@oh-my-pi/pi-ai 11.6.1 → 11.7.1

package/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@oh-my-pi/pi-ai",
-	"version": "11.6.1",
+	"version": "11.7.1",
 	"description": "Unified LLM API with automatic model discovery and provider configuration",
 	"type": "module",
 	"main": "./src/index.ts",
@@ -63,7 +63,7 @@
 		"@connectrpc/connect-node": "^2.1.1",
 		"@google/genai": "^1.39.0",
 		"@mistralai/mistralai": "^1.13.0",
-		"@oh-my-pi/pi-utils": "11.6.1",
+		"@oh-my-pi/pi-utils": "11.7.1",
 		"@sinclair/typebox": "^0.34.48",
 		"@smithy/node-http-handler": "^4.4.9",
 		"ajv": "^8.17.1",

package/src/models.generated.ts

@@ -107,8 +107,8 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 4096,
 		} satisfies Model<"bedrock-converse-stream">,
-		"anthropic.claude-opus-4-6-v1:0": {
-			id: "anthropic.claude-opus-4-6-v1:0",
+		"anthropic.claude-opus-4-6-v1": {
+			id: "anthropic.claude-opus-4-6-v1",
 			name: "Claude Opus 4.6",
 			api: "bedrock-converse-stream",
 			provider: "amazon-bedrock",
@@ -121,7 +121,7 @@ export const MODELS = {
 				cacheRead: 0.5,
 				cacheWrite: 6.25,
 			},
-			contextWindow: 200000,
+			contextWindow: 1000000,
 			maxTokens: 128000,
 		} satisfies Model<"bedrock-converse-stream">,
 		"cohere.command-r-plus-v1:0": {
@@ -209,8 +209,8 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 64000,
 		} satisfies Model<"bedrock-converse-stream">,
-		"eu.anthropic.claude-opus-4-6-v1:0": {
-			id: "eu.anthropic.claude-opus-4-6-v1:0",
+		"eu.anthropic.claude-opus-4-6-v1": {
+			id: "eu.anthropic.claude-opus-4-6-v1",
 			name: "Claude Opus 4.6 (EU)",
 			api: "bedrock-converse-stream",
 			provider: "amazon-bedrock",
@@ -220,10 +220,10 @@ export const MODELS = {
 			cost: {
 				input: 5,
 				output: 25,
-				cacheRead: 1.5,
-				cacheWrite: 18.75,
+				cacheRead: 0.5,
+				cacheWrite: 6.25,
 			},
-			contextWindow: 200000,
+			contextWindow: 1000000,
 			maxTokens: 128000,
 		} satisfies Model<"bedrock-converse-stream">,
 		"eu.anthropic.claude-sonnet-4-20250514-v1:0": {
@@ -311,8 +311,8 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 64000,
 		} satisfies Model<"bedrock-converse-stream">,
-		"global.anthropic.claude-opus-4-6-v1:0": {
-			id: "global.anthropic.claude-opus-4-6-v1:0",
+		"global.anthropic.claude-opus-4-6-v1": {
+			id: "global.anthropic.claude-opus-4-6-v1",
 			name: "Claude Opus 4.6 (Global)",
 			api: "bedrock-converse-stream",
 			provider: "amazon-bedrock",
@@ -325,7 +325,7 @@ export const MODELS = {
 				cacheRead: 0.5,
 				cacheWrite: 6.25,
 			},
-			contextWindow: 200000,
+			contextWindow: 1000000,
 			maxTokens: 128000,
 		} satisfies Model<"bedrock-converse-stream">,
 		"global.anthropic.claude-sonnet-4-20250514-v1:0": {
@@ -900,14 +900,14 @@ export const MODELS = {
 			cost: {
 				input: 5,
 				output: 25,
-				cacheRead: 1.5,
-				cacheWrite: 18.75,
+				cacheRead: 0.5,
+				cacheWrite: 6.25,
 			},
 			contextWindow: 200000,
 			maxTokens: 64000,
 		} satisfies Model<"bedrock-converse-stream">,
-		"us.anthropic.claude-opus-4-6-v1:0": {
-			id: "us.anthropic.claude-opus-4-6-v1:0",
+		"us.anthropic.claude-opus-4-6-v1": {
+			id: "us.anthropic.claude-opus-4-6-v1",
 			name: "Claude Opus 4.6 (US)",
 			api: "bedrock-converse-stream",
 			provider: "amazon-bedrock",
@@ -917,10 +917,10 @@ export const MODELS = {
 			cost: {
 				input: 5,
 				output: 25,
-				cacheRead: 1.5,
-				cacheWrite: 18.75,
+				cacheRead: 0.5,
+				cacheWrite: 6.25,
 			},
-			contextWindow: 200000,
+			contextWindow: 1000000,
 			maxTokens: 128000,
 		} satisfies Model<"bedrock-converse-stream">,
 		"us.anthropic.claude-sonnet-4-20250514-v1:0": {
