npm - @dreb/ai - Versions diffs - 2.61.2 → 2.63.0 - Mend

@dreb/ai 2.61.2 → 2.63.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (5) hide show

package/dist/models.generated.d.ts +435 -701
package/dist/models.generated.d.ts.map +1 -1
package/dist/models.generated.js +542 -812
package/dist/models.generated.js.map +1 -1
package/package.json +1 -1

package/dist/models.generated.js CHANGED Viewed

@@ -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,
@@ -3235,9 +3235,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1.5,
-                output: 7.5,
-                cacheRead: 0.15,
+                input: 0.75,
+                output: 3.75,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -3438,7 +3438,7 @@ export const MODELS = {
                 input: 0.2,
                 output: 1.2,
                 cacheRead: 0.02,
-                cacheWrite: 0,
+                cacheWrite: 0.25,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -3453,10 +3453,10 @@ 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,
@@ -3474,7 +3474,7 @@ export const MODELS = {
                 input: 2,
                 output: 12,
                 cacheRead: 0.2,
-                cacheWrite: 0,
+                cacheWrite: 2.5,
             },
             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", "image"],
+            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": {
@@ -8230,6 +8283,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 131072,
         },
+        "ling-3.0-flash-fin-free": {
+            id: "ling-3.0-flash-fin-free",
+            name: "Ling 3.0 Flash Fin Free",
+            api: "openai-completions",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 32768,
+        },
         "mimo-v2.5-free": {
             id: "mimo-v2.5-free",
             name: "MiMo V2.5 Free",
@@ -8400,23 +8470,6 @@ 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 +8574,23 @@ 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",
@@ -8572,6 +8642,23 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 64000,
         },
+        "hy4-preview": {
+            id: "hy4-preview",
+            name: "Hy4 preview",
+            api: "openai-completions",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.834,
+                output: 2.501,
+                cacheRead: 0.042,
+                cacheWrite: 0,
+            },
+            contextWindow: 1024000,
+            maxTokens: 64000,
+        },
         "kimi-k2.6": {
             id: "kimi-k2.6",
             name: "Kimi K2.6",
@@ -8725,23 +8812,6 @@ 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",
@@ -8793,6 +8863,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 65536,
         },
+        "qwen3.8-flash": {
+            id: "qwen3.8-flash",
+            name: "Qwen3.8 Flash",
+            api: "anthropic-messages",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.15,
+                output: 0.47,
+                cacheRead: 0.016,
+                cacheWrite: 0.2,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
         "qwen3.8-max": {
             id: "qwen3.8-max",
             name: "Qwen3.8 Max",
@@ -9739,13 +9826,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.26,
-                output: 0.38,
-                cacheRead: 0.13,
+                input: 0.26899999999999996,
+                output: 0.39999999999999997,
+                cacheRead: 0.13449999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 147456,
+            maxTokens: 65536,
         },
         "deepseek/deepseek-v3.2-exp": {
             id: "deepseek/deepseek-v3.2-exp",
@@ -9773,9 +9860,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.0798,
-                output: 0.1596,
-                cacheRead: 0.01596,
+                input: 0.0868,
+                output: 0.1736,
+                cacheRead: 0.01736,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -9790,9 +9877,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.04,
-                output: 0.08,
-                cacheRead: 0.008,
+                input: 0.06,
+                output: 0.12,
+                cacheRead: 0.012,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
@@ -9824,9 +9911,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.55593,
-                output: 1.11186,
-                cacheRead: 0.0463275,
+                input: 0.7518539999999999,
+                output: 1.5037079999999998,
+                cacheRead: 0.0626545,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -9841,13 +9928,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.122,
-                output: 3.366,
