@dreb/ai 2.66.2 → 2.66.3

package/dist/models.generated.js

@@ -4158,6 +4158,25 @@ export const MODELS = {
             contextWindow: 500000,
             maxTokens: 128000,
         },
+        "grok-4.7": {
+            id: "grok-4.7",
+            name: "Grok 4.7",
+            api: "openai-completions",
+            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" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 6,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 500000,
+            maxTokens: 128000,
+        },
         "kimi-k2.7-code": {
             id: "kimi-k2.7-code",
             name: "Kimi K2.7 Code",
@@ -6296,6 +6315,24 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 128000,
         },
+        "tencent/Hy4-preview": {
+            id: "tencent/Hy4-preview",
+            name: "Hy4 preview",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.834,
+                output: 2.501,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 64000,
+        },
         "thinkingmachines/Inkling": {
             id: "thinkingmachines/Inkling",
             name: "Inkling",
@@ -6567,74 +6604,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
-        "k3": {
-            id: "k3",
-            name: "Kimi K3",
-            api: "anthropic-messages",
-            provider: "kimi-coding",
-            baseUrl: "https://api.kimi.com/coding",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 131072,
-        },
-        "k3-256k": {
-            id: "k3-256k",
-            name: "Kimi K3-256K",
-            api: "anthropic-messages",
-            provider: "kimi-coding",
-            baseUrl: "https://api.kimi.com/coding",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 131072,
-        },
-        "kimi-for-coding": {
-            id: "kimi-for-coding",
-            name: "kimi-for-coding",
-            api: "anthropic-messages",
-            provider: "kimi-coding",
-            baseUrl: "https://api.kimi.com/coding",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 32768,
-        },
-        "kimi-for-coding-highspeed": {
-            id: "kimi-for-coding-highspeed",
-            name: "Kimi For Coding HighSpeed",
-            api: "anthropic-messages",
-            provider: "kimi-coding",
-            baseUrl: "https://api.kimi.com/coding",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 32768,
-        },
         "kimi-k2-thinking": {
             id: "kimi-k2-thinking",
             name: "Kimi K2 Thinking",
@@ -7309,6 +7278,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 131072,
         },
+        "zai-glm-5-3": {
+            id: "zai-glm-5-3",
+            name: "GLM-5.3",
+            api: "mistral-conversations",
+            provider: "mistral",
+            baseUrl: "https://api.mistral.ai",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.4,
+                output: 4.4,
+                cacheRead: 0.14,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
     },
     "openai": {
         "gpt-4": {
@@ -8403,6 +8389,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 384000,
         },
+        "deepseek-v4.1-flash": {
+            id: "deepseek-v4.1-flash",
+            name: "DeepSeek V4.1 Flash",
+            api: "openai-completions",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.006,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
         "gemini-3-flash": {
             id: "gemini-3-flash",
             name: "Gemini 3 Flash",
@@ -8898,17 +8901,17 @@ export const MODELS = {
         },
         "gpt-5.6-sol": {
             id: "gpt-5.6-sol",
-            name: "GPT-5.6 Sol (50% Off)",
+            name: "GPT-5.6 Sol",
             api: "openai-responses",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 0.2,
-                cacheWrite: 2.5,
+                input: 4,
+                output: 20,
+                cacheRead: 0.4,
+                cacheWrite: 5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -9287,21 +9290,21 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
-        "union-alpha": {
-            id: "union-alpha",
-            name: "Union Alpha Free",
+        "qwen3.8-flash": {
+            id: "qwen3.8-flash",
+            name: "Qwen3.8 Flash",
             api: "anthropic-messages",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
+                input: 0.15,
+                output: 0.47,
+                cacheRead: 0.016,
+                cacheWrite: 0.2,
             },
-            contextWindow: 262144,
+            contextWindow: 1000000,
             maxTokens: 131072,
         },
     },
@@ -9476,6 +9479,23 @@ export const MODELS = {
             contextWindow: 500000,
             maxTokens: 500000,
         },
+        "grok-4.7": {
+            id: "grok-4.7",
+            name: "Grok 4.7",