@@ -1398,23 +1398,6 @@ export const MODELS = {
 				cacheRead: 0.5,
 				cacheWrite: 6.25,
 			},
-			contextWindow: 1000000,
-			maxTokens: 128000,
-		} satisfies Model<"anthropic-messages">,
-		"claude-opus-4-6-20260205": {
-			id: "claude-opus-4-6-20260205",
-			name: "Claude Opus 4.6",
-			api: "anthropic-messages",
-			provider: "anthropic",
-			baseUrl: "https://api.anthropic.com",
-			reasoning: true,
-			input: ["text", "image"],
-			cost: {
-				input: 5,
-				output: 25,
-				cacheRead: 0.5,
-				cacheWrite: 6.25,
-			},
 			contextWindow: 200000,
 			maxTokens: 128000,
 		} satisfies Model<"anthropic-messages">,
@@ -1819,7 +1802,7 @@ export const MODELS = {
 				cacheWrite: 0,
 			},
 			contextWindow: 128000,
-			maxTokens: 16000,
+			maxTokens: 64000,
 		} satisfies Model<"openai-completions">,
 		"claude-sonnet-4": {
 			id: "claude-sonnet-4",
@@ -2480,17 +2463,34 @@ export const MODELS = {
 	"google-antigravity": {
 		"claude-opus-4-5-thinking": {
 			id: "claude-opus-4-5-thinking",
-			name: "Claude Opus 4.5 Thinking (Antigravity)",
+			name: "Claude Opus 4.5 (Thinking) (Antigravity)",
 			api: "google-gemini-cli",
 			provider: "google-antigravity",
 			baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 5,
-				output: 25,
-				cacheRead: 0.5,
-				cacheWrite: 6.25,
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 64000,
+		} satisfies Model<"google-gemini-cli">,
+		"claude-opus-4-6-thinking": {
+			id: "claude-opus-4-6-thinking",
+			name: "Claude Opus 4.6 (Thinking) (Antigravity)",
+			api: "google-gemini-cli",
+			provider: "google-antigravity",
+			baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
 			},
 			contextWindow: 200000,
 			maxTokens: 64000,
@@ -2504,31 +2504,82 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text", "image"],
 			cost: {
-				input: 3,
-				output: 15,
-				cacheRead: 0.3,
-				cacheWrite: 3.75,
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
 			},
 			contextWindow: 200000,
 			maxTokens: 64000,
 		} satisfies Model<"google-gemini-cli">,
 		"claude-sonnet-4-5-thinking": {
 			id: "claude-sonnet-4-5-thinking",
-			name: "Claude Sonnet 4.5 Thinking (Antigravity)",
+			name: "Claude Sonnet 4.5 (Thinking) (Antigravity)",
 			api: "google-gemini-cli",
 			provider: "google-antigravity",
 			baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 3,
-				output: 15,
-				cacheRead: 0.3,
-				cacheWrite: 3.75,
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
 			},
 			contextWindow: 200000,
 			maxTokens: 64000,
 		} satisfies Model<"google-gemini-cli">,
+		"gemini-2.5-flash": {
+			id: "gemini-2.5-flash",
+			name: "Gemini 2.5 Flash (Antigravity)",
+			api: "google-gemini-cli",
+			provider: "google-antigravity",
+			baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65535,
+		} satisfies Model<"google-gemini-cli">,
+		"gemini-2.5-flash-thinking": {
+			id: "gemini-2.5-flash-thinking",
+			name: "Gemini 2.5 Flash (Thinking) (Antigravity)",
+			api: "google-gemini-cli",
+			provider: "google-antigravity",
+			baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65535,
+		} satisfies Model<"google-gemini-cli">,
+		"gemini-2.5-pro": {
+			id: "gemini-2.5-pro",
+			name: "Gemini 2.5 Pro (Antigravity)",
+			api: "google-gemini-cli",
+			provider: "google-antigravity",
+			baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
+			reasoning: true,
+			input: ["text", "image"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 1048576,
+			maxTokens: 65535,
+		} satisfies Model<"google-gemini-cli">,
 		"gemini-3-flash": {
 			id: "gemini-3-flash",
 			name: "Gemini 3 Flash (Antigravity)",