-                cacheRead: 0.037399999999999996,
+                input: 0.66,
+                output: 1.9800000000000002,
+                cacheRead: 0.022,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 943717,
+            maxTokens: 384000,
         },
         "dots-studio/dots-3-note-preview:free": {
             id: "dots-studio/dots-3-note-preview:free",
@@ -10266,10 +10353,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.375,
-                output: 1.875,
-                cacheRead: 0.0375,
-                cacheWrite: 0.0208333333333333,
+                input: 0.75,
+                output: 3.75,
+                cacheRead: 0.075,
+                cacheWrite: 0.0416666666666667,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -10322,7 +10409,7 @@ export const MODELS = {
                 cacheRead: 0.04,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
+            contextWindow: 131072,
             maxTokens: 117964,
         },
         "google/gemma-4-26b-a4b-it": {
@@ -10368,13 +10455,13 @@ 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: 235929,
+            maxTokens: 16384,
         },
         "google/gemma-4-31b-it:free": {
             id: "google/gemma-4-31b-it:free",
@@ -10444,6 +10531,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
+        "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,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 32768,
+        },
         "kwaipilot/kat-coder-air-v2.5": {
             id: "kwaipilot/kat-coder-air-v2.5",
             name: "Kwaipilot: KAT-Coder-Air V2.5",
@@ -10492,7 +10596,7 @@ export const MODELS = {
                 cacheRead: 0.15,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
+            contextWindow: 262144,
             maxTokens: 80000,
         },
         "liquid/lfm-2.5-2.6b:free": {
@@ -10572,13 +10676,13 @@ 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",
@@ -10606,13 +10710,13 @@ 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",
@@ -10852,6 +10956,23 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 204800,
         },
+        "mistralai/codestral-2508:batch": {
+            id: "mistralai/codestral-2508:batch",
+            name: "Mistral: Codestral 2508 (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.3,
+                output: 0.8999999999999999,
+                cacheRead: 0.03,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 204800,
+        },
         "mistralai/devstral-2512": {
             id: "mistralai/devstral-2512",
             name: "Mistral: Devstral 2 2512",
@@ -10920,21 +11041,38 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 209715,
         },
-        "mistralai/mistral-large": {
-            id: "mistralai/mistral-large",
-            name: "Mistral Large",
+        "mistralai/ministral-8b-2512:batch": {
+            id: "mistralai/ministral-8b-2512:batch",
+            name: "Mistral: Ministral 3 8B 2512 (batch)",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: false,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 6,
-                cacheRead: 0.19999999999999998,
+                input: 0.15,
+                output: 0.15,
+                cacheRead: 0.015,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 262144,
+            maxTokens: 209715,
+        },
+        "mistralai/mistral-large": {
+            id: "mistralai/mistral-large",
+            name: "Mistral Large",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 2,
+                output: 6,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
             maxTokens: 102400,
         },
         "mistralai/mistral-large-2407": {
@@ -10971,6 +11109,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 209715,
         },
+        "mistralai/mistral-large-2512:batch": {
+            id: "mistralai/mistral-large-2512:batch",
+            name: "Mistral: Mistral Large 3 2512 (batch)",
+            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-medium-3": {
             id: "mistralai/mistral-medium-3",
             name: "Mistral: Mistral Medium 3",
@@ -11005,6 +11160,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 209715,
         },
+        "mistralai/mistral-medium-3-5:batch": {
+            id: "mistralai/mistral-medium-3-5:batch",
+            name: "Mistral: Mistral Medium 3.5 (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.75,
+                output: 3.75,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 209715,
+        },
         "mistralai/mistral-medium-3.1": {
             id: "mistralai/mistral-medium-3.1",
             name: "Mistral: Mistral Medium 3.1",