+            api: "openai-responses",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 6,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 500000,
+            maxTokens: 500000,
+        },
         "hy3": {
             id: "hy3",
             name: "Hy3",
@@ -9624,7 +9644,7 @@ export const MODELS = {
                 input: 0.3,
                 output: 1.2,
                 cacheRead: 0.06,
-                cacheWrite: 0,
+                cacheWrite: 0.375,
             },
             contextWindow: 204800,
             maxTokens: 131072,
@@ -9765,23 +9785,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 131072,
         },
-        "union-alpha": {
-            id: "union-alpha",
-            name: "Union Alpha Free",
-            api: "anthropic-messages",
-            provider: "opencode-go",
-            baseUrl: "https://opencode.ai/zen/go",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 131072,
-        },
     },
     "openrouter": {
         "aion-labs/aion-2.0": {
@@ -10039,23 +10042,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 64000,
         },
-        "anthropic/claude-opus-4": {
-            id: "anthropic/claude-opus-4",
-            name: "Anthropic: Claude Opus 4",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 15,
-                output: 75,
-                cacheRead: 1.5,
-                cacheWrite: 18.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 32000,
-        },
         "anthropic/claude-opus-4.1": {
             id: "anthropic/claude-opus-4.1",
             name: "Anthropic: Claude Opus 4.1",
@@ -10274,7 +10260,7 @@ export const MODELS = {
                 cacheRead: 0.3,
                 cacheWrite: 3.75,
             },
-            contextWindow: 1000000,
+            contextWindow: 200000,
             maxTokens: 64000,
         },
         "anthropic/claude-sonnet-4.5": {
@@ -10575,13 +10561,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.2574,
-                output: 1.0287,
+                input: 0.32,
+                output: 0.8899999999999999,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 16000,
+            maxTokens: 16384,
         },
         "deepseek/deepseek-chat-v3-0324": {
             id: "deepseek/deepseek-chat-v3-0324",
@@ -10711,9 +10697,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.08707999999999999,
-                output: 0.17415999999999998,
-                cacheRead: 0.017415999999999997,
+                input: 0.055439999999999996,
+                output: 0.11087999999999999,
+                cacheRead: 0.011087999999999999,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -10728,9 +10714,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.06,
-                output: 0.12,
-                cacheRead: 0.012,
+                input: 0.04,
+                output: 0.32,
+                cacheRead: 0.016,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
@@ -10796,13 +10782,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.5999999999999999,
-                output: 3.1999999999999997,
-                cacheRead: 0.135,
+                input: 0.919242,
+                output: 1.838484,
+                cacheRead: 0.0766035,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 393216,
+            maxTokens: 384000,
         },
         "deepseek/deepseek-v4-pro-0813": {
             id: "deepseek/deepseek-v4-pro-0813",
@@ -10813,13 +10799,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.57948,
-                output: 1.73844,
-                cacheRead: 0.018438,
+                input: 0.66,
+                output: 1.9800000000000002,
+                cacheRead: 0.022,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 393216,
+            maxTokens: 384000,
         },
         "deepseek/deepseek-v4-pro-0813:batch": {
             id: "deepseek/deepseek-v4-pro-0813:batch",
@@ -11697,8 +11683,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.1875,
-                output: 0.6525,
+                input: 0.19999999999999998,
+                output: 0.7999999999999999,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -11731,13 +11717,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.35,
-                output: 1.5,
+                input: 0.3,
+                output: 1.2,
                 cacheRead: 0.04,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 117964,
+            maxTokens: 16384,
         },
         "meta/muse-glimmer-30b:batch": {
             id: "meta/muse-glimmer-30b:batch",
@@ -11943,23 +11929,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 512000,
         },
-        "minimax/minimax-m3:batch": {
-            id: "minimax/minimax-m3:batch",
-            name: "MiniMax: MiniMax M3 (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.3,
