@mariozechner/pi-ai 0.58.4 → 0.60.0

package/dist/models.generated.js

@@ -254,7 +254,7 @@ export const MODELS = {
                 cacheRead: 0.5,
                 cacheWrite: 6.25,
             },
-            contextWindow: 1000000,
+            contextWindow: 200000,
             maxTokens: 128000,
         },
         "anthropic.claude-sonnet-4-20250514-v1:0": {
@@ -305,7 +305,7 @@ export const MODELS = {
                 cacheRead: 0.3,
                 cacheWrite: 3.75,
             },
-            contextWindow: 1000000,
+            contextWindow: 200000,
             maxTokens: 64000,
         },
         "deepseek.r1-v1:0": {
@@ -407,7 +407,7 @@ export const MODELS = {
                 cacheRead: 0.5,
                 cacheWrite: 6.25,
             },
-            contextWindow: 1000000,
+            contextWindow: 200000,
             maxTokens: 128000,
         },
         "eu.anthropic.claude-sonnet-4-20250514-v1:0": {
@@ -458,7 +458,7 @@ export const MODELS = {
                 cacheRead: 0.3,
                 cacheWrite: 3.75,
             },
-            contextWindow: 1000000,
+            contextWindow: 200000,
             maxTokens: 64000,
         },
         "global.anthropic.claude-haiku-4-5-20251001-v1:0": {
@@ -509,7 +509,7 @@ export const MODELS = {
                 cacheRead: 0.5,
                 cacheWrite: 6.25,
             },
-            contextWindow: 1000000,
+            contextWindow: 200000,
             maxTokens: 128000,
         },
         "global.anthropic.claude-sonnet-4-20250514-v1:0": {
@@ -560,7 +560,7 @@ export const MODELS = {
                 cacheRead: 0.3,
                 cacheWrite: 3.75,
             },
-            contextWindow: 1000000,
+            contextWindow: 200000,
             maxTokens: 64000,
         },
         "google.gemma-3-27b-it": {
@@ -1291,7 +1291,7 @@ export const MODELS = {
                 cacheRead: 0.5,
                 cacheWrite: 6.25,
             },
-            contextWindow: 1000000,
+            contextWindow: 200000,
             maxTokens: 128000,
         },
         "us.anthropic.claude-sonnet-4-20250514-v1:0": {
@@ -1342,7 +1342,7 @@ export const MODELS = {
                 cacheRead: 0.3,
                 cacheWrite: 3.75,
             },
-            contextWindow: 1000000,
+            contextWindow: 200000,
             maxTokens: 64000,
         },
         "writer.palmyra-x4-v1:0": {
@@ -2301,6 +2301,40 @@ export const MODELS = {
             contextWindow: 272000,
             maxTokens: 128000,
         },
+        "gpt-5.4-mini": {
+            id: "gpt-5.4-mini",
+            name: "GPT-5.4 mini",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.75,
+                output: 4.5,
+                cacheRead: 0.075,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "gpt-5.4-nano": {
+            id: "gpt-5.4-nano",
+            name: "GPT-5.4 nano",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.2,
+                output: 1.25,
+                cacheRead: 0.02,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
         "gpt-5.4-pro": {
             id: "gpt-5.4-pro",
             name: "GPT-5.4 Pro",
@@ -2577,7 +2611,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 1000000,
             maxTokens: 64000,
         },
         "claude-sonnet-4": {
@@ -2631,7 +2665,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 1000000,
             maxTokens: 32000,
         },
         "gemini-2.5-pro": {
@@ -2928,6 +2962,42 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
+        "gpt-5.4-mini": {
+            id: "gpt-5.4-mini",
+            name: "GPT-5.4 mini",
+            api: "openai-responses",
+            provider: "github-copilot",
+            baseUrl: "https://api.individual.githubcopilot.com",
+            headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "gpt-5.4-nano": {
+            id: "gpt-5.4-nano",
+            name: "GPT-5.4 nano",
+            api: "openai-responses",
+            provider: "github-copilot",
+            baseUrl: "https://api.individual.githubcopilot.com",
+            headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
         "grok-code-fast-1": {
             id: "grok-code-fast-1",
             name: "Grok Code Fast 1",
@@ -5503,6 +5573,40 @@ export const MODELS = {
             contextWindow: 272000,
             maxTokens: 128000,
         },
+        "gpt-5.4-mini": {
+            id: "gpt-5.4-mini",
+            name: "GPT-5.4 mini",
+            api: "openai-responses",
+            provider: "openai",
+            baseUrl: "https://api.openai.com/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.75,
+                output: 4.5,
+                cacheRead: 0.075,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "gpt-5.4-nano": {
+            id: "gpt-5.4-nano",
+            name: "GPT-5.4 nano",
+            api: "openai-responses",
+            provider: "openai",
+            baseUrl: "https://api.openai.com/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.2,
+                output: 1.25,
+                cacheRead: 0.02,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
         "gpt-5.4-pro": {
             id: "gpt-5.4-pro",
             name: "GPT-5.4 Pro",
@@ -5966,23 +6070,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "gemini-3-pro": {
-            id: "gemini-3-pro",
-            name: "Gemini 3 Pro",
-            api: "google-generative-ai",