@@ -11022,6 +11194,23 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 104857,
         },
+        "mistralai/mistral-medium-3.1:batch": {
+            id: "mistralai/mistral-medium-3.1:batch",
+            name: "Mistral: Mistral Medium 3.1 (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.39999999999999997,
+                output: 2,
+                cacheRead: 0.04,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 104857,
+        },
         "mistralai/mistral-nemo": {
             id: "mistralai/mistral-nemo",
             name: "Mistral: Mistral Nemo",
@@ -11073,6 +11262,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 209715,
         },
+        "mistralai/mistral-small-2603:batch": {
+            id: "mistralai/mistral-small-2603:batch",
+            name: "Mistral: Mistral Small 4 (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0.015,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 209715,
+        },
         "mistralai/mistral-small-3.2-24b-instruct": {
             id: "mistralai/mistral-small-3.2-24b-instruct",
             name: "Mistral: Mistral Small 3.2 24B",
@@ -11121,8 +11327,8 @@ export const MODELS = {
                 cacheRead: 0.01,
                 cacheWrite: 0,
             },
-            contextWindow: 32000,
-            maxTokens: 25600,
+            contextWindow: 32768,
+            maxTokens: 26214,
         },
         "moonshotai/kimi-k2": {
             id: "moonshotai/kimi-k2",
@@ -11218,26 +11424,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.67,
+                input: 0.66,
                 output: 3.4,
-                cacheRead: 0.19,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 235929,
-        },
-        "moonshotai/kimi-k2.7-code:batch": {
-            id: "moonshotai/kimi-k2.7-code:batch",
-            name: "MoonshotAI: Kimi K2.7 Code (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.95,
-                output: 4,
-                cacheRead: 0.19,
+                cacheRead: 0.18,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -11305,11 +11494,11 @@ export const MODELS = {
             cost: {
                 input: 0.049999999999999996,
                 output: 0.19999999999999998,
-                cacheRead: 0.03,
+                cacheRead: 0.024999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 235929,
+            maxTokens: 228000,
         },
         "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": {
             id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
@@ -11371,13 +11560,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.6,
-                output: 3.5999999999999996,
-                cacheRead: 0.19999999999999998,
+                input: 0.5,
+                output: 2.2,
+                cacheRead: 0.09999999999999999,
                 cacheWrite: 0,
             },
-            contextWindow: 512288,
-            maxTokens: 461059,
+            contextWindow: 262144,
+            maxTokens: 16384,
         },
         "nvidia/nemotron-3-ultra-550b-a55b:batch": {
             id: "nvidia/nemotron-3-ultra-550b-a55b:batch",
@@ -11498,23 +11687,6 @@ export const MODELS = {
             contextWindow: 16385,
             maxTokens: 4096,
         },
-        "openai/gpt-3.5-turbo:batch": {
-            id: "openai/gpt-3.5-turbo:batch",
-            name: "OpenAI: GPT-3.5 Turbo (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.25,
-                output: 0.75,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 16385,
-            maxTokens: 4096,
-        },
         "openai/gpt-4": {
             id: "openai/gpt-4",
             name: "OpenAI: GPT-4",
@@ -11566,23 +11738,6 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 4096,
         },
-        "openai/gpt-4-turbo:batch": {
-            id: "openai/gpt-4-turbo:batch",
-            name: "OpenAI: GPT-4 Turbo (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 5,
-                output: 15,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 4096,
-        },
         "openai/gpt-4.1": {
             id: "openai/gpt-4.1",
             name: "OpenAI: GPT-4.1",
@@ -11617,23 +11772,6 @@ export const MODELS = {
             contextWindow: 1047576,
             maxTokens: 32768,
         },
-        "openai/gpt-4.1-mini:batch": {
-            id: "openai/gpt-4.1-mini:batch",
-            name: "OpenAI: GPT-4.1 Mini (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.19999999999999998,
-                output: 0.7999999999999999,
-                cacheRead: 0.049999999999999996,
-                cacheWrite: 0,
-            },
-            contextWindow: 1047576,
