@dreb/ai 2.61.1 → 2.62.0

package/dist/models.generated.js

@@ -776,10 +776,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.22,
-                output: 1.32,
-                cacheRead: 0.022,
-                cacheWrite: 0.275,
+                input: 0.2,
+                output: 1.2,
+                cacheRead: 0.02,
+                cacheWrite: 0.25,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -793,10 +793,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 5.5,
-                output: 33,
-                cacheRead: 0.55,
-                cacheWrite: 6.875,
+                input: 4,
+                output: 20,
+                cacheRead: 0.4,
+                cacheWrite: 5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -810,10 +810,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2.2,
-                output: 13.2,
-                cacheRead: 0.22,
-                cacheWrite: 2.75,
+                input: 2,
+                output: 12,
+                cacheRead: 0.2,
+                cacheWrite: 2.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -1422,10 +1422,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 5.5,
-                output: 33,
-                cacheRead: 0.55,
-                cacheWrite: 6.875,
+                input: 4.4,
+                output: 22,
+                cacheRead: 0.44,
+                cacheWrite: 5.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -2769,10 +2769,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 30,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 4,
+                output: 20,
+                cacheRead: 0.4,
+                cacheWrite: 5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -2803,10 +2803,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 30,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 4,
+                output: 20,
+                cacheRead: 0.4,
+                cacheWrite: 5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -4556,7 +4556,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 204800,
-            maxTokens: 128000,
+            maxTokens: 131072,
         },
         "MiniMaxAI/MiniMax-M2.1": {
             id: "MiniMaxAI/MiniMax-M2.1",
@@ -4628,7 +4628,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 524288,
-            maxTokens: 128000,
+            maxTokens: 512000,
         },
         "Qwen/Qwen2.5-Coder-32B-Instruct": {
             id: "Qwen/Qwen2.5-Coder-32B-Instruct",
@@ -5008,6 +5008,24 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 131072,
         },
+        "Qwen/Qwen3.8-27B": {
+            id: "Qwen/Qwen3.8-27B",
+            name: "Qwen3.8 27B",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.4,
+                output: 3,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 32768,
+        },
         "XiaomiMiMo/MiMo-V2-Flash": {
             id: "XiaomiMiMo/MiMo-V2-Flash",
             name: "MiMo-V2-Flash",
@@ -5746,6 +5764,24 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 131072,
         },
+        "zai-org/GLM-5.3-Flash": {
+            id: "zai-org/GLM-5.3-Flash",
+            name: "GLM-5.3-Flash",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.15,
+                output: 0.5,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
     },
     "kimi-coding": {
         "k2p5": {
@@ -6490,6 +6526,23 @@ export const MODELS = {
             contextWindow: 32000,
             maxTokens: 32000,
         },
+        "zai-glm-5-2": {
+            id: "zai-glm-5-2",
+            name: "GLM-5.2",
+            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": {
@@ -7011,10 +7064,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 30,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 4,
+                output: 20,
+                cacheRead: 0.4,
+                cacheWrite: 5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -7045,10 +7098,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 30,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 4,
+                output: 20,
+                cacheRead: 0.4,
+                cacheWrite: 5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -8069,10 +8122,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2.5,
-                output: 15,
-                cacheRead: 0.25,
-                cacheWrite: 3.125,
+                input: 2,
+                output: 10,
+                cacheRead: 0.2,
+                cacheWrite: 2.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -8105,7 +8158,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0.5,
+                cacheRead: 0.3,
                 cacheWrite: 0,
             },
             contextWindow: 500000,
@@ -8400,23 +8453,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
-        "x-preview-f-free": {
-            id: "x-preview-f-free",
-            name: "Ox Alpha Free (Unlimited)",
-            api: "openai-completions",
-            provider: "opencode",
-            baseUrl: "https://opencode.ai/zen/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 131072,
-        },
     },
     "opencode-go": {
         "deepseek-v4-flash": {
@@ -8521,6 +8557,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 131072,
         },
+        "glm-5.3-flash": {
+            id: "glm-5.3-flash",
+            name: "GLM-5.3-Flash (2x usage)",
+            api: "openai-completions",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.075,
+                output: 0.25,
+                cacheRead: 0.015,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
         "gpt-5.6-luna": {
             id: "gpt-5.6-luna",
             name: "GPT-5.6 Luna",