-            provider: "opencode",
-            baseUrl: "https://opencode.ai/zen/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 12,
-                cacheRead: 0.2,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
         "gemini-3.1-pro": {
             id: "gemini-3.1-pro",
             name: "Gemini 3.1 Pro Preview",
@@ -6000,40 +6087,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "glm-4.6": {
-            id: "glm-4.6",
-            name: "GLM-4.6",
-            api: "openai-completions",
-            provider: "opencode",
-            baseUrl: "https://opencode.ai/zen/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.6,
-                output: 2.2,
-                cacheRead: 0.1,
-                cacheWrite: 0,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
-        "glm-4.7": {
-            id: "glm-4.7",
-            name: "GLM-4.7",
-            api: "openai-completions",
-            provider: "opencode",
-            baseUrl: "https://opencode.ai/zen/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.6,
-                output: 2.2,
-                cacheRead: 0.1,
-                cacheWrite: 0,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
         "glm-5": {
             id: "glm-5",
             name: "GLM-5",
@@ -6289,23 +6342,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
-        "minimax-m2.1": {
-            id: "minimax-m2.1",
-            name: "MiniMax M2.1",
-            api: "openai-completions",
-            provider: "opencode",
-            baseUrl: "https://opencode.ai/zen/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 1.2,
-                cacheRead: 0.1,
-                cacheWrite: 0,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
         "minimax-m2.5": {
             id: "minimax-m2.5",
             name: "MiniMax M2.5",
@@ -7101,13 +7137,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.26,
-                output: 0.38,
-                cacheRead: 0.13,
+                input: 0.255,
+                output: 0.39999999999999997,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 4096,
+            maxTokens: 163840,
         },
         "deepseek/deepseek-v3.2-exp": {
             id: "deepseek/deepseek-v3.2-exp",
@@ -7662,7 +7698,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.25,
+                input: 0.19999999999999998,
                 output: 1.2,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -7698,7 +7734,7 @@ export const MODELS = {
             cost: {
                 input: 0.3,
                 output: 0.8999999999999999,
-                cacheRead: 0,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
@@ -7715,7 +7751,7 @@ export const MODELS = {
             cost: {
                 input: 0.39999999999999997,
                 output: 2,
-                cacheRead: 0,
+                cacheRead: 0.04,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -7732,7 +7768,7 @@ export const MODELS = {
             cost: {
                 input: 0.39999999999999997,
                 output: 2,
-                cacheRead: 0,
+                cacheRead: 0.04,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -7749,7 +7785,7 @@ export const MODELS = {
             cost: {
                 input: 0.09999999999999999,
                 output: 0.3,
-                cacheRead: 0,
+                cacheRead: 0.01,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -7766,7 +7802,7 @@ export const MODELS = {
             cost: {
                 input: 0.19999999999999998,
                 output: 0.19999999999999998,
-                cacheRead: 0,
+                cacheRead: 0.02,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -7783,7 +7819,7 @@ export const MODELS = {
             cost: {
                 input: 0.09999999999999999,
                 output: 0.09999999999999999,
-                cacheRead: 0,
+                cacheRead: 0.01,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -7800,7 +7836,7 @@ export const MODELS = {
             cost: {
                 input: 0.15,
                 output: 0.15,
-                cacheRead: 0,
+                cacheRead: 0.015,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -7817,7 +7853,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0,
+                cacheRead: 0.19999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -7834,7 +7870,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0,
+                cacheRead: 0.19999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -7851,7 +7887,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0,
+                cacheRead: 0.19999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -7868,7 +7904,7 @@ export const MODELS = {
             cost: {
                 input: 0.5,
                 output: 1.5,
-                cacheRead: 0,
+                cacheRead: 0.049999999999999996,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -7885,7 +7921,7 @@ export const MODELS = {
             cost: {
                 input: 0.39999999999999997,
                 output: 2,
-                cacheRead: 0,
+                cacheRead: 0.04,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -7902,7 +7938,7 @@ export const MODELS = {
             cost: {
                 input: 0.39999999999999997,
                 output: 2,
-                cacheRead: 0,
+                cacheRead: 0.04,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -7936,7 +7972,7 @@ export const MODELS = {