-            maxTokens: 32768,
-        },
         "openai/gpt-4.1-nano": {
             id: "openai/gpt-4.1-nano",
             name: "OpenAI: GPT-4.1 Nano",
@@ -11645,45 +11783,11 @@ export const MODELS = {
             cost: {
                 input: 0.09999999999999999,
                 output: 0.39999999999999997,
-                cacheRead: 0.024999999999999998,
-                cacheWrite: 0,
-            },
-            contextWindow: 1047576,
-            maxTokens: 32768,
-        },
-        "openai/gpt-4.1-nano:batch": {
-            id: "openai/gpt-4.1-nano:batch",
-            name: "OpenAI: GPT-4.1 Nano (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.049999999999999996,
-                output: 0.19999999999999998,
-                cacheRead: 0.012499999999999999,
-                cacheWrite: 0,
-            },
-            contextWindow: 1047576,
-            maxTokens: 32768,
-        },
-        "openai/gpt-4.1:batch": {
-            id: "openai/gpt-4.1:batch",
-            name: "OpenAI: GPT-4.1 (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 1,
-                output: 4,
-                cacheRead: 0.25,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 1047576,
-            maxTokens: 32768,
+            maxTokens: 942818,
         },
         "openai/gpt-4o": {
             id: "openai/gpt-4o",
@@ -11787,40 +11891,6 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 16384,
         },
-        "openai/gpt-4o-mini:batch": {
-            id: "openai/gpt-4o-mini:batch",
-            name: "OpenAI: GPT-4o-mini (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.075,
-                output: 0.3,
-                cacheRead: 0.0375,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 16384,
-        },
-        "openai/gpt-4o:batch": {
-            id: "openai/gpt-4o:batch",
-            name: "OpenAI: GPT-4o (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 1.25,
-                output: 5,
-                cacheRead: 0.625,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 16384,
-        },
         "openai/gpt-5": {
             id: "openai/gpt-5",
             name: "OpenAI: GPT-5",
@@ -11838,23 +11908,6 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
-        "openai/gpt-5-codex:batch": {
-            id: "openai/gpt-5-codex:batch",
-            name: "OpenAI: GPT-5 Codex (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.625,
-                output: 5,
-                cacheRead: 0.0625,
-                cacheWrite: 0,
-            },
-            contextWindow: 400000,
-            maxTokens: 128000,
-        },
         "openai/gpt-5-mini": {
             id: "openai/gpt-5-mini",
             name: "OpenAI: GPT-5 Mini",
@@ -11872,23 +11925,6 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
-        "openai/gpt-5-mini:batch": {
-            id: "openai/gpt-5-mini:batch",
-            name: "OpenAI: GPT-5 Mini (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.125,
-                output: 1,
-                cacheRead: 0.012499999999999999,
-                cacheWrite: 0,
-            },
-            contextWindow: 400000,
-            maxTokens: 128000,
-        },
         "openai/gpt-5-nano": {
             id: "openai/gpt-5-nano",
             name: "OpenAI: GPT-5 Nano",
@@ -11906,23 +11942,6 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
-        "openai/gpt-5-nano:batch": {
-            id: "openai/gpt-5-nano:batch",
-            name: "OpenAI: GPT-5 Nano (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.024999999999999998,
-                output: 0.19999999999999998,
-                cacheRead: 0.0025,
-                cacheWrite: 0,
-            },
-            contextWindow: 400000,
-            maxTokens: 128000,
-        },
         "openai/gpt-5-pro": {
             id: "openai/gpt-5-pro",
             name: "OpenAI: GPT-5 Pro",
@@ -11940,26 +11959,9 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
-        "openai/gpt-5-pro:batch": {
-            id: "openai/gpt-5-pro:batch",
-            name: "OpenAI: GPT-5 Pro (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 7.5,
-                output: 60,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 400000,
-            maxTokens: 128000,
-        },
-        "openai/gpt-5.1": {
-            id: "openai/gpt-5.1",
-            name: "OpenAI: GPT-5.1",
+        "openai/gpt-5.1": {
+            id: "openai/gpt-5.1",
+            name: "OpenAI: GPT-5.1",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
@@ -12025,23 +12027,6 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
-        "openai/gpt-5.1:batch": {