@@ -8538,9 +8591,9 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
-        "grok-4.5": {
-            id: "grok-4.5",
-            name: "Grok 4.5",
+        "grok-4.6": {
+            id: "grok-4.6",
+            name: "Grok 4.6",
             api: "openai-responses",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
@@ -8623,6 +8676,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 131072,
         },
+        "longcat-2.0": {
+            id: "longcat-2.0",
+            name: "LongCat-2.0",
+            api: "openai-completions",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.006,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
         "mimo-v2.5": {
             id: "mimo-v2.5",
             name: "MiMo V2.5",
@@ -8708,23 +8778,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 131072,
         },
-        "ox-alpha-free": {
-            id: "ox-alpha-free",
-            name: "Ox Alpha Free (Unlimited)",
-            api: "openai-completions",
-            provider: "opencode-go",
-            baseUrl: "https://opencode.ai/zen/go/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 131072,
-        },
         "qwen3.6-plus": {
             id: "qwen3.6-plus",
             name: "Qwen3.6 Plus",
@@ -9422,7 +9475,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 235929,
         },
         "arcee-ai/virtuoso-large": {
             id: "arcee-ai/virtuoso-large",
@@ -9507,7 +9560,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 235929,
         },
         "bytedance-seed/seed-2.0-code": {
             id: "bytedance-seed/seed-2.0-code",
@@ -9643,7 +9696,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 163840,
+            maxTokens: 147456,
         },
         "deepseek/deepseek-chat-v3.1": {
             id: "deepseek/deepseek-chat-v3.1",
@@ -9654,13 +9707,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.25,
-                output: 0.95,
-                cacheRead: 0.13,
+                input: 0.55,
+                output: 1.6500000000000001,
+                cacheRead: 0.55,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 32768,
+            maxTokens: 144900,
         },
         "deepseek/deepseek-r1": {
             id: "deepseek/deepseek-r1",
@@ -9722,13 +9775,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.26899999999999996,
-                output: 0.39999999999999997,
-                cacheRead: 0.13449999999999998,
+                input: 0.26,
+                output: 0.38,
+                cacheRead: 0.13,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 65536,
+            maxTokens: 147456,
         },
         "deepseek/deepseek-v3.2-exp": {
             id: "deepseek/deepseek-v3.2-exp",
@@ -9756,9 +9809,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.07966,
-                output: 0.15932,
-                cacheRead: 0.015932,
+                input: 0.07798000000000001,
+                output: 0.15596000000000002,
+                cacheRead: 0.015595999999999999,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -9773,13 +9826,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.08,
-                output: 0.18,
-                cacheRead: 0.016,
+                input: 0.049999999999999996,
+                output: 0.09999999999999999,
+                cacheRead: 0.01,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
-            maxTokens: 384000,
+            maxTokens: 943718,
         },
         "deepseek/deepseek-v4-flash-vision-exp": {
             id: "deepseek/deepseek-v4-flash-vision-exp",
@@ -9807,13 +9860,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.5999999999999999,
-                output: 3.1999999999999997,
-                cacheRead: 0.135,
+                input: 0.87,
+                output: 1.74,
+                cacheRead: 0.0725,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 393216,
+            maxTokens: 384000,
         },
         "deepseek/deepseek-v4-pro-0813": {
             id: "deepseek/deepseek-v4-pro-0813",
@@ -9824,13 +9877,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.1880000000000002,
-                output: 3.564,
-                cacheRead: 0.039599999999999996,
+                input: 1.122,
+                output: 3.366,
+                cacheRead: 0.037399999999999996,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 4096,
+            maxTokens: 943717,
         },
         "dots-studio/dots-3-note-preview:free": {
             id: "dots-studio/dots-3-note-preview:free",
@@ -9847,7 +9900,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 512000,
-            maxTokens: 512000,
+            maxTokens: 460800,
         },
         "google/gemini-2.5-flash": {
             id: "google/gemini-2.5-flash",
@@ -10306,7 +10359,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 131072,
+            maxTokens: 117964,
         },
         "google/gemma-4-26b-a4b-it": {
             id: "google/gemma-4-26b-a4b-it",
@@ -10351,13 +10404,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.09999999999999999,
+                input: 0.09,
                 output: 0.33999999999999997,
-                cacheRead: 0.09999999999999999,
+                cacheRead: 0.049999999999999996,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 16384,
         },
         "google/gemma-4-31b-it:free": {
             id: "google/gemma-4-31b-it:free",
@@ -10391,7 +10444,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 131072,
+            maxTokens: 117964,
         },
         "inception/mercury-2": {
             id: "inception/mercury-2",
@@ -10410,40 +10463,6 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 50000,
