@mariozechner/pi-ai 0.49.2 → 0.50.0

package/dist/models.generated.js

@@ -1297,6 +1297,586 @@ export const MODELS = {
             maxTokens: 64000,
         },
     },
+    "azure-openai-responses": {
+        "codex-mini-latest": {
+            id: "codex-mini-latest",
+            name: "Codex Mini",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.5,
+                output: 6,
+                cacheRead: 0.375,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 100000,
+        },
+        "gpt-4": {
+            id: "gpt-4",
+            name: "GPT-4",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 30,
+                output: 60,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 8192,
+            maxTokens: 8192,
+        },
+        "gpt-4-turbo": {
+            id: "gpt-4-turbo",
+            name: "GPT-4 Turbo",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 10,
+                output: 30,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 4096,
+        },
+        "gpt-4.1": {
+            id: "gpt-4.1",
+            name: "GPT-4.1",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 8,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 1047576,
+            maxTokens: 32768,
+        },
+        "gpt-4.1-mini": {
+            id: "gpt-4.1-mini",
+            name: "GPT-4.1 mini",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.4,
+                output: 1.6,
+                cacheRead: 0.1,
+                cacheWrite: 0,
+            },
+            contextWindow: 1047576,
+            maxTokens: 32768,
+        },
+        "gpt-4.1-nano": {
+            id: "gpt-4.1-nano",
+            name: "GPT-4.1 nano",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.1,
+                output: 0.4,
+                cacheRead: 0.03,
+                cacheWrite: 0,
+            },
+            contextWindow: 1047576,
+            maxTokens: 32768,
+        },
+        "gpt-4o": {
+            id: "gpt-4o",
+            name: "GPT-4o",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 2.5,
+                output: 10,
+                cacheRead: 1.25,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
+        "gpt-4o-2024-05-13": {
+            id: "gpt-4o-2024-05-13",
+            name: "GPT-4o (2024-05-13)",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 15,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 4096,
+        },
+        "gpt-4o-2024-08-06": {
+            id: "gpt-4o-2024-08-06",
+            name: "GPT-4o (2024-08-06)",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 2.5,
+                output: 10,
+                cacheRead: 1.25,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
+        "gpt-4o-2024-11-20": {
+            id: "gpt-4o-2024-11-20",
+            name: "GPT-4o (2024-11-20)",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 2.5,
+                output: 10,
+                cacheRead: 1.25,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
+        "gpt-4o-mini": {
+            id: "gpt-4o-mini",
+            name: "GPT-4o mini",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0.08,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
+        "gpt-5": {
+            id: "gpt-5",
+            name: "GPT-5",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.25,
+                output: 10,
+                cacheRead: 0.125,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "gpt-5-chat-latest": {
+            id: "gpt-5-chat-latest",
+            name: "GPT-5 Chat Latest",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 1.25,
+                output: 10,
+                cacheRead: 0.125,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
+        "gpt-5-codex": {
+            id: "gpt-5-codex",
+            name: "GPT-5-Codex",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.25,
+                output: 10,
+                cacheRead: 0.125,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "gpt-5-mini": {
+            id: "gpt-5-mini",
+            name: "GPT-5 Mini",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.25,
+                output: 2,
+                cacheRead: 0.025,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "gpt-5-nano": {
+            id: "gpt-5-nano",
+            name: "GPT-5 Nano",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.05,
+                output: 0.4,
+                cacheRead: 0.005,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "gpt-5-pro": {
+            id: "gpt-5-pro",
+            name: "GPT-5 Pro",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 15,
+                output: 120,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 272000,
+        },
+        "gpt-5.1": {
+            id: "gpt-5.1",
+            name: "GPT-5.1",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.25,
+                output: 10,
+                cacheRead: 0.13,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "gpt-5.1-chat-latest": {
+            id: "gpt-5.1-chat-latest",