-            id: "openai/gpt-5.1:batch",
-            name: "OpenAI: GPT-5.1 (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.625,
-                output: 5,
-                cacheRead: 0.0625,
-                cacheWrite: 0,
-            },
-            contextWindow: 400000,
-            maxTokens: 128000,
-        },
         "openai/gpt-5.2": {
             id: "openai/gpt-5.2",
             name: "OpenAI: GPT-5.2",
@@ -12110,40 +12095,6 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
-        "openai/gpt-5.2-pro:batch": {
-            id: "openai/gpt-5.2-pro:batch",
-            name: "OpenAI: GPT-5.2 Pro (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 10.5,
-                output: 84,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 400000,
-            maxTokens: 128000,
-        },
-        "openai/gpt-5.2:batch": {
-            id: "openai/gpt-5.2:batch",
-            name: "OpenAI: GPT-5.2 (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.875,
-                output: 7,
-                cacheRead: 0.0875,
-                cacheWrite: 0,
-            },
-            contextWindow: 400000,
-            maxTokens: 128000,
-        },
         "openai/gpt-5.3-codex": {
             id: "openai/gpt-5.3-codex",
             name: "OpenAI: GPT-5.3-Codex",
@@ -12195,23 +12146,6 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
-        "openai/gpt-5.4-mini:batch": {
-            id: "openai/gpt-5.4-mini:batch",
-            name: "OpenAI: GPT-5.4 Mini (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.375,
-                output: 2.25,
-                cacheRead: 0.0375,
-                cacheWrite: 0,
-            },
-            contextWindow: 400000,
-            maxTokens: 128000,
-        },
         "openai/gpt-5.4-nano": {
             id: "openai/gpt-5.4-nano",
             name: "OpenAI: GPT-5.4 Nano",
@@ -12229,23 +12163,6 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
-        "openai/gpt-5.4-nano:batch": {
-            id: "openai/gpt-5.4-nano:batch",
-            name: "OpenAI: GPT-5.4 Nano (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.09999999999999999,
-                output: 0.625,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 400000,
-            maxTokens: 128000,
-        },
         "openai/gpt-5.4-pro": {
             id: "openai/gpt-5.4-pro",
             name: "OpenAI: GPT-5.4 Pro",
@@ -12263,40 +12180,6 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
-        "openai/gpt-5.4-pro:batch": {
-            id: "openai/gpt-5.4-pro:batch",
-            name: "OpenAI: GPT-5.4 Pro (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 15,
-                output: 90,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1050000,
-            maxTokens: 128000,
-        },
-        "openai/gpt-5.4:batch": {
-            id: "openai/gpt-5.4:batch",
-            name: "OpenAI: GPT-5.4 (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1.25,
-                output: 7.5,
-                cacheRead: 0.125,
-                cacheWrite: 0,
-            },
-            contextWindow: 1050000,
-            maxTokens: 128000,
-        },
         "openai/gpt-5.5": {
             id: "openai/gpt-5.5",
             name: "OpenAI: GPT-5.5",
@@ -12331,40 +12214,6 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
-        "openai/gpt-5.5-pro:batch": {
-            id: "openai/gpt-5.5-pro:batch",
-            name: "OpenAI: GPT-5.5 Pro (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 15,
-                output: 90,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1050000,
-            maxTokens: 128000,
-        },
-        "openai/gpt-5.5:batch": {
-            id: "openai/gpt-5.5:batch",
-            name: "OpenAI: GPT-5.5 (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 2.5,
-                output: 15,
-                cacheRead: 0.25,
-                cacheWrite: 0,
-            },
-            contextWindow: 1050000,
-            maxTokens: 128000,
-        },
         "openai/gpt-5.6-luna": {
             id: "openai/gpt-5.6-luna",
             name: "OpenAI: GPT-5.6 Luna",
@@ -12399,40 +12248,6 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
-        "openai/gpt-5.6-luna-pro:batch": {
-            id: "openai/gpt-5.6-luna-pro:batch",
-            name: "OpenAI: GPT-5.6 Luna Pro (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.09999999999999999,
-                output: 0.6,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 1050000,
-            maxTokens: 128000,
-        },
-        "openai/gpt-5.6-luna:batch": {
-            id: "openai/gpt-5.6-luna:batch",