         },
-        "inclusionai/ling-2.6-1t": {
-            id: "inclusionai/ling-2.6-1t",
-            name: "inclusionAI: Ling-2.6-1T",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.075,
-                output: 0.625,
-                cacheRead: 0.015,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 32768,
-        },
-        "inclusionai/ling-2.6-flash": {
-            id: "inclusionai/ling-2.6-flash",
-            name: "inclusionAI: Ling-2.6-flash",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.01,
-                output: 0.03,
-                cacheRead: 0.002,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 32768,
-        },
         "inclusionai/ling-3.0-flash": {
             id: "inclusionai/ling-3.0-flash",
             name: "Ling-3.0-flash",
@@ -10461,22 +10480,22 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
-        "inclusionai/ring-2.6-1t": {
-            id: "inclusionai/ring-2.6-1t",
-            name: "inclusionAI: Ring-2.6-1T",
+        "inclusionai/ling-3.0-flash-fin:free": {
+            id: "inclusionai/ling-3.0-flash-fin:free",
+            name: "Ling 3.0 Flash Fin (free)",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.075,
-                output: 0.625,
-                cacheRead: 0.015,
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 65536,
+            maxTokens: 32768,
         },
         "kwaipilot/kat-coder-air-v2.5": {
             id: "kwaipilot/kat-coder-air-v2.5",
@@ -10595,7 +10614,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 131072,
+            maxTokens: 117964,
         },
         "meta-llama/llama-3.3-70b-instruct": {
             id: "meta-llama/llama-3.3-70b-instruct",
@@ -10606,13 +10625,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.32,
-                cacheRead: 0,
+                input: 0.71,
+                output: 0.71,
+                cacheRead: 0.71,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 16384,
+            maxTokens: 115200,
         },
         "meta-llama/llama-4-maverick": {
             id: "meta-llama/llama-4-maverick",
@@ -10640,13 +10659,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.3,
-                cacheRead: 0,
+                input: 0.11,
+                output: 0.33999999999999997,
+                cacheRead: 0.055,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
-            maxTokens: 16384,
+            maxTokens: 8192,
         },
         "meta/muse-glimmer-30b": {
             id: "meta/muse-glimmer-30b",
@@ -10657,13 +10676,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.3,
-                output: 1.1,
+                input: 0.35,
+                output: 1.5,
                 cacheRead: 0.04,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 131072,
+            maxTokens: 117964,
         },
         "meta/muse-spark-1.1": {
             id: "meta/muse-spark-1.1",
@@ -10680,7 +10699,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 4096,
+            maxTokens: 943718,
         },
         "meta/muse-spark-1.2": {
             id: "meta/muse-spark-1.2",
@@ -10697,7 +10716,24 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 4096,
+            maxTokens: 943718,
+        },
+        "meta/muse-spark-1.2-contributor": {
+            id: "meta/muse-spark-1.2-contributor",
+            name: "Meta: Muse Spark 1.2 Contributor",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.09999999999999999,
+                output: 0.19999999999999998,
+                cacheRead: 0.002,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 943718,
         },
         "minimax/minimax-m1": {
             id: "minimax/minimax-m1",
@@ -10760,12 +10796,12 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.27,
-                output: 0.95,
-                cacheRead: 0.03,
+                output: 1.08,
+                cacheRead: 0.027,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
-            maxTokens: 32768,
+            maxTokens: 128000,
         },
         "minimax/minimax-m2.7": {
             id: "minimax/minimax-m2.7",
@@ -10784,6 +10820,23 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131072,
         },
+        "minimax/minimax-m2.7:free": {
+            id: "minimax/minimax-m2.7:free",
+            name: "MiniMax: MiniMax M2.7 (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: 196608,
+            maxTokens: 176947,
+        },
         "minimax/minimax-m3": {
             id: "minimax/minimax-m3",
             name: "MiniMax: MiniMax M3",
@@ -10816,7 +10869,24 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 524288,
-            maxTokens: 4096,
+            maxTokens: 471859,
+        },
+        "minimax/minimax-m3:free": {
+            id: "minimax/minimax-m3:free",
+            name: "MiniMax: MiniMax M3 (free)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 943718,
         },
         "mistralai/codestral-2508": {
             id: "mistralai/codestral-2508",
@@ -10833,7 +10903,24 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 256000,
-            maxTokens: 4096,
+            maxTokens: 204800,
+        },
+        "mistralai/devstral-2512": {
+            id: "mistralai/devstral-2512",
+            name: "Mistral: Devstral 2 2512",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.44,
+                output: 2.2,
+                cacheRead: 0.044,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 209715,
         },
         "mistralai/ministral-14b-2512": {
             id: "mistralai/ministral-14b-2512",
@@ -10850,7 +10937,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 209715,
         },