-                output: 1.2,
-                cacheRead: 0.06,
-                cacheWrite: 0,
-            },
-            contextWindow: 524288,
-            maxTokens: 471859,
-        },
         "mistralai/codestral-2508": {
             id: "mistralai/codestral-2508",
             name: "Mistral: Codestral 2508",
@@ -12113,23 +12082,6 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 104857,
         },
-        "mistralai/mistral-large-2512": {
-            id: "mistralai/mistral-large-2512",
-            name: "Mistral: Mistral Large 3 2512",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.5,
-                output: 1.5,
-                cacheRead: 0.049999999999999996,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 209715,
-        },
         "mistralai/mistral-large-2512:batch": {
             id: "mistralai/mistral-large-2512:batch",
             name: "Mistral: Mistral Large 3 2512 (batch)",
@@ -12300,9 +12252,26 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 209715,
         },
-        "mistralai/mistral-small-3.2-24b-instruct": {
-            id: "mistralai/mistral-small-3.2-24b-instruct",
-            name: "Mistral: Mistral Small 3.2 24B",
+        "mistralai/mistral-small-3.1-24b-instruct": {
+            id: "mistralai/mistral-small-3.1-24b-instruct",
+            name: "Mistral: Mistral Small 3.1 24B",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.351,
+                output: 0.5549999999999999,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 102400,
+        },
+        "mistralai/mistral-small-3.2-24b-instruct": {
+            id: "mistralai/mistral-small-3.2-24b-instruct",
+            name: "Mistral: Mistral Small 3.2 24B",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
@@ -12461,23 +12430,6 @@ export const MODELS = {
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
             input: ["text", "image"],
-            cost: {
-                input: 2.6481380629999998,
-                output: 13.282724250000001,
-                cacheRead: 0.30264435,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 943718,
-        },
-        "moonshotai/kimi-k3:batch": {
-            id: "moonshotai/kimi-k3:batch",
-            name: "MoonshotAI: Kimi K3 (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
             cost: {
                 input: 3,
                 output: 15,
@@ -12598,13 +12550,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.625,
-                output: 3.125,
-                cacheRead: 0.1875,
+                input: 0.6,
+                output: 2.4,
+                cacheRead: 0.12,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 32768,
+            maxTokens: 182520,
         },
         "nvidia/nemotron-3-ultra-550b-a55b:free": {
             id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -12632,13 +12584,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.08,
+                input: 0.07,
                 output: 0.19999999999999998,
                 cacheRead: 0.04,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 131072,
+            maxTokens: 235929,
         },
         "nvidia/nemotron-3.5-lightning:free": {
             id: "nvidia/nemotron-3.5-lightning:free",
@@ -13889,31 +13841,14 @@ export const MODELS = {
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
             input: ["text"],
-            cost: {
-                input: 0.037,
-                output: 0.16999999999999998,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 117964,
-        },
-        "openai/gpt-oss-120b:batch": {
-            id: "openai/gpt-oss-120b:batch",
-            name: "OpenAI: gpt-oss-120b (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
             cost: {
                 input: 0.15,
                 output: 0.6,
-                cacheRead: 0,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 117964,
+            maxTokens: 65536,
         },
         "openai/gpt-oss-20b": {
             id: "openai/gpt-oss-20b",
@@ -14238,6 +14173,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
+        "prism-ml/ternary-bonsai-2-27b": {
+            id: "prism-ml/ternary-bonsai-2-27b",
+            name: "PrismML: Ternary Bonsai 2 27B",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.075,
+                output: 0.5,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 32768,
+        },
         "qwen/qwen-2.5-72b-instruct": {
             id: "qwen/qwen-2.5-72b-instruct",
             name: "Qwen2.5 72B Instruct",
@@ -14774,13 +14726,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.1625,
-                output: 1.3,
-                cacheRead: 0,
+                input: 0.3125,
+                output: 1.25,
+                cacheRead: 0.15625,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 65536,