-            name: "OpenAI: GPT-5.6 Luna (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.09999999999999999,
-                output: 0.6,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 1050000,
-            maxTokens: 128000,
-        },
         "openai/gpt-5.6-sol": {
             id: "openai/gpt-5.6-sol",
             name: "OpenAI: GPT-5.6 Sol",
@@ -12467,40 +12282,6 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
-        "openai/gpt-5.6-sol-pro:batch": {
-            id: "openai/gpt-5.6-sol-pro:batch",
-            name: "OpenAI: GPT-5.6 Sol Pro (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1,
-                output: 5,
-                cacheRead: 0.09999999999999999,
-                cacheWrite: 1.25,
-            },
-            contextWindow: 1050000,
-            maxTokens: 128000,
-        },
-        "openai/gpt-5.6-sol:batch": {
-            id: "openai/gpt-5.6-sol:batch",
-            name: "OpenAI: GPT-5.6 Sol (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1,
-                output: 5,
-                cacheRead: 0.09999999999999999,
-                cacheWrite: 1.25,
-            },
-            contextWindow: 1050000,
-            maxTokens: 128000,
-        },
         "openai/gpt-5.6-terra": {
             id: "openai/gpt-5.6-terra",
             name: "OpenAI: GPT-5.6 Terra",
@@ -12535,57 +12316,6 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
-        "openai/gpt-5.6-terra-pro:batch": {
-            id: "openai/gpt-5.6-terra-pro:batch",
-            name: "OpenAI: GPT-5.6 Terra Pro (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1,
-                output: 6,
-                cacheRead: 0.09999999999999999,
-                cacheWrite: 0,
-            },
-            contextWindow: 1050000,
-            maxTokens: 128000,
-        },
-        "openai/gpt-5.6-terra:batch": {
-            id: "openai/gpt-5.6-terra:batch",
-            name: "OpenAI: GPT-5.6 Terra (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1,
-                output: 6,
-                cacheRead: 0.09999999999999999,
-                cacheWrite: 0,
-            },
-            contextWindow: 1050000,
-            maxTokens: 128000,
-        },
-        "openai/gpt-5:batch": {
-            id: "openai/gpt-5:batch",
-            name: "OpenAI: GPT-5 (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.625,
-                output: 5,
-                cacheRead: 0.0625,
-                cacheWrite: 0,
-            },
-            contextWindow: 400000,
-            maxTokens: 128000,
-        },
         "openai/gpt-audio": {
             id: "openai/gpt-audio",
             name: "OpenAI: GPT Audio",
@@ -12705,23 +12435,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 100000,
         },
-        "openai/o1:batch": {
-            id: "openai/o1:batch",
-            name: "OpenAI: o1 (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 7.5,
-                output: 30,
-                cacheRead: 3.75,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 100000,
-        },
         "openai/o3": {
             id: "openai/o3",
             name: "OpenAI: o3",
@@ -12773,86 +12486,18 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 100000,
         },
-        "openai/o3-mini-high:batch": {
-            id: "openai/o3-mini-high:batch",
-            name: "OpenAI: o3 Mini High (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.55,
-                output: 2.2,
-                cacheRead: 0.275,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 100000,
-        },
-        "openai/o3-mini:batch": {
-            id: "openai/o3-mini:batch",
-            name: "OpenAI: o3 Mini (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.55,
-                output: 2.2,
-                cacheRead: 0.275,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 100000,
-        },
-        "openai/o3-pro": {
-            id: "openai/o3-pro",
-            name: "OpenAI: o3 Pro",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 20,
-                output: 80,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 100000,
-        },
-        "openai/o3-pro:batch": {
-            id: "openai/o3-pro:batch",
-            name: "OpenAI: o3 Pro (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 10,
-                output: 40,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 100000,
-        },
-        "openai/o3:batch": {
-            id: "openai/o3:batch",
-            name: "OpenAI: o3 (batch)",
+        "openai/o3-pro": {
+            id: "openai/o3-pro",