         "mistralai/ministral-3b-2512": {
             id: "mistralai/ministral-3b-2512",
@@ -10867,7 +10954,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 4096,
+            maxTokens: 104857,
         },
         "mistralai/ministral-8b-2512": {
             id: "mistralai/ministral-8b-2512",
@@ -10884,7 +10971,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 209715,
         },
         "mistralai/mistral-large": {
             id: "mistralai/mistral-large",
@@ -10901,7 +10988,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 4096,
+            maxTokens: 102400,
         },
         "mistralai/mistral-large-2407": {
             id: "mistralai/mistral-large-2407",
@@ -10918,7 +11005,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 4096,
+            maxTokens: 104857,
         },
         "mistralai/mistral-large-2512": {
             id: "mistralai/mistral-large-2512",
@@ -10935,7 +11022,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 209715,
         },
         "mistralai/mistral-medium-3": {
             id: "mistralai/mistral-medium-3",
@@ -10952,7 +11039,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 4096,
+            maxTokens: 104857,
         },
         "mistralai/mistral-medium-3-5": {
             id: "mistralai/mistral-medium-3-5",
@@ -10969,7 +11056,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 209715,
         },
         "mistralai/mistral-medium-3.1": {
             id: "mistralai/mistral-medium-3.1",
@@ -10986,7 +11073,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 4096,
+            maxTokens: 104857,
         },
         "mistralai/mistral-nemo": {
             id: "mistralai/mistral-nemo",
@@ -11020,7 +11107,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 32768,
-            maxTokens: 4096,
+            maxTokens: 26214,
         },
         "mistralai/mistral-small-2603": {
             id: "mistralai/mistral-small-2603",
@@ -11037,7 +11124,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 209715,
         },
         "mistralai/mistral-small-3.2-24b-instruct": {
             id: "mistralai/mistral-small-3.2-24b-instruct",
@@ -11048,12 +11135,12 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.09375,
-                output: 0.25,
+                input: 0.075,
+                output: 0.19999999999999998,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
+            contextWindow: 131072,
             maxTokens: 16384,
         },
         "mistralai/mixtral-8x22b-instruct": {
@@ -11071,7 +11158,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 65536,
-            maxTokens: 4096,
+            maxTokens: 52428,
         },
         "mistralai/voxtral-small-24b-2507": {
             id: "mistralai/voxtral-small-24b-2507",
@@ -11088,7 +11175,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 32000,
-            maxTokens: 4096,
+            maxTokens: 25600,
         },
         "moonshotai/kimi-k2": {
             id: "moonshotai/kimi-k2",
@@ -11167,13 +11254,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.5795,
-                output: 2.44,
-                cacheRead: 0.0976,
+                input: 0.95,
+                output: 4,
+                cacheRead: 0.16,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 235929,
         },
         "moonshotai/kimi-k2.7-code": {
             id: "moonshotai/kimi-k2.7-code",
@@ -11184,13 +11271,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.67,
+                input: 0.66,
                 output: 3.4,
-                cacheRead: 0.16999999999999998,
+                cacheRead: 0.18,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 235929,
         },
         "moonshotai/kimi-k2.7-code:batch": {
             id: "moonshotai/kimi-k2.7-code:batch",
@@ -11207,7 +11294,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 235929,
         },
         "moonshotai/kimi-k3": {
             id: "moonshotai/kimi-k3",
@@ -11224,7 +11311,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 4096,
+            maxTokens: 943718,
         },
         "nex-agi/nex-n2-mini": {
             id: "nex-agi/nex-n2-mini",
@@ -11241,7 +11328,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 235929,
         },
         "nex-agi/nex-n2-pro": {
             id: "nex-agi/nex-n2-pro",
@@ -11258,7 +11345,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 235929,
         },
         "nvidia/nemotron-3-nano-30b-a3b": {
             id: "nvidia/nemotron-3-nano-30b-a3b",
@@ -11271,28 +11358,11 @@ export const MODELS = {
             cost: {
                 input: 0.049999999999999996,
                 output: 0.19999999999999998,
-                cacheRead: 0.03,
+                cacheRead: 0.024999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
-        },
-        "nvidia/nemotron-3-nano-30b-a3b:free": {
-            id: "nvidia/nemotron-3-nano-30b-a3b:free",
-            name: "NVIDIA: Nemotron 3 Nano 30B A3B (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: 256000,
-            maxTokens: 4096,
+            maxTokens: 228000,
         },
         "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": {
             id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
@@ -11343,7 +11413,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 235929,
         },
         "nvidia/nemotron-3-ultra-550b-a55b": {
             id: "nvidia/nemotron-3-ultra-550b-a55b",
@@ -11360,7 +11430,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 512288,
-            maxTokens: 4096,
+            maxTokens: 461059,
         },
         "nvidia/nemotron-3-ultra-550b-a55b:batch": {
             id: "nvidia/nemotron-3-ultra-550b-a55b:batch",