+            maxTokens: 16384,
         },
         "qwen/qwen3.5-397b-a17b": {
             id: "qwen/qwen3.5-397b-a17b",
@@ -14814,24 +14766,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 235929,
-        },
-        "qwen/qwen3.5-9b:batch": {
-            id: "qwen/qwen3.5-9b:batch",
-            name: "Qwen: Qwen3.5-9B (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.16999999999999998,
-                output: 0.25,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 235929,
+            maxTokens: 32768,
         },
         "qwen/qwen3.5-flash-02-23": {
             id: "qwen/qwen3.5-flash-02-23",
@@ -14910,8 +14845,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.8999999999999999,
+                input: 0.15,
+                output: 1,
                 cacheRead: 0.049999999999999996,
                 cacheWrite: 0,
             },
@@ -15037,39 +14972,39 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 131072,
         },
-        "qwen/qwen3.8-2.4t-a95b:batch": {
-            id: "qwen/qwen3.8-2.4t-a95b:batch",
-            name: "Qwen: Qwen3.8 2.4T A95B (batch)",
+        "qwen/qwen3.8-27b": {
+            id: "qwen/qwen3.8-27b",
+            name: "Qwen: Qwen3.8 27B",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 6,
-                cacheRead: 0.25,
+                input: 0.42,
+                output: 3,
+                cacheRead: 0.08499999999999999,
                 cacheWrite: 0,
             },
-            contextWindow: 1010000,
-            maxTokens: 909000,
+            contextWindow: 1000000,
+            maxTokens: 131072,
         },
-        "qwen/qwen3.8-27b": {
-            id: "qwen/qwen3.8-27b",
-            name: "Qwen: Qwen3.8 27B",
+        "qwen/qwen3.8-27b:free": {
+            id: "qwen/qwen3.8-27b:free",
+            name: "Qwen: Qwen3.8 27B (free)",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.21400000000000002,
-                output: 2.5500000000000003,
-                cacheRead: 0.15,
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 131072,
+            contextWindow: 262144,
+            maxTokens: 235929,
         },
         "qwen/qwen3.8-flash": {
             id: "qwen/qwen3.8-flash",
@@ -15224,23 +15159,6 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 16384,
         },
-        "stealth/union-alpha": {
-            id: "stealth/union-alpha",
-            name: "Union Alpha",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 131072,
-        },
         "stepfun/step-3.5-flash": {
             id: "stepfun/step-3.5-flash",
             name: "StepFun: Step 3.5 Flash",
@@ -15377,23 +15295,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 262144,
         },
-        "thinkingmachines/inkling:batch": {
-            id: "thinkingmachines/inkling:batch",
-            name: "Thinking Machines: Inkling (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1,
-                output: 4.05,
-                cacheRead: 0.16999999999999998,
-                cacheWrite: 0,
-            },
-            contextWindow: 524288,
-            maxTokens: 471859,
-        },
         "thinkingmachines/inkling:free": {
             id: "thinkingmachines/inkling:free",
             name: "Thinking Machines: Inkling (free)",
@@ -15411,6 +15312,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 262144,
         },
+        "unbiased/pareto": {
+            id: "unbiased/pareto",
+            name: "Pareto",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 2.5,
+                output: 7.5,
+                cacheRead: 0.25,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 131072,
+        },
         "upstage/solar-pro-3": {
             id: "upstage/solar-pro-3",
             name: "Upstage: Solar Pro 3",
@@ -15530,6 +15448,23 @@ export const MODELS = {
             contextWindow: 500000,
             maxTokens: 450000,
         },
+        "x-ai/grok-4.7": {
+            id: "x-ai/grok-4.7",
+            name: "SpaceXAI: Grok 4.7",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.5999999999999999,
+                output: 4.8,
+                cacheRead: 0.39999999999999997,
+                cacheWrite: 0,
+            },
+            contextWindow: 500000,
+            maxTokens: 450000,
+        },
         "x-ai/grok-build-0.1": {
             id: "x-ai/grok-build-0.1",
             name: "SpaceXAI: Grok Build 0.1",
@@ -15760,13 +15695,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.4,
-                output: 4.4,
-                cacheRead: 0.14,
+                input: 0.6496,
+                output: 2.0416,
+                cacheRead: 0.12064,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 128000,
+            maxTokens: 131072,
         },
         "z-ai/glm-5.2:batch": {
             id: "z-ai/glm-5.2:batch",