@@ -2538,59 +2589,59 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 0.5,
-				output: 3,
-				cacheRead: 0.5,
+				input: 0,
+				output: 0,
+				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 1048576,
-			maxTokens: 65535,
+			maxTokens: 65536,
 		} satisfies Model<"google-gemini-cli">,
 		"gemini-3-pro-high": {
 			id: "gemini-3-pro-high",
-			name: "Gemini 3 Pro High (Antigravity)",
+			name: "Gemini 3 Pro (High) (Antigravity)",
 			api: "google-gemini-cli",
 			provider: "google-antigravity",
 			baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 2,
-				output: 12,
-				cacheRead: 0.2,
-				cacheWrite: 2.375,
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
 			},
 			contextWindow: 1048576,
 			maxTokens: 65535,
 		} satisfies Model<"google-gemini-cli">,
 		"gemini-3-pro-low": {
 			id: "gemini-3-pro-low",
-			name: "Gemini 3 Pro Low (Antigravity)",
+			name: "Gemini 3 Pro (Low) (Antigravity)",
 			api: "google-gemini-cli",
 			provider: "google-antigravity",
 			baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
 			reasoning: true,
 			input: ["text", "image"],
 			cost: {
-				input: 2,
-				output: 12,
-				cacheRead: 0.2,
-				cacheWrite: 2.375,
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
 			},
 			contextWindow: 1048576,
 			maxTokens: 65535,
 		} satisfies Model<"google-gemini-cli">,
 		"gpt-oss-120b-medium": {
 			id: "gpt-oss-120b-medium",
-			name: "GPT-OSS 120B Medium (Antigravity)",
+			name: "GPT-OSS 120B (Medium) (Antigravity)",
 			api: "google-gemini-cli",
 			provider: "google-antigravity",
 			baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
-			reasoning: false,
+			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.09,
-				output: 0.36,
+				input: 0,
+				output: 0,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
@@ -4909,8 +4960,8 @@ export const MODELS = {
 			input: ["text"],
 			cost: {
 				input: 0.09,
-				output: 0.39999999999999997,
-				cacheRead: 0,
+				output: 0.44999999999999996,
+				cacheRead: 0.09,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
@@ -5408,7 +5459,7 @@ export const MODELS = {
 			cost: {
 				input: 0.3,
 				output: 1.2,
-				cacheRead: 0,
+				cacheRead: 0.15,
 				cacheWrite: 0,
 			},
 			contextWindow: 163840,
@@ -5425,7 +5476,7 @@ export const MODELS = {
 			cost: {
 				input: 0.19,
 				output: 0.87,
-				cacheRead: 0,
+				cacheRead: 0.095,
 				cacheWrite: 0,
 			},
 			contextWindow: 163840,
@@ -5476,7 +5527,7 @@ export const MODELS = {
 			cost: {
 				input: 0.39999999999999997,
 				output: 1.75,
-				cacheRead: 0,
+				cacheRead: 0.19999999999999998,
 				cacheWrite: 0,
 			},
 			contextWindow: 163840,
@@ -5527,7 +5578,7 @@ export const MODELS = {
 			cost: {
 				input: 0.25,
 				output: 0.38,
-				cacheRead: 0,
+				cacheRead: 0.125,
 				cacheWrite: 0,
 			},
 			contextWindow: 163840,
@@ -5748,7 +5799,7 @@ export const MODELS = {
 			cost: {
 				input: 0.04,
 				output: 0.15,
-				cacheRead: 0,
+				cacheRead: 0.02,
 				cacheWrite: 0,
 			},
 			contextWindow: 128000,
@@ -5848,12 +5899,12 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 3.5,
-				output: 3.5,
+				input: 4,
+				output: 4,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
-			contextWindow: 10000,
+			contextWindow: 131000,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
 		"meta-llama/llama-3.1-70b-instruct": {
@@ -6037,7 +6088,7 @@ export const MODELS = {
 			cost: {
 				input: 0.049999999999999996,
 				output: 0.22,
-				cacheRead: 0,
+				cacheRead: 0.024999999999999998,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
@@ -6307,13 +6358,13 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0.03,