             cost: {
                 input: 0.19999999999999998,
                 output: 0.6,
-                cacheRead: 0,
+                cacheRead: 0.02,
                 cacheWrite: 0,
             },
             contextWindow: 32768,
@@ -7959,6 +7995,23 @@ export const MODELS = {
             contextWindow: 32768,
             maxTokens: 16384,
         },
+        "mistralai/mistral-small-2603": {
+            id: "mistralai/mistral-small-2603",
+            name: "Mistral: Mistral Small 4",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0.015,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 4096,
+        },
         "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)",
@@ -8004,7 +8057,7 @@ export const MODELS = {
             cost: {
                 input: 0.09999999999999999,
                 output: 0.3,
-                cacheRead: 0,
+                cacheRead: 0.01,
                 cacheWrite: 0,
             },
             contextWindow: 32768,
@@ -8021,7 +8074,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0,
+                cacheRead: 0.19999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 65536,
@@ -8055,7 +8108,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0,
+                cacheRead: 0.19999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -8072,7 +8125,7 @@ export const MODELS = {
             cost: {
                 input: 0.09999999999999999,
                 output: 0.3,
-                cacheRead: 0,
+                cacheRead: 0.01,
                 cacheWrite: 0,
             },
             contextWindow: 32000,
@@ -8945,6 +8998,40 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "openai/gpt-5.4-mini": {
+            id: "openai/gpt-5.4-mini",
+            name: "OpenAI: GPT-5.4 Mini",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.75,
+                output: 4.5,
+                cacheRead: 0.075,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "openai/gpt-5.4-nano": {
+            id: "openai/gpt-5.4-nano",
+            name: "OpenAI: GPT-5.4 Nano",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.19999999999999998,
+                output: 1.25,
+                cacheRead: 0.02,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
         "openai/gpt-5.4-pro": {
             id: "openai/gpt-5.4-pro",
             name: "OpenAI: GPT-5.4 Pro",
@@ -9053,7 +9140,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
+            reasoning: true,
             input: ["text", "image"],
             cost: {
                 input: 15,
@@ -9104,7 +9191,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
+            reasoning: true,
             input: ["text"],
             cost: {
                 input: 1.1,
@@ -9121,7 +9208,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
+            reasoning: true,
             input: ["text"],
             cost: {
                 input: 1.1,
@@ -10523,7 +10610,7 @@ export const MODELS = {
                 cacheRead: 0.119,
                 cacheWrite: 0,
             },
-            contextWindow: 202752,
+            contextWindow: 80000,
             maxTokens: 131072,
         },
         "z-ai/glm-5-turbo": {
@@ -10554,7 +10641,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.06,
+                input: 0.12,
                 output: 0.24,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -10607,7 +10694,7 @@ export const MODELS = {
             cost: {
                 input: 0.29,
                 output: 0.59,
-                cacheRead: 0,
+                cacheRead: 0.145,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -10622,9 +10709,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.3,
-                output: 2.9000000000000004,
-                cacheRead: 0,
+                input: 0.22999999999999998,
+                output: 2.3,
+                cacheRead: 0.19999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 262114,
@@ -10641,7 +10728,7 @@ export const MODELS = {
             cost: {
                 input: 0.39999999999999997,
                 output: 1.5999999999999999,
-                cacheRead: 0,
+                cacheRead: 0.022,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -11134,7 +11221,7 @@ export const MODELS = {
             cost: {
                 input: 0.27,
                 output: 1,
-                cacheRead: 0,
+                cacheRead: 0.135,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -11149,9 +11236,9 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.26,
-                output: 0.38,
-                cacheRead: 0.13,
+                input: 0.28,
+                output: 0.42,
+                cacheRead: 0.028,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -11185,7 +11272,7 @@ export const MODELS = {
             cost: {
                 input: 0.15,
                 output: 0.6,
-                cacheRead: 0,
+                cacheRead: 0.024999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -11202,7 +11289,7 @@ export const MODELS = {
             cost: {
                 input: 0.075,
                 output: 0.3,
-                cacheRead: 0,
+                cacheRead: 0.02,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -11242,40 +11329,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "google/gemini-2.5-flash-lite-preview-09-2025": {