+            name: "OpenAI: o3 Pro",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 4,
-                cacheRead: 0.25,
+                input: 20,
+                output: 80,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 200000,
@@ -12892,40 +12537,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 100000,
         },
-        "openai/o4-mini-high:batch": {
-            id: "openai/o4-mini-high:batch",
-            name: "OpenAI: o4 Mini High (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.55,
-                output: 2.2,
-                cacheRead: 0.1375,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 100000,
-        },
-        "openai/o4-mini:batch": {
-            id: "openai/o4-mini:batch",
-            name: "OpenAI: o4 Mini (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.55,
-                output: 2.2,
-                cacheRead: 0.1375,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 100000,
-        },
         "openrouter/auto": {
             id: "openrouter/auto",
             name: "Auto Router",
@@ -13156,13 +12767,13 @@ 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",
@@ -13547,13 +13158,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.26,
-                output: 2.08,
+                input: 0.29,
+                output: 2.4,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 235929,
+            maxTokens: 81920,
         },
         "qwen/qwen3.5-27b": {
             id: "qwen/qwen3.5-27b",
@@ -13598,13 +13209,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.5,
-                output: 3.5999999999999996,
-                cacheRead: 0.3,
+                input: 0.39,
+                output: 2.34,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 235929,
+            maxTokens: 65536,
         },
         "qwen/qwen3.5-9b": {
             id: "qwen/qwen3.5-9b",
@@ -13683,13 +13294,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.32,
-                output: 3.1999999999999997,
-                cacheRead: 0,
+                input: 0.6,
+                output: 3.5999999999999996,
+                cacheRead: 0.12,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 81920,
+            maxTokens: 235929,
         },
         "qwen/qwen3.6-35b-a3b": {
             id: "qwen/qwen3.6-35b-a3b",
@@ -13700,8 +13311,8 @@ 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,
             },
@@ -13821,12 +13432,29 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0.25,
+                cacheRead: 0.19999999999999998,
                 cacheWrite: 0,
             },
             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)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 2,
+                output: 6,
+                cacheRead: 0.25,
+                cacheWrite: 0,
+            },
+            contextWindow: 1010000,
+            maxTokens: 909000,
+        },
         "qwen/qwen3.8-27b": {
             id: "qwen/qwen3.8-27b",
             name: "Qwen: Qwen3.8 27B",
@@ -13844,6 +13472,23 @@ export const MODELS = {
             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,
+        },
         "qwen/qwen3.8-max": {
             id: "qwen/qwen3.8-max",
             name: "Qwen: Qwen3.8 Max",
@@ -13946,23 +13591,6 @@ 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",
@@ -14006,9 +13634,9 @@ 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,
@@ -14031,6 +13659,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 235929,
         },
+        "tencent/hy4-preview": {
+            id: "tencent/hy4-preview",
+            name: "Tencent: Hy4 preview",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.834,
+                output: 2.501,
+                cacheRead: 0.041999999999999996,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 64000,
+        },
         "thedrummer/unslopnemo-12b": {
             id: "thedrummer/unslopnemo-12b",
             name: "TheDrummer: UnslopNemo 12B",
@@ -14346,13 +13991,13 @@ 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",
@@ -14473,23 +14118,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 262144,
         },
-        "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: 943717,
-        },
         "z-ai/glm-5.2:free": {
             id: "z-ai/glm-5.2:free",
             name: "Z.ai: GLM 5.2 (free)",
@@ -14521,7 +14149,24 @@ export const MODELS = {
                 cacheRead: 0.26,
                 cacheWrite: 0,
             },
-            contextWindow: 1048576,
+            contextWindow: 1310720,
+            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": {
@@ -14618,13 +14263,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.035,