+            name: "GPT-5.1 Chat",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.25,
+                output: 10,
+                cacheRead: 0.125,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
+        "gpt-5.1-codex": {
+            id: "gpt-5.1-codex",
+            name: "GPT-5.1 Codex",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.25,
+                output: 10,
+                cacheRead: 0.125,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "gpt-5.1-codex-max": {
+            id: "gpt-5.1-codex-max",
+            name: "GPT-5.1 Codex Max",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.25,
+                output: 10,
+                cacheRead: 0.125,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "gpt-5.1-codex-mini": {
+            id: "gpt-5.1-codex-mini",
+            name: "GPT-5.1 Codex mini",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.25,
+                output: 2,
+                cacheRead: 0.025,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "gpt-5.2": {
+            id: "gpt-5.2",
+            name: "GPT-5.2",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.75,
+                output: 14,
+                cacheRead: 0.175,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "gpt-5.2-chat-latest": {
+            id: "gpt-5.2-chat-latest",
+            name: "GPT-5.2 Chat",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.75,
+                output: 14,
+                cacheRead: 0.175,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
+        "gpt-5.2-codex": {
+            id: "gpt-5.2-codex",
+            name: "GPT-5.2 Codex",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.75,
+                output: 14,
+                cacheRead: 0.175,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "gpt-5.2-pro": {
+            id: "gpt-5.2-pro",
+            name: "GPT-5.2 Pro",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 21,
+                output: 168,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+        "o1": {
+            id: "o1",
+            name: "o1",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 15,
+                output: 60,
+                cacheRead: 7.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 100000,
+        },
+        "o1-pro": {
+            id: "o1-pro",
+            name: "o1-pro",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 150,
+                output: 600,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 100000,
+        },
+        "o3": {
+            id: "o3",
+            name: "o3",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 8,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 100000,
+        },
+        "o3-deep-research": {
+            id: "o3-deep-research",
+            name: "o3-deep-research",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 10,
+                output: 40,
+                cacheRead: 2.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 100000,
+        },
+        "o3-mini": {
+            id: "o3-mini",
+            name: "o3-mini",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.1,
+                output: 4.4,
+                cacheRead: 0.55,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 100000,
+        },
+        "o3-pro": {
+            id: "o3-pro",
+            name: "o3-pro",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 20,
+                output: 80,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 100000,
+        },
+        "o4-mini": {
+            id: "o4-mini",
+            name: "o4-mini",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.1,
+                output: 4.4,
+                cacheRead: 0.28,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 100000,
+        },
+        "o4-mini-deep-research": {
+            id: "o4-mini-deep-research",
+            name: "o4-mini-deep-research",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 8,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 100000,
+        },
+    },
     "cerebras": {
         "gpt-oss-120b": {
             id: "gpt-oss-120b",
@@ -1500,7 +2080,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 64000,
             maxTokens: 16384,
         },
         "gpt-4o": {
@@ -1540,24 +2120,6 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 128000,
         },
-        "gpt-5-codex": {
-            id: "gpt-5-codex",
-            name: "GPT-5-Codex",
-            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: 128000,
-            maxTokens: 128000,
-        },
         "gpt-5-mini": {
             id: "gpt-5-mini",
             name: "GPT-5-mini",
@@ -3415,7 +3977,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.13,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -3466,7 +4028,7 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 2,
-                cacheRead: 0.03,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -3483,7 +4045,7 @@ export const MODELS = {
             cost: {
                 input: 0.05,