-				output: 0.11,
+				input: 0.049999999999999996,
+				output: 0.08,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
 			contextWindow: 32768,
-			maxTokens: 32768,
+			maxTokens: 16384,
 		} satisfies Model<"openai-completions">,
 		"mistralai/mistral-small-3.1-24b-instruct": {
 			id: "mistralai/mistral-small-3.1-24b-instruct",
@@ -6326,7 +6377,7 @@ export const MODELS = {
 			cost: {
 				input: 0.03,
 				output: 0.11,
-				cacheRead: 0,
+				cacheRead: 0.015,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
@@ -6360,7 +6411,7 @@ export const MODELS = {
 			cost: {
 				input: 0.06,
 				output: 0.18,
-				cacheRead: 0,
+				cacheRead: 0.03,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
@@ -6513,7 +6564,7 @@ export const MODELS = {
 			cost: {
 				input: 0.39,
 				output: 1.9,
-				cacheRead: 0,
+				cacheRead: 0.195,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
@@ -6547,7 +6598,7 @@ export const MODELS = {
 			cost: {
 				input: 0.39999999999999997,
 				output: 1.75,
-				cacheRead: 0,
+				cacheRead: 0.19999999999999998,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
@@ -6563,12 +6614,12 @@ export const MODELS = {
 			input: ["text", "image"],
 			cost: {
 				input: 0.44999999999999996,
-				output: 2.5,
-				cacheRead: 0,
+				output: 2.25,
+				cacheRead: 0.075,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
-			maxTokens: 65535,
+			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
 		"nex-agi/deepseek-v3.1-nex-n1": {
 			id: "nex-agi/deepseek-v3.1-nex-n1",
@@ -6598,7 +6649,7 @@ export const MODELS = {
 			cost: {
 				input: 0.02,
 				output: 0.09999999999999999,
-				cacheRead: 0,
+				cacheRead: 0.01,
 				cacheWrite: 0,
 			},
 			contextWindow: 32768,
@@ -6615,7 +6666,7 @@ export const MODELS = {
 			cost: {
 				input: 0.11,
 				output: 0.38,
-				cacheRead: 0,
+				cacheRead: 0.055,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
@@ -7395,13 +7446,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.02,
-				output: 0.09999999999999999,
+				input: 0.03,
+				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",
@@ -7624,6 +7675,24 @@ export const MODELS = {
 			contextWindow: 200000,
 			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
+		"openrouter/pony-alpha": {
+			id: "openrouter/pony-alpha",
+			name: "Pony Alpha",
+			api: "openai-completions",
+			provider: "openrouter",
+			baseUrl: "https://openrouter.ai/api/v1",
+			compat: {"supportsToolChoice":false},
+			reasoning: true,
+			input: ["text"],
+			cost: {
+				input: 0,
+				output: 0,
+				cacheRead: 0,
+				cacheWrite: 0,
+			},
+			contextWindow: 200000,
+			maxTokens: 131000,
+		} satisfies Model<"openai-completions">,
 		"prime-intellect/intellect-3": {
 			id: "prime-intellect/intellect-3",
 			name: "Prime Intellect: INTELLECT-3",
@@ -7788,7 +7857,7 @@ export const MODELS = {
 			cost: {
 				input: 0.049999999999999996,
 				output: 0.22,
-				cacheRead: 0,
+				cacheRead: 0.024999999999999998,
 				cacheWrite: 0,
 			},
 			contextWindow: 40960,
@@ -7839,7 +7908,7 @@ export const MODELS = {
 			cost: {
 				input: 0.11,
 				output: 0.6,
-				cacheRead: 0,
+				cacheRead: 0.055,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
@@ -7856,7 +7925,7 @@ export const MODELS = {
 			cost: {
 				input: 0.06,
 				output: 0.22,
-				cacheRead: 0,
+				cacheRead: 0.03,
 				cacheWrite: 0,
 			},
 			contextWindow: 40960,
@@ -7873,7 +7942,7 @@ export const MODELS = {
 			cost: {
 				input: 0.08,
 				output: 0.33,
-				cacheRead: 0,
+				cacheRead: 0.04,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
@@ -7907,7 +7976,7 @@ export const MODELS = {
