: 262142,
+			maxTokens: 262144,
 		} satisfies Model<"openai-completions">,
 		"moonshotai/kimi-k2.7-code": {
 			id: "moonshotai/kimi-k2.7-code",
@@ -10555,30 +10935,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 0.612,
-				output: 3.069,
-				cacheRead: 0.1296,
+				input: 0.74,
+				output: 3.5,
+				cacheRead: 0.15,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
-			maxTokens: 262144,
-		} satisfies Model<"openai-completions">,
-		"nex-agi/nex-n2-pro:free": {
-			id: "nex-agi/nex-n2-pro:free",
-			name: "Nex AGI: Nex-N2-Pro (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: 262144,
+			maxTokens: 16384,
 		} satisfies Model<"openai-completions">,
 		"nvidia/llama-3.3-nemotron-super-49b-v1.5": {
 			id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
@@ -10884,7 +11247,7 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 1047576,
-			maxTokens: 4096,
+			maxTokens: 32768,
 		} satisfies Model<"openai-completions">,
 		"openai/gpt-4.1-nano": {
 			id: "openai/gpt-4.1-nano",
@@ -10914,7 +11277,7 @@ export const MODELS = {
 			cost: {
 				input: 2.5,
 				output: 10,
-				cacheRead: 1.25,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 128000,
@@ -11050,11 +11413,11 @@ export const MODELS = {
 			cost: {
 				input: 0.25,
 				output: 2,
-				cacheRead: 0.03,
+				cacheRead: 0.025,
 				cacheWrite: 0,
 			},
 			contextWindow: 400000,
-			maxTokens: 4096,
+			maxTokens: 128000,
 		} satisfies Model<"openai-completions">,
 		"openai/gpt-5-nano": {
 			id: "openai/gpt-5-nano",
@@ -11118,11 +11481,11 @@ export const MODELS = {
 			cost: {
 				input: 1.25,
 				output: 10,
-				cacheRead: 0.125,
+				cacheRead: 0.13,
 				cacheWrite: 0,
 			},
 			contextWindow: 128000,
-			maxTokens: 16384,
+			maxTokens: 32000,
 		} satisfies Model<"openai-completions">,
 		"openai/gpt-5.1-codex": {
 			id: "openai/gpt-5.1-codex",
@@ -11209,7 +11572,7 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 128000,
-			maxTokens: 32000,
+			maxTokens: 16384,
 		} satisfies Model<"openai-completions">,
 		"openai/gpt-5.2-codex": {
 			id: "openai/gpt-5.2-codex",
@@ -11816,23 +12179,6 @@ export const MODELS = {
 			contextWindow: 262144,
 			maxTokens: 32768,
 		} satisfies Model<"openai-completions">,
-		"prime-intellect/intellect-3": {
-			id: "prime-intellect/intellect-3",
-			name: "Prime Intellect: INTELLECT-3",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
-			input: ["text"],
-			cost: {
-				input: 0.2,
-				output: 1.1,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 131072,
-			maxTokens: 131072,
-		} satisfies Model<"openai-completions">,
 		"qwen/qwen-2.5-72b-instruct": {
 			id: "qwen/qwen-2.5-72b-instruct",
 			name: "Qwen2.5 72B Instruct",
@@ -12422,11 +12768,11 @@ export const MODELS = {
 			cost: {
 				input: 0.14,
 				output: 1,
-				cacheRead: 0.05,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
-			maxTokens: 81920,
+			maxTokens: 262144,
 		} satisfies Model<"openai-completions">,
 		"qwen/qwen3.5-397b-a17b": {
 			id: "qwen/qwen3.5-397b-a17b",
@@ -12459,8 +12805,8 @@ export const MODELS = {
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 256000,
-			maxTokens: 32768,
+			contextWindow: 262144,
+			maxTokens: 262144,
 		} satisfies Model<"openai-completions">,
 		"qwen/qwen3.5-flash-02-23": {
 			id: "qwen/qwen3.5-flash-02-23",
@@ -12734,23 +13080,6 @@ export const MODELS = {