@@ -11377,7 +11447,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 512288,
-            maxTokens: 4096,
+            maxTokens: 461059,
         },
         "nvidia/nemotron-3-ultra-550b-a55b:free": {
             id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -11430,40 +11500,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 65536,
         },
-        "nvidia/nemotron-nano-12b-v2-vl:free": {
-            id: "nvidia/nemotron-nano-12b-v2-vl:free",
-            name: "NVIDIA: Nemotron Nano 12B 2 VL (free)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 128000,
-        },
-        "nvidia/nemotron-nano-9b-v2:free": {
-            id: "nvidia/nemotron-nano-9b-v2:free",
-            name: "NVIDIA: Nemotron Nano 9B V2 (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: 128000,
-            maxTokens: 4096,
-        },
         "openai/gpt-3.5-turbo": {
             id: "openai/gpt-3.5-turbo",
             name: "OpenAI: GPT-3.5 Turbo",
@@ -11496,7 +11532,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 4095,
-            maxTokens: 4096,
+            maxTokens: 3685,
         },
         "openai/gpt-3.5-turbo-16k": {
             id: "openai/gpt-3.5-turbo-16k",
@@ -12459,10 +12495,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2.5,
-                output: 15,
-                cacheRead: 0.25,
-                cacheWrite: 3.125,
+                input: 2,
+                output: 10,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 2.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -12476,10 +12512,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2.5,
-                output: 15,
-                cacheRead: 0.25,
-                cacheWrite: 3.125,
+                input: 2,
+                output: 10,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 2.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -12493,10 +12529,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1.25,
-                output: 7.5,
-                cacheRead: 0.125,
-                cacheWrite: 0,
+                input: 1,
+                output: 5,
+                cacheRead: 0.09999999999999999,
+                cacheWrite: 1.25,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -12510,10 +12546,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1.25,
-                output: 7.5,
-                cacheRead: 0.125,
-                cacheWrite: 0,
+                input: 1,
+                output: 5,
+                cacheRead: 0.09999999999999999,
+                cacheWrite: 1.25,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -12663,13 +12699,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.03,
+                input: 0.037,
                 output: 0.16999999999999998,
-                cacheRead: 0.03,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 131072,
+            maxTokens: 117964,
         },
         "openai/gpt-oss-20b": {
             id: "openai/gpt-oss-20b",
@@ -12686,24 +12722,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 131072,
-        },
-        "openai/gpt-oss-20b:free": {
-            id: "openai/gpt-oss-20b:free",
-            name: "OpenAI: gpt-oss-20b (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: 131072,
-            maxTokens: 32768,
+            maxTokens: 117964,
         },
         "openai/gpt-oss-safeguard-20b": {
             id: "openai/gpt-oss-safeguard-20b",
@@ -13111,7 +13130,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 32768,
-            maxTokens: 32768,
+            maxTokens: 29491,
         },
         "qwen/qwen-plus": {
             id: "qwen/qwen-plus",
@@ -13147,23 +13166,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 32768,
         },
-        "qwen/qwen-plus-2025-07-28:thinking": {
-            id: "qwen/qwen-plus-2025-07-28:thinking",
-            name: "Qwen: Qwen Plus 0728 (thinking)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.26,
-                output: 0.78,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 32768,
-        },
         "qwen/qwen3-14b": {
             id: "qwen/qwen3-14b",
             name: "Qwen: Qwen3 14B",
@@ -13207,13 +13209,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09,
-                output: 0.55,
-                cacheRead: 0,
+                input: 0.0875,
+                output: 0.35,
+                cacheRead: 0.0175,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 235929,
         },
         "qwen/qwen3-235b-a22b-thinking-2507": {
             id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -13229,8 +13231,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 4096,
+            contextWindow: 131072,
+            maxTokens: 117964,
         },
         "qwen/qwen3-30b-a3b": {
             id: "qwen/qwen3-30b-a3b",
@@ -13241,13 +13243,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.13,
-                output: 0.52,
+                input: 0.12,
+                output: 0.5,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 8192,
+            maxTokens: 16384,
         },
         "qwen/qwen3-30b-a3b-instruct-2507": {
             id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -13349,7 +13351,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 235929,
         },
         "qwen/qwen3-coder-flash": {
             id: "qwen/qwen3-coder-flash",
@@ -13383,7 +13385,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 235929,
         },
         "qwen/qwen3-coder-plus": {
             id: "qwen/qwen3-coder-plus",
@@ -13445,13 +13447,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09,
+                input: 0.09999999999999999,