@@ -15794,13 +15729,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.4,
-                output: 4.4,
-                cacheRead: 0.26,
+                input: 0.9099999999999999,
+                output: 2.8600000000000003,
+                cacheRead: 0.16899999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
-            maxTokens: 943717,
+            maxTokens: 131072,
         },
         "z-ai/glm-5.3-flash": {
             id: "z-ai/glm-5.3-flash",
@@ -15811,13 +15746,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.09,
-                output: 0.3,
-                cacheRead: 0.018,
+                input: 0.075,
+                output: 0.25,
+                cacheRead: 0.02,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
-            maxTokens: 131072,
+            maxTokens: 102400,
         },
         "z-ai/glm-5.3-flash:batch": {
             id: "z-ai/glm-5.3-flash:batch",
@@ -15836,6 +15771,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 943718,
         },
+        "z-ai/glm-5.3-flashx": {
+            id: "z-ai/glm-5.3-flashx",
+            name: "Z.ai: GLM 5.3 FlashX",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.37,
+                output: 1.25,
+                cacheRead: 0.075,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
         "z-ai/glm-5.3:batch": {
             id: "z-ai/glm-5.3:batch",
             name: "Z.ai: GLM 5.3 (batch)",
@@ -15947,13 +15899,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0.015,
+                input: 0.12,
+                output: 0.48,
+                cacheRead: 0.0036,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 393216,
+            maxTokens: 943718,
         },
         "~deepseek/deepseek-pro-latest": {
             id: "~deepseek/deepseek-pro-latest",
@@ -15964,13 +15916,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.57948,
-                output: 1.73844,
-                cacheRead: 0.018438,
+                input: 0.558624,
+                output: 1.675872,
+                cacheRead: 0.0186208,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 393216,
+            maxTokens: 384000,
         },
         "~deepseek/deepseek-v4-flash-latest": {
             id: "~deepseek/deepseek-v4-flash-latest",
@@ -15982,12 +15934,12 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.04,
-                output: 0.09999999999999999,
+                output: 0.19999999999999998,
                 cacheRead: 0.01,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
-            maxTokens: 393216,
+            maxTokens: 943718,
         },
         "~google/gemini-flash-latest": {
             id: "~google/gemini-flash-latest",
@@ -16032,9 +15984,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2.0999999999999996,
-                output: 10.950000000000001,
-                cacheRead: 0.22999999999999998,
+                input: 1.7,
+                output: 8.5,
+                cacheRead: 0.16999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -16134,9 +16086,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 6,
-                cacheRead: 0.5,
+                input: 1.5999999999999999,
+                output: 4.8,
+                cacheRead: 0.39999999999999997,
                 cacheWrite: 0,
             },
             contextWindow: 500000,
@@ -16153,11 +16105,11 @@ export const MODELS = {
             cost: {
                 input: 0.075,
                 output: 0.25,
-                cacheRead: 0.015,
+                cacheRead: 0.02,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
-            maxTokens: 131072,
+            maxTokens: 102400,
         },
         "~z-ai/glm-latest": {
             id: "~z-ai/glm-latest",
@@ -16168,13 +16120,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.8775,
-                output: 2.9699999999999998,
-                cacheRead: 0.1755,
+                input: 0.7728,
+                output: 2.4288,
+                cacheRead: 0.14352,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
-            maxTokens: 235929,
+            maxTokens: 131072,
         },
     },
     "vercel-ai-gateway": {
@@ -16413,8 +16365,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 32768,
+            contextWindow: 262114,
+            maxTokens: 262114,
         },
         "alibaba/qwen3-next-80b-a3b-thinking": {
             id: "alibaba/qwen3-next-80b-a3b-thinking",
@@ -16430,8 +16382,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 32768,
+            contextWindow: 262144,
+            maxTokens: 262144,
         },
         "alibaba/qwen3-vl-235b-a22b-instruct": {
             id: "alibaba/qwen3-vl-235b-a22b-instruct",
@@ -16666,9 +16618,9 @@ export const MODELS = {
                 input: 2,
                 output: 6,
                 cacheRead: 0.25,