                 output: 0.4,
-                cacheRead: 0.01,
+                cacheRead: 0.005,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -3884,40 +4446,6 @@ export const MODELS = {
         },
     },
     "opencode": {
-        "alpha-gd4": {
-            id: "alpha-gd4",
-            name: "Alpha GD4",
-            api: "anthropic-messages",
-            provider: "opencode",
-            baseUrl: "https://opencode.ai/zen",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.5,
-                output: 2,
-                cacheRead: 0.15,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 32768,
-        },
-        "alpha-glm-4.7": {
-            id: "alpha-glm-4.7",
-            name: "Alpha 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: 0.6,
-                cacheWrite: 0,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
         "big-pickle": {
             id: "big-pickle",
             name: "Big Pickle",
@@ -4088,6 +4616,23 @@ export const MODELS = {
             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-4.7-free": {
             id: "glm-4.7-free",
             name: "GLM-4.7",
@@ -4526,8 +5071,8 @@ export const MODELS = {
             cost: {
                 input: 0.7999999999999999,
                 output: 4,
-                cacheRead: 0.08,
-                cacheWrite: 1,
+                cacheRead: 0,
+                cacheWrite: 0,
             },
             contextWindow: 200000,
             maxTokens: 8192,
@@ -4802,7 +5347,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 32768,
         },
         "cohere/command-r-08-2024": {
             id: "cohere/command-r-08-2024",
@@ -5071,7 +5616,7 @@ export const MODELS = {
                 input: 0.09999999999999999,
                 output: 0.39999999999999997,
                 cacheRead: 0.024999999999999998,
-                cacheWrite: 0.0833,
+                cacheWrite: 0.08333333333333334,
             },
             contextWindow: 1048576,
             maxTokens: 8192,
@@ -5139,7 +5684,7 @@ export const MODELS = {
                 input: 0.09999999999999999,
                 output: 0.39999999999999997,
                 cacheRead: 0.01,
-                cacheWrite: 0.0833,
+                cacheWrite: 0.08333333333333334,
             },
             contextWindow: 1048576,
             maxTokens: 65535,
@@ -5156,10 +5701,10 @@ export const MODELS = {
                 input: 0.09999999999999999,
                 output: 0.39999999999999997,
                 cacheRead: 0.01,
-                cacheWrite: 0.0833,
+                cacheWrite: 0.08333333333333334,
             },
             contextWindow: 1048576,
-            maxTokens: 65536,
+            maxTokens: 65535,
         },
         "google/gemini-2.5-flash-preview-09-2025": {
             id: "google/gemini-2.5-flash-preview-09-2025",
@@ -5172,8 +5717,8 @@ export const MODELS = {
             cost: {
                 input: 0.3,
                 output: 2.5,
-                cacheRead: 0.075,
-                cacheWrite: 0.0833,
+                cacheRead: 0.03,
+                cacheWrite: 0.08333333333333334,
             },
             contextWindow: 1048576,
             maxTokens: 65535,
@@ -5206,7 +5751,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.31,
+                cacheRead: 0.125,
                 cacheWrite: 0.375,
             },
             contextWindow: 1048576,
@@ -5223,7 +5768,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.31,
+                cacheRead: 0.125,
                 cacheWrite: 0.375,
             },
             contextWindow: 1048576,
@@ -5241,7 +5786,7 @@ export const MODELS = {
                 input: 0.5,
                 output: 3,
                 cacheRead: 0.049999999999999996,
-                cacheWrite: 0,
+                cacheWrite: 0.08333333333333334,
             },
             contextWindow: 1048576,
             maxTokens: 65535,
@@ -5528,12 +6073,12 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.27,
-                output: 1.12,
+                output: 1.1,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 196608,
-            maxTokens: 65536,
+            maxTokens: 196608,
         },
         "mistralai/codestral-2508": {
             id: "mistralai/codestral-2508",
@@ -5822,7 +6367,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 131072,
+            maxTokens: 16384,
         },
         "mistralai/mistral-saba": {
             id: "mistralai/mistral-saba",
@@ -7535,7 +8080,7 @@ export const MODELS = {
             cost: {
                 input: 0.22,
                 output: 1.7999999999999998,
-                cacheRead: 0,
+                cacheRead: 0.022,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -7643,6 +8188,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 4096,
         },
+        "qwen/qwen3-vl-235b-a22b-thinking": {
+            id: "qwen/qwen3-vl-235b-a22b-thinking",
+            name: "Qwen: Qwen3 VL 235B A22B Thinking",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.44999999999999996,