-            id: "google/gemini-2.5-flash-lite-preview-09-2025",
-            name: "Gemini 2.5 Flash Lite Preview 09-2025",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.09999999999999999,
-                output: 0.39999999999999997,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
-        "google/gemini-2.5-flash-preview-09-2025": {
-            id: "google/gemini-2.5-flash-preview-09-2025",
-            name: "Gemini 2.5 Flash Preview 09-2025",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.3,
-                output: 2.5,
-                cacheRead: 0.03,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 65536,
-        },
         "google/gemini-2.5-pro": {
             id: "google/gemini-2.5-pro",
             name: "Gemini 2.5 Pro",
@@ -11457,7 +11510,7 @@ export const MODELS = {
             cost: {
                 input: 0.09999999999999999,
                 output: 0.09999999999999999,
-                cacheRead: 0,
+                cacheRead: 0.09999999999999999,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -11630,8 +11683,8 @@ export const MODELS = {
                 cacheRead: 0.03,
                 cacheWrite: 0.375,
             },
-            contextWindow: 4096,
-            maxTokens: 4096,
+            contextWindow: 204800,
+            maxTokens: 131000,
         },
         "mistral/codestral": {
             id: "mistral/codestral",
@@ -11659,8 +11712,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0,
-                output: 0,
+                input: 0.39999999999999997,
+                output: 2,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -11693,8 +11746,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0,
-                output: 0,
+                input: 0.09999999999999999,
+                output: 0.3,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -11710,8 +11763,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.04,
-                output: 0.04,
+                input: 0.09999999999999999,
+                output: 0.09999999999999999,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -11727,8 +11780,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.09999999999999999,
+                input: 0.15,
+                output: 0.15,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -11814,7 +11867,7 @@ export const MODELS = {
             cost: {
                 input: 0.6,
                 output: 2.5,
-                cacheRead: 0,
+                cacheRead: 0.15,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -11831,7 +11884,7 @@ export const MODELS = {
             cost: {
                 input: 0.6,
                 output: 2.5,
-                cacheRead: 0,
+                cacheRead: 0.15,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
@@ -11880,9 +11933,9 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 2.4,
-                output: 10,
-                cacheRead: 0,
+                input: 1.15,
+                output: 8,
+                cacheRead: 0.15,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
@@ -12347,6 +12400,40 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "openai/gpt-5.4-mini": {
+            id: "openai/gpt-5.4-mini",
+            name: "GPT 5.4 Mini",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.75,
+                output: 4.5,
+                cacheRead: 0.075,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "openai/gpt-5.4-nano": {
+            id: "openai/gpt-5.4-nano",
+            name: "GPT 5.4 Nano",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.19999999999999998,
+                output: 1.25,
+                cacheRead: 0.02,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
         "openai/gpt-5.4-pro": {
             id: "openai/gpt-5.4-pro",
             name: "GPT 5.4 Pro",
@@ -12551,40 +12638,6 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 131072,
         },
-        "vercel/v0-1.0-md": {
-            id: "vercel/v0-1.0-md",
-            name: "v0-1.0-md",
-            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,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 32000,
-        },
-        "vercel/v0-1.5-md": {
-            id: "vercel/v0-1.5-md",
-            name: "v0-1.5-md",
-            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,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 32768,
-        },
         "xai/grok-2-vision": {
             id: "xai/grok-2-vision",
             name: "Grok 2 Vision",
@@ -12613,7 +12666,7 @@ export const MODELS = {
             cost: {
                 input: 3,
                 output: 15,
-                cacheRead: 0,
+                cacheRead: 0.75,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -12630,7 +12683,7 @@ export const MODELS = {
             cost: {
                 input: 5,
                 output: 25,
-                cacheRead: 0,
+                cacheRead: 1.25,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -12647,7 +12700,7 @@ export const MODELS = {
             cost: {
                 input: 0.3,
                 output: 0.5,
-                cacheRead: 0,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -12900,8 +12953,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.44999999999999996,
-                output: 1.7999999999999998,
+                input: 0.6,
+                output: 2.2,
                 cacheRead: 0.11,
                 cacheWrite: 0,
             },