 			contextWindow: 262144,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
-		"thedrummer/rocinante-12b": {
-			id: "thedrummer/rocinante-12b",
-			name: "TheDrummer: Rocinante 12B",
-			api: "openai-completions",
-			provider: "openrouter",
-			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: false,
-			input: ["text"],
-			cost: {
-				input: 0.17,
-				output: 0.43,
-				cacheRead: 0,
-				cacheWrite: 0,
-			},
-			contextWindow: 32768,
-			maxTokens: 32768,
-		} satisfies Model<"openai-completions">,
 		"thedrummer/unslopnemo-12b": {
 			id: "thedrummer/unslopnemo-12b",
 			name: "TheDrummer: UnslopNemo 12B",
@@ -12845,13 +13174,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 0.14,
+				input: 0.105,
 				output: 0.28,
-				cacheRead: 0.0028,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 1048576,
-			maxTokens: 131072,
+			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
 		"xiaomi/mimo-v2.5-pro": {
 			id: "xiaomi/mimo-v2.5-pro",
@@ -13034,11 +13363,11 @@ export const MODELS = {
 			cost: {
 				input: 0.98,
 				output: 3.08,
-				cacheRead: 0.182,
+				cacheRead: 0.49,
 				cacheWrite: 0,
 			},
 			contextWindow: 202752,
-			maxTokens: 4096,
+			maxTokens: 65535,
 		} satisfies Model<"openai-completions">,
 		"z-ai/glm-5.2": {
 			id: "z-ai/glm-5.2",
@@ -13050,12 +13379,29 @@ export const MODELS = {
 			thinkingLevelMap: {"xhigh":"xhigh"},
 			input: ["text"],
 			cost: {
-				input: 1.2,
-				output: 4.1,
-				cacheRead: 0.2,
+				input: 0.95,
+				output: 3,
+				cacheRead: 0.18,
 				cacheWrite: 0,
 			},
 			contextWindow: 1048576,
+			maxTokens: 32768,
+		} 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,
 			maxTokens: 131072,
 		} satisfies Model<"openai-completions">,
 		"~anthropic/claude-fable-latest": {
@@ -13170,12 +13516,12 @@ export const MODELS = {
 			input: ["text", "image"],
 			cost: {
 				input: 0.66,
-				output: 3.5,
-				cacheRead: 0.33,
+				output: 3.41,
+				cacheRead: 0.144,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
-			maxTokens: 262142,
+			maxTokens: 262144,
 		} satisfies Model<"openai-completions">,
 		"~openai/gpt-latest": {
 			id: "~openai/gpt-latest",
@@ -15936,6 +16282,23 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 8000,
 		} satisfies Model<"anthropic-messages">,
+		"sakana/fugu-ultra": {
+			id: "sakana/fugu-ultra",
+			name: "Fugu Ultra",
+			api: "anthropic-messages",
+			provider: "vercel-ai-gateway",
+			baseUrl: "https://ai-gateway.vercel.sh",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 5,
+				output: 30,
+				cacheRead: 0.5,
+				cacheWrite: 0,
+			},
+			contextWindow: 1000000,
+			maxTokens: 1000000,
+		} satisfies Model<"anthropic-messages">,
 		"stepfun/step-3.5-flash": {
 			id: "stepfun/step-3.5-flash",
 			name: "StepFun 3.5 Flash",
@@ -16429,6 +16792,23 @@ export const MODELS = {
 			contextWindow: 1000000,
 			maxTokens: 128000,
 		} satisfies Model<"anthropic-messages">,
+		"zai/glm-5.2-fast": {
+			id: "zai/glm-5.2-fast",
+			name: "GLM 5.2 Fast",
+			api: "anthropic-messages",
+			provider: "vercel-ai-gateway",
+			baseUrl: "https://ai-gateway.vercel.sh",
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 3,
+				output: 10.25,
+				cacheRead: 0.5,
+				cacheWrite: 0,
+			},
+			contextWindow: 1000000,
+			maxTokens: 128000,
+		} satisfies Model<"anthropic-messages">,
 		"zai/glm-5v-turbo": {
 			id: "zai/glm-5v-turbo",
 			name: "GLM 5V Turbo",