@elyracode/ai 0.9.32 → 0.9.33

package/dist/models.generated.js

@@ -828,10 +828,10 @@ 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,
@@ -845,10 +845,10 @@ 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,
@@ -862,10 +862,10 @@ 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,
@@ -1485,10 +1485,10 @@ 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,
@@ -3872,6 +3872,42 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 256000,
         },
+        "@cf/zai-org/glm-5.3": {
+            id: "@cf/zai-org/glm-5.3",
+            name: "Glm 5.3",
+            api: "openai-completions",
+            provider: "cloudflare-workers-ai",
+            baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+            compat: { "sendSessionAffinityHeaders": true },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.4,
+                output: 4.4,
+                cacheRead: 0.26,
+                cacheWrite: 0,
+            },
+            contextWindow: 1310720,
+            maxTokens: 1310720,
+        },
+        "@cf/zai-org/glm-5.3-flash": {
+            id: "@cf/zai-org/glm-5.3-flash",
+            name: "Glm 5.3 Flash",
+            api: "openai-completions",
+            provider: "cloudflare-workers-ai",
+            baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+            compat: { "sendSessionAffinityHeaders": true },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.15,
+                output: 0.5,
+                cacheRead: 0.03,
+                cacheWrite: 0,
+            },
+            contextWindow: 1310720,
+            maxTokens: 1310720,
+        },
     },
     "deepseek": {
         "deepseek-v4-flash": {
@@ -3914,23 +3950,6 @@ export const MODELS = {
         },
     },
     "fireworks": {
-        "accounts/fireworks/models/deepseek-v4-flash": {
-            id: "accounts/fireworks/models/deepseek-v4-flash",
-            name: "DeepSeek V4 Flash",
-            api: "anthropic-messages",
-            provider: "fireworks",
-            baseUrl: "https://api.fireworks.ai/inference",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.14,
-                output: 0.28,
-                cacheRead: 0.028,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 384000,
-        },
         "accounts/fireworks/models/deepseek-v4-flash-0731": {
             id: "accounts/fireworks/models/deepseek-v4-flash-0731",
             name: "DeepSeek V4 Flash 0731",
@@ -3948,23 +3967,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 384000,
         },
-        "accounts/fireworks/models/deepseek-v4-pro": {
-            id: "accounts/fireworks/models/deepseek-v4-pro",
-            name: "DeepSeek V4 Pro",
-            api: "anthropic-messages",
-            provider: "fireworks",
-            baseUrl: "https://api.fireworks.ai/inference",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 1.74,
-                output: 3.48,
-                cacheRead: 0.145,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 384000,
-        },
         "accounts/fireworks/models/deepseek-v4-pro-0813": {
             id: "accounts/fireworks/models/deepseek-v4-pro-0813",
             name: "DeepSeek V4 Pro 0813",
@@ -3999,35 +4001,35 @@ export const MODELS = {
             contextWindow: 1048575,
             maxTokens: 131072,
         },
-        "accounts/fireworks/models/gpt-oss-120b": {
-            id: "accounts/fireworks/models/gpt-oss-120b",
-            name: "GPT OSS 120B",
+        "accounts/fireworks/models/glm-5p3": {
+            id: "accounts/fireworks/models/glm-5p3",
+            name: "GLM 5.3",
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0.015,
+                input: 1.4,
+                output: 4.4,
+                cacheRead: 0.26,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 32768,
+            contextWindow: 1000000,
+            maxTokens: 131072,
         },
-        "accounts/fireworks/models/gpt-oss-20b": {
-            id: "accounts/fireworks/models/gpt-oss-20b",
-            name: "GPT OSS 20B",
+        "accounts/fireworks/models/gpt-oss-120b": {
+            id: "accounts/fireworks/models/gpt-oss-120b",
+            name: "GPT OSS 120B",
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.07,
-                output: 0.3,
-                cacheRead: 0.035,
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0.015,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -4101,23 +4103,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 131072,
         },
-        "accounts/fireworks/models/minimax-m2p7": {
-            id: "accounts/fireworks/models/minimax-m2p7",
-            name: "MiniMax-M2.7",
-            api: "anthropic-messages",
-            provider: "fireworks",
-            baseUrl: "https://api.fireworks.ai/inference",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 1.2,
-                cacheRead: 0.06,
-                cacheWrite: 0,
-            },
-            contextWindow: 196608,
-            maxTokens: 196608,
-        },
         "accounts/fireworks/models/minimax-m3": {
             id: "accounts/fireworks/models/minimax-m3",
             name: "MiniMax-M3",
@@ -4237,57 +4222,6 @@ export const MODELS = {
             contextWindow: 1048575,
             maxTokens: 131072,
         },
-        "accounts/fireworks/routers/kimi-k2p6-fast": {
-            id: "accounts/fireworks/routers/kimi-k2p6-fast",
-            name: "Kimi K2.6 Fast",
-            api: "anthropic-messages",
-            provider: "fireworks",
-            baseUrl: "https://api.fireworks.ai/inference",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 8,
-                cacheRead: 0.3,
-                cacheWrite: 0,
-            },
-            contextWindow: 262000,
-            maxTokens: 262000,
-        },
-        "accounts/fireworks/routers/kimi-k2p6-turbo": {
-            id: "accounts/fireworks/routers/kimi-k2p6-turbo",
-            name: "Kimi K2.6 Turbo",
-            api: "anthropic-messages",
-            provider: "fireworks",
-            baseUrl: "https://api.fireworks.ai/inference",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 8,
-                cacheRead: 0.3,
-                cacheWrite: 0,
-            },
-            contextWindow: 262000,
-            maxTokens: 262000,
-        },
-        "accounts/fireworks/routers/kimi-k2p7-code-fast": {
-            id: "accounts/fireworks/routers/kimi-k2p7-code-fast",
-            name: "Kimi K2.7 Code Fast",
-            api: "anthropic-messages",
-            provider: "fireworks",
-            baseUrl: "https://api.fireworks.ai/inference",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1.9,
-                output: 8,
-                cacheRead: 0.38,
-                cacheWrite: 0,
-            },
-            contextWindow: 262000,
-            maxTokens: 262000,
-        },
         "accounts/fireworks/routers/kimi-k3-fast": {
             id: "accounts/fireworks/routers/kimi-k3-fast",
             name: "Kimi K3 Fast",
@@ -4564,9 +4498,9 @@ 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,
@@ -4776,7 +4710,7 @@ export const MODELS = {
                 input: 0.2,
                 output: 1.2,
                 cacheRead: 0.02,
-                cacheWrite: 0,
+                cacheWrite: 0.25,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -4792,10 +4726,10 @@ export const MODELS = {
             thinkingLevelMap: { "off": null },
             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,
@@ -4814,7 +4748,7 @@ export const MODELS = {
                 input: 2,
                 output: 12,
                 cacheRead: 0.2,
-                cacheWrite: 0,
+                cacheWrite: 2.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -5671,7 +5605,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 204800,
-            maxTokens: 128000,
+            maxTokens: 131072,
         },
         "MiniMaxAI/MiniMax-M2.1": {
             id: "MiniMaxAI/MiniMax-M2.1",
@@ -5743,7 +5677,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 524288,
-            maxTokens: 128000,
+            maxTokens: 512000,
         },
         "Qwen/Qwen2.5-Coder-32B-Instruct": {
             id: "Qwen/Qwen2.5-Coder-32B-Instruct",
@@ -6123,6 +6057,24 @@ 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-V2.