                 output: 1.1,
-                cacheRead: 0,
+                cacheRead: 0.07,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 235929,
         },
         "qwen/qwen3-next-80b-a3b-thinking": {
             id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -13604,7 +13606,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 65536,
+            maxTokens: 235929,
         },
         "qwen/qwen3.5-27b": {
             id: "qwen/qwen3.5-27b",
@@ -13638,7 +13640,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 235929,
         },
         "qwen/qwen3.5-397b-a17b": {
             id: "qwen/qwen3.5-397b-a17b",
@@ -13672,7 +13674,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 235929,
         },
         "qwen/qwen3.5-flash-02-23": {
             id: "qwen/qwen3.5-flash-02-23",
@@ -13740,7 +13742,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 235929,
         },
         "qwen/qwen3.6-35b-a3b": {
             id: "qwen/qwen3.6-35b-a3b",
@@ -13751,13 +13753,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.14,
-                output: 1,
+                input: 0.09999999999999999,
+                output: 0.8999999999999999,
                 cacheRead: 0.049999999999999996,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 235929,
         },
         "qwen/qwen3.6-flash": {
             id: "qwen/qwen3.6-flash",
@@ -13876,7 +13878,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 262144,
+            maxTokens: 131072,
         },
         "qwen/qwen3.8-27b": {
             id: "qwen/qwen3.8-27b",
@@ -13887,10 +13889,27 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.44999999999999996,
-                output: 3.1999999999999997,
-                cacheRead: 0.049999999999999996,
-                cacheWrite: 0,
+                input: 0.425,
+                output: 2.5500000000000003,
+                cacheRead: 0.08499999999999999,
+                cacheWrite: 0.53125,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
+        "qwen/qwen3.8-flash": {
+            id: "qwen/qwen3.8-flash",
+            name: "Qwen: Qwen3.8 Flash",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.15,
+                output: 0.47,
+                cacheRead: 0.016,
+                cacheWrite: 0.19999999999999998,
             },
             contextWindow: 1000000,
             maxTokens: 131072,
@@ -13927,7 +13946,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 16384,
-            maxTokens: 16384,
+            maxTokens: 14745,
         },
         "relace/relace-search": {
             id: "relace/relace-search",
@@ -13997,23 +14016,6 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 16384,
         },
-        "stealth/ox-alpha": {
-            id: "stealth/ox-alpha",
-            name: "Ox Alpha",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 131072,
-        },
         "stepfun/step-3.5-flash": {
             id: "stepfun/step-3.5-flash",
             name: "StepFun: Step 3.5 Flash",
@@ -14046,7 +14048,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 256000,
+            maxTokens: 230400,
         },
         "tencent/hy3": {
             id: "tencent/hy3",
@@ -14057,9 +14059,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.13199999999999998,
-                output: 0.5279999999999999,
-                cacheRead: 0.032999999999999995,
+                input: 0.0825,
+                output: 0.33,
+                cacheRead: 0.020625,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -14080,7 +14082,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 235929,
         },
         "thedrummer/unslopnemo-12b": {
             id: "thedrummer/unslopnemo-12b",
@@ -14097,7 +14099,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1024000,
-            maxTokens: 1024000,
+            maxTokens: 26214,
         },
         "thinkingmachines/inkling": {
             id: "thinkingmachines/inkling",
@@ -14133,6 +14135,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 262144,
         },
+        "thinkingmachines/inkling-small:free": {
+            id: "thinkingmachines/inkling-small:free",
+            name: "Thinking Machines: Inkling Small (free)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 262144,
+        },
         "thinkingmachines/inkling:batch": {
             id: "thinkingmachines/inkling:batch",
             name: "Thinking Machines: Inkling (batch)",
@@ -14147,8 +14166,25 @@ export const MODELS = {
                 cacheRead: 0.16999999999999998,
                 cacheWrite: 0,
             },
-            contextWindow: 524288,
-            maxTokens: 4096,
+            contextWindow: 524288,
+            maxTokens: 471859,
+        },
+        "thinkingmachines/inkling:free": {
+            id: "thinkingmachines/inkling:free",
+            name: "Thinking Machines: Inkling (free)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 262144,
         },
         "upstage/solar-pro-3": {
             id: "upstage/solar-pro-3",
@@ -14165,7 +14201,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 131072,
+            maxTokens: 117964,
         },
         "upstage/solar-pro4": {
             id: "upstage/solar-pro4",
@@ -14199,7 +14235,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 2000000,
-            maxTokens: 4096,
+            maxTokens: 1800000,
         },
         "x-ai/grok-4.3": {
             id: "x-ai/grok-4.3",
@@ -14216,7 +14252,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
-            maxTokens: 4096,
+            maxTokens: 900000,
         },
         "x-ai/grok-4.5": {
             id: "x-ai/grok-4.5",