-                cacheWrite: 2.5,
+                cacheWrite: 0,
             },
-            contextWindow: 1000000,
+            contextWindow: 262144,
             maxTokens: 128000,
         },
         "alibaba/qwen3.8-max-0902": {
@@ -16688,6 +16640,23 @@ export const MODELS = {
             contextWindow: 991000,
             maxTokens: 128000,
         },
+        "alibaba/qwen3.8-omni-flash": {
+            id: "alibaba/qwen3.8-omni-flash",
+            name: "Qwen 3.8 Omni Flash",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.15,
+                output: 0.47,
+                cacheRead: 0.016,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
         "amazon/nova-2-lite": {
             id: "amazon/nova-2-lite",
             name: "Nova 2 Lite",
@@ -17292,13 +17261,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0.015,
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 384000,
+            contextWindow: 1048576,
+            maxTokens: 32768,
         },
         "google/gemini-2.5-flash": {
             id: "google/gemini-2.5-flash",
@@ -18167,6 +18136,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 4000,
         },
+        "mixedbread/toast-1": {
+            id: "mixedbread/toast-1",
+            name: "Toast 1",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.3,
+                output: 0.72,
+                cacheRead: 0.036,
+                cacheWrite: 0,
+            },
+            contextWindow: 131000,
+            maxTokens: 4000,
+        },
         "moonshotai/kimi-k2": {
             id: "moonshotai/kimi-k2",
             name: "Kimi K2 Instruct",
@@ -19111,10 +19097,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 0.19999999999999998,
-                cacheWrite: 2.5,
+                input: 4,
+                output: 20,
+                cacheRead: 0.39999999999999997,
+                cacheWrite: 5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -19128,10 +19114,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 4,
-                output: 20,
-                cacheRead: 0.39999999999999997,
-                cacheWrite: 5,
+                input: 8,
+                output: 40,
+                cacheRead: 0.7999999999999999,
+                cacheWrite: 10,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -19425,6 +19411,40 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 32768,
         },
+        "quiverai/arrow-2": {
+            id: "quiverai/arrow-2",
+            name: "Arrow 2",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 4,
+                output: 20,
+                cacheRead: 0.39999999999999997,
+                cacheWrite: 5,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
+        "quiverai/arrow-2-telos": {
+            id: "quiverai/arrow-2-telos",
+            name: "Arrow 2 Telos",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 6,
+                output: 30,
+                cacheRead: 0.6,
+                cacheWrite: 7.5,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
         "sakana/fugu-max": {
             id: "sakana/fugu-max",
             name: "Fugu Max",
@@ -19680,6 +19700,23 @@ export const MODELS = {
             contextWindow: 500000,
             maxTokens: 500000,
         },
+        "spacexai/grok-4.7": {
+            id: "spacexai/grok-4.7",
+            name: "Grok 4.7",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.2,
+                output: 3.5999999999999996,
+                cacheRead: 0.3,
+                cacheWrite: 0,
+            },
+            contextWindow: 500000,
+            maxTokens: 500000,
+        },
         "spacexai/grok-build-0.1": {
             id: "spacexai/grok-build-0.1",
             name: "Grok Build 0.1",
@@ -20088,6 +20125,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 131000,
         },
+        "zai/glm-5.3-flashx": {
+            id: "zai/glm-5.3-flashx",
+            name: "GLM 5.3 FlashX",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.37,
+                output: 1.25,
+                cacheRead: 0.075,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
         "zai/glm-5v-turbo": {
             id: "zai/glm-5v-turbo",
             name: "GLM 5V Turbo",
@@ -20192,6 +20246,23 @@ export const MODELS = {
             contextWindow: 500000,
             maxTokens: 500000,
         },
+        "grok-4.7": {
+            id: "grok-4.7",
+            name: "Grok 4.7",
+            api: "openai-completions",
+            provider: "xai",
+            baseUrl: "https://api.x.ai/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 6,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 500000,
+            maxTokens: 500000,
+        },
         "grok-build-0.1": {
             id: "grok-build-0.1",
             name: "Grok Build 0.1",