+                input: 0.03,
                 output: 0.09999999999999999,
-                cacheRead: 0.008,
+                cacheRead: 0.007,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
-            maxTokens: 943718,
+            maxTokens: 131072,
         },
         "~google/gemini-flash-latest": {
             id: "~google/gemini-flash-latest",
@@ -14635,10 +14280,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.375,
-                output: 1.875,
-                cacheRead: 0.0375,
-                cacheWrite: 0.0208333333333333,
+                input: 0.75,
+                output: 3.75,
+                cacheRead: 0.075,
+                cacheWrite: 0.0416666666666667,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -14669,13 +14314,13 @@ 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: 877357,
+            maxTokens: 943718,
         },
         "~openai/gpt-latest": {
             id: "~openai/gpt-latest",
@@ -14737,12 +14382,12 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.4,
+                input: 1.25,
                 output: 4.4,
                 cacheRead: 0.26,
                 cacheWrite: 0,
             },
-            contextWindow: 1048576,
+            contextWindow: 1310720,
             maxTokens: 131072,
         },
     },
@@ -15183,11 +14828,11 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.25,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 131072,
+            maxTokens: 128000,
         },
         "alibaba/qwen3.8-27b": {
             id: "alibaba/qwen3.8-27b",
@@ -15206,6 +14851,23 @@ 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",
@@ -15776,13 +15438,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.74,
-                output: 3.48,
-                cacheRead: 0.14,
+                input: 0.66,
+                output: 1.9800000000000002,
+                cacheRead: 0.022,
                 cacheWrite: 0,
             },
-            contextWindow: 1048600,
-            maxTokens: 1048600,
+            contextWindow: 1000000,
+            maxTokens: 384000,
         },
         "deepseek/deepseek-v4-pro-0813": {
             id: "deepseek/deepseek-v4-pro-0813",
@@ -16056,6 +15718,40 @@ 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",
@@ -16381,7 +16077,7 @@ export const MODELS = {
         },
         "minimax/minimax-m2.7": {
             id: "minimax/minimax-m2.7",
-            name: "Minimax M2.7",
+            name: "MiniMax M2.7",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
@@ -16398,7 +16094,7 @@ export const MODELS = {
         },
         "minimax/minimax-m2.7-free": {
             id: "minimax/minimax-m2.7-free",
-            name: "Minimax M2.7 (Free)",
+            name: "MiniMax M2.7 (Free)",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
@@ -16444,8 +16140,8 @@ export const MODELS = {
                 cacheRead: 0.06,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 1000000,
+            contextWindow: 512000,
+            maxTokens: 512000,
         },
         "minimax/minimax-m3-free": {
             id: "minimax/minimax-m3-free",
@@ -16747,7 +16443,7 @@ export const MODELS = {
             cost: {
                 input: 0.95,
                 output: 4,
-                cacheRead: 0.19,
+                cacheRead: 0.16,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
@@ -18173,13 +17869,30 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.13199999999999998,
-                output: 0.5279999999999999,
-                cacheRead: 0.032999999999999995,
+                input: 0.14,
+                output: 0.58,
+                cacheRead: 0.035,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "tencent/hy4-preview": {
+            id: "tencent/hy4-preview",
+            name: "Tencent Hy4 Preview",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.834,
+                output: 2.501,
+                cacheRead: 0.041999999999999996,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 128000,
+            contextWindow: 1024000,
+            maxTokens: 64000,
         },
         "thinkingmachines/inkling": {
             id: "thinkingmachines/inkling",
@@ -18464,11 +18177,28 @@ export const MODELS = {
             cost: {
                 input: 1.4,
                 output: 4.4,
-                cacheRead: 0.26,
+                cacheRead: 0.14,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 1000000,
+        },
+        "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: 12800,
+            maxTokens: 131000,
         },
         "zai/glm-5v-turbo": {
             id: "zai/glm-5v-turbo",