+                output: 3.5,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
         "qwen/qwen3-vl-30b-a3b-instruct": {
             id: "qwen/qwen3-vl-30b-a3b-instruct",
             name: "Qwen: Qwen3 VL 30B A3B Instruct",
@@ -7654,7 +8216,7 @@ export const MODELS = {
             cost: {
                 input: 0.15,
                 output: 0.6,
-                cacheRead: 0,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -8034,23 +8596,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 4096,
         },
-        "xiaomi/mimo-v2-flash:free": {
-            id: "xiaomi/mimo-v2-flash:free",
-            name: "Xiaomi: MiMo-V2-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: 262144,
-            maxTokens: 65536,
-        },
         "z-ai/glm-4-32b": {
             id: "z-ai/glm-4-32b",
             name: "Z.AI: GLM 4 32B ",
@@ -8164,7 +8709,7 @@ export const MODELS = {
             cost: {
                 input: 0.44,
                 output: 1.76,
-                cacheRead: 0,
+                cacheRead: 0.11,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
@@ -8204,6 +8749,23 @@ export const MODELS = {
             contextWindow: 202752,
             maxTokens: 65535,
         },
+        "z-ai/glm-4.7-flash": {
+            id: "z-ai/glm-4.7-flash",
+            name: "Z.AI: GLM 4.7 Flash",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.07,
+                output: 0.39999999999999997,
+                cacheRead: 0.01,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 131072,
+        },
     },
     "vercel-ai-gateway": {
         "alibaba/qwen-3-14b": {
@@ -8336,7 +8898,7 @@ export const MODELS = {
             cost: {
                 input: 1,
                 output: 5,
-                cacheRead: 0,
+                cacheRead: 0.19999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -8393,23 +8955,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 4096,
         },
-        "anthropic/claude-3-opus": {
-            id: "anthropic/claude-3-opus",
-            name: "Claude 3 Opus",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 15,
-                output: 75,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 8192,
-        },
         "anthropic/claude-3.5-haiku": {
             id: "anthropic/claude-3.5-haiku",
             name: "Claude 3.5 Haiku",
@@ -8560,7 +9105,7 @@ export const MODELS = {
                 cacheRead: 0.3,
                 cacheWrite: 3.75,
             },
-            contextWindow: 200000,
+            contextWindow: 1000000,
             maxTokens: 64000,
         },
         "anthropic/claude-sonnet-4.5": {
@@ -8577,7 +9122,7 @@ export const MODELS = {
                 cacheRead: 0.3,
                 cacheWrite: 3.75,
             },
-            contextWindow: 200000,
+            contextWindow: 1000000,
             maxTokens: 64000,
         },
         "bytedance/seed-1.6": {
@@ -8699,40 +9244,6 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 64000,
         },
-        "google/gemini-2.0-flash": {
-            id: "google/gemini-2.0-flash",
-            name: "Gemini 2.0 Flash",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.09999999999999999,
-                output: 0.39999999999999997,
-                cacheRead: 0.024999999999999998,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 8192,
-        },
-        "google/gemini-2.0-flash-lite": {
-            id: "google/gemini-2.0-flash-lite",
-            name: "Gemini 2.0 Flash Lite",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.075,
-                output: 0.3,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 8192,
-        },
         "google/gemini-2.5-flash": {
             id: "google/gemini-2.5-flash",
             name: "Gemini 2.5 Flash",
@@ -8740,15 +9251,15 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
                 input: 0.3,
                 output: 2.5,
-                cacheRead: 0.03,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
-            maxTokens: 64000,
+            maxTokens: 65536,
         },
         "google/gemini-2.5-flash-lite": {
             id: "google/gemini-2.5-flash-lite",
@@ -8808,11 +9319,11 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.125,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -10223,7 +10734,7 @@ export const MODELS = {
             cost: {
                 input: 0.19999999999999998,
                 output: 1.1,
-                cacheRead: 0,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -10314,6 +10825,23 @@ export const MODELS = {
             contextWindow: 202752,
             maxTokens: 120000,
         },
+        "zai/glm-4.7-flashx": {
+            id: "zai/glm-4.7-flashx",
+            name: "GLM 4.7 FlashX",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.06,
+                output: 0.39999999999999997,
+                cacheRead: 0.01,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 128000,
+        },
     },
     "xai": {
         "grok-2": {