 			cost: {
 				input: 0.08,
 				output: 0.24,
-				cacheRead: 0,
+				cacheRead: 0.04,
 				cacheWrite: 0,
 			},
 			contextWindow: 40960,
@@ -7957,12 +8026,12 @@ export const MODELS = {
 			input: ["text"],
 			cost: {
 				input: 0.22,
-				output: 0.95,
-				cacheRead: 0,
+				output: 1,
+				cacheRead: 0.022,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
-			maxTokens: 262144,
+			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
 		"qwen/qwen3-coder-30b-a3b-instruct": {
 			id: "qwen/qwen3-coder-30b-a3b-instruct",
@@ -8009,7 +8078,7 @@ export const MODELS = {
 			cost: {
 				input: 0.07,
 				output: 0.3,
-				cacheRead: 0,
+				cacheRead: 0.035,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
@@ -8038,7 +8107,7 @@ export const MODELS = {
 			api: "openai-completions",
 			provider: "openrouter",
 			baseUrl: "https://openrouter.ai/api/v1",
-			reasoning: true,
+			reasoning: false,
 			input: ["text"],
 			cost: {
 				input: 0.22,
@@ -8384,7 +8453,7 @@ export const MODELS = {
 			cost: {
 				input: 0.25,
 				output: 0.85,
-				cacheRead: 0,
+				cacheRead: 0.125,
 				cacheWrite: 0,
 			},
 			contextWindow: 163840,
@@ -8401,7 +8470,7 @@ export const MODELS = {
 			cost: {
 				input: 0.25,
 				output: 0.85,
-				cacheRead: 0,
+				cacheRead: 0.125,
 				cacheWrite: 0,
 			},
 			contextWindow: 163840,
@@ -8588,7 +8657,7 @@ export const MODELS = {
 			cost: {
 				input: 0.09,
 				output: 0.29,
-				cacheRead: 0,
+				cacheRead: 0.045,
 				cacheWrite: 0,
 			},
 			contextWindow: 262144,
@@ -8622,7 +8691,7 @@ export const MODELS = {
 			cost: {
 				input: 0.35,
 				output: 1.55,
-				cacheRead: 0,
+				cacheRead: 0.175,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
@@ -8637,13 +8706,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.049999999999999996,
-				output: 0.22,
-				cacheRead: 0,
+				input: 0.13,
+				output: 0.85,
+				cacheRead: 0.024999999999999998,
 				cacheWrite: 0,
 			},
 			contextWindow: 131072,
-			maxTokens: 131072,
+			maxTokens: 98304,
 		} satisfies Model<"openai-completions">,
 		"z-ai/glm-4.5-air:free": {
 			id: "z-ai/glm-4.5-air:free",
@@ -8690,7 +8759,7 @@ export const MODELS = {
 			cost: {
 				input: 0.35,
 				output: 1.5,
-				cacheRead: 0,
+				cacheRead: 0.175,
 				cacheWrite: 0,
 			},
 			contextWindow: 202752,
@@ -8741,7 +8810,7 @@ export const MODELS = {
 			cost: {
 				input: 0.39999999999999997,
 				output: 1.5,
-				cacheRead: 0,
+				cacheRead: 0.19999999999999998,
 				cacheWrite: 0,
 			},
 			contextWindow: 202752,
@@ -8756,13 +8825,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.07,
+				input: 0.06,
 				output: 0.39999999999999997,
-				cacheRead: 0.01,
+				cacheRead: 0.0100000002,
 				cacheWrite: 0,
 			},
-			contextWindow: 200000,
-			maxTokens: 131072,
+			contextWindow: 202752,
+			maxTokens: 4096,
 		} satisfies Model<"openai-completions">,
 	},
 	"vercel-ai-gateway": {
@@ -8860,8 +8929,8 @@ export const MODELS = {
 			reasoning: false,
 			input: ["text"],
 			cost: {
-				input: 0.38,
-				output: 1.53,
+				input: 0.39999999999999997,
+				output: 1.5999999999999999,
 				cacheRead: 0,
 				cacheWrite: 0,
 			},
@@ -9625,13 +9694,13 @@ export const MODELS = {
 			reasoning: true,
 			input: ["text"],
 			cost: {
-				input: 0.28,
+				input: 0.3,
 				output: 1.2,
-				cacheRead: 0.14,
+				cacheRead: 0.15,
 				cacheWrite: 0,
 			},
-			contextWindow: 196608,
-			maxTokens: 196608,
+			contextWindow: 204800,
+			maxTokens: 131072,
 		} satisfies Model<"anthropic-messages">,
 		"minimax/minimax-m2.1-lightning": {
 			id: "minimax/minimax-m2.1-lightning",