@@ -14233,7 +14269,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 500000,
-            maxTokens: 4096,
+            maxTokens: 450000,
         },
         "x-ai/grok-4.6": {
             id: "x-ai/grok-4.6",
@@ -14250,7 +14286,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 500000,
-            maxTokens: 4096,
+            maxTokens: 450000,
         },
         "x-ai/grok-build-0.1": {
             id: "x-ai/grok-build-0.1",
@@ -14267,7 +14303,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 256000,
-            maxTokens: 4096,
+            maxTokens: 230400,
         },
         "xiaomi/mimo-v2.5": {
             id: "xiaomi/mimo-v2.5",
@@ -14363,13 +14399,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.5,
-                output: 2,
-                cacheRead: 0.09999999999999999,
+                input: 0.43,
+                output: 1.75,
+                cacheRead: 0.08,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
-            maxTokens: 131072,
+            maxTokens: 16384,
         },
         "z-ai/glm-4.6v": {
             id: "z-ai/glm-4.6v",
@@ -14465,13 +14501,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.966,
-                output: 3.036,
-                cacheRead: 0.1794,
+                input: 1.26,
+                output: 3.9600000000000004,
+                cacheRead: 0.234,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
-            maxTokens: 128000,
+            maxTokens: 182476,
         },
         "z-ai/glm-5.2": {
             id: "z-ai/glm-5.2",
@@ -14482,30 +14518,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.966,
-                output: 3.036,
-                cacheRead: 0.1932,
+                input: 1.19,
+                output: 3.74,
+                cacheRead: 0.221,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 131072,
-        },
-        "z-ai/glm-5.2:batch": {
-            id: "z-ai/glm-5.2:batch",
-            name: "Z.ai: GLM 5.2 (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 1.4,
-                output: 4.4,
-                cacheRead: 0.26,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048575,
-            maxTokens: 4096,
+            maxTokens: 262144,
         },
         "z-ai/glm-5.2:free": {
             id: "z-ai/glm-5.2:free",
@@ -14522,7 +14541,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 256000,
-            maxTokens: 256000,
+            maxTokens: 230400,
         },
         "z-ai/glm-5.3": {
             id: "z-ai/glm-5.3",
@@ -14541,6 +14560,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 131072,
         },
+        "z-ai/glm-5.3-flash": {
+            id: "z-ai/glm-5.3-flash",
+            name: "Z.ai: GLM 5.3 Flash",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.075,
+                output: 0.25,
+                cacheRead: 0.015,
+                cacheWrite: 0,
+            },
+            contextWindow: 1310720,
+            maxTokens: 131072,
+        },
         "z-ai/glm-5v-turbo": {
             id: "z-ai/glm-5v-turbo",
             name: "Z.ai: GLM 5V Turbo",
@@ -14635,13 +14671,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.065,
-                output: 0.18,
-                cacheRead: 0.02,
+                input: 0.03,
+                output: 0.09999999999999999,
+                cacheRead: 0.007,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
-            maxTokens: 1048576,
+            maxTokens: 131072,
         },
         "~google/gemini-flash-latest": {
             id: "~google/gemini-flash-latest",
@@ -14686,13 +14722,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2.6,
-                output: 13,
-                cacheRead: 0.29,
+                input: 2.5500000000000003,
+                output: 12.75,
+                cacheRead: 0.25599998999999996,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 974842,
+            maxTokens: 943718,
         },
         "~openai/gpt-latest": {
             id: "~openai/gpt-latest",
@@ -14703,10 +14739,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2.5,
-                output: 15,
-                cacheRead: 0.25,
-                cacheWrite: 3.125,
+                input: 2,
+                output: 10,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 2.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -14743,7 +14779,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 500000,
-            maxTokens: 4096,
+            maxTokens: 450000,
         },
         "~z-ai/glm-latest": {
             id: "~z-ai/glm-latest",
@@ -15223,6 +15259,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 131072,
         },
+        "alibaba/qwen3.8-flash": {
+            id: "alibaba/qwen3.8-flash",
+            name: "Qwen 3.8 Flash",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.16,
+                output: 0.47,
+                cacheRead: 0.016,
+                cacheWrite: 0.19999999999999998,
+            },
+            contextWindow: 991000,
+            maxTokens: 128000,
+        },
         "alibaba/qwen3.8-max": {
             id: "alibaba/qwen3.8-max",
             name: "Qwen 3.8 Max",
@@ -15580,23 +15633,6 @@ export const MODELS = {
             contextWindow: 262100,
             maxTokens: 80000,
         },
-        "arcee-ai/trinity-mini": {
-            id: "arcee-ai/trinity-mini",
-            name: "Trinity Mini",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.045,
-                output: 0.15,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
         "bytedance/seed-1.6": {
             id: "bytedance/seed-1.6",
             name: "Seed 1.6",
@@ -15776,9 +15812,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.13,
-                output: 0.26,
-                cacheRead: 0.028,
+                input: 0.07600000000000001,
+                output: 0.153,
+                cacheRead: 0.014,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -15827,9 +15863,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.32,
-                output: 3.9600000000000004,
-                cacheRead: 0.13199999999999998,
+                input: 0.66,
+                output: 1.9800000000000002,
+                cacheRead: 0.06599999999999999,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -16090,6 +16126,40 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 32000,
         },
+        "inclusionai/ling-3.0-flash-fin": {
+            id: "inclusionai/ling-3.0-flash-fin",
+            name: "Ling 3.0 Flash Fin",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 32000,
+        },
+        "inclusionai/ling-3.0-flash-fin-free": {
+            id: "inclusionai/ling-3.0-flash-fin-free",
+            name: "Ling 3.0 Flash Fin (Free)",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 32000,
+        },
         "interfaze/interfaze-beta": {
             id: "interfaze/interfaze-beta",
             name: "Interfaze Beta",
@@ -16430,6 +16500,23 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131000,
         },
+        "minimax/minimax-m2.7-free": {
+            id: "minimax/minimax-m2.7-free",
+            name: "Minimax M2.7 (Free)",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 196608,
+            maxTokens: 196608,
+        },
         "minimax/minimax-m2.7-highspeed": {
             id: "minimax/minimax-m2.7-highspeed",
             name: "MiniMax M2.7 High Speed",
@@ -16464,6 +16551,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 1000000,
         },
+        "minimax/minimax-m3-free": {
+            id: "minimax/minimax-m3-free",
+            name: "MiniMax M3 (Free)",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 1048576,
+        },
         "mistral/codestral": {
             id: "mistral/codestral",
             name: "Mistral Codestral",
@@ -16515,40 +16619,6 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 256000,
         },
-        "mistral/magistral-medium": {
-            id: "mistral/magistral-medium",
-            name: "Magistral Medium 2509",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 5,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 64000,
-        },
-        "mistral/magistral-small": {
-            id: "mistral/magistral-small",
-            name: "Magistral Small 2509",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.5,
-                output: 1.5,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 64000,
-        },
         "mistral/ministral-14b": {
             id: "mistral/ministral-14b",
             name: "Ministral 14B",
@@ -16899,8 +16969,8 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.049999999999999996,
-                output: 0.19999999999999998,
-                cacheRead: 0.01,
+                output: 0.15,
+                cacheRead: 0.049999999999999996,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -17646,10 +17716,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2.5,
-                output: 15,
-                cacheRead: 0.25,
-                cacheWrite: 3.125,
+                input: 2,
+                output: 10,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 2.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -17663,10 +17733,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 30,
-                cacheRead: 0.5,
-                cacheWrite: 3.125,
+                input: 4,
+                output: 20,
+                cacheRead: 0.39999999999999997,
+                cacheWrite: 2.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -17739,6 +17809,23 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 8192,
         },
+        "openai/gpt-oss-safeguard-120b": {
+            id: "openai/gpt-oss-safeguard-120b",
+            name: "GPT OSS Safeguard 120B",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16000,
+        },
         "openai/gpt-oss-safeguard-20b": {
             id: "openai/gpt-oss-safeguard-20b",
             name: "GPT OSS Safeguard 20B",
@@ -17748,13 +17835,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.075,
-                output: 0.3,
-                cacheRead: 0.037,
+                input: 0.07,
+                output: 0.19999999999999998,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 65536,
+            contextWindow: 128000,
+            maxTokens: 16000,
         },
         "openai/o1": {
             id: "openai/o1",
@@ -17790,23 +17877,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 100000,
         },
-        "openai/o3-deep-research": {
-            id: "openai/o3-deep-research",
-            name: "o3-deep-research",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 10,
-                output: 40,
-                cacheRead: 2.5,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 100000,
-        },
         "openai/o3-fast": {
             id: "openai/o3-fast",
             name: "o3 (Fast)",
@@ -18504,6 +18574,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 12800,
         },
+        "zai/glm-5.3-flash": {
+            id: "zai/glm-5.3-flash",
+            name: "GLM 5.3 Flash",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.15,
+                output: 0.5,
+                cacheRead: 0.03,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131000,
+        },
         "zai/glm-5v-turbo": {
             id: "zai/glm-5v-turbo",
             name: "GLM 5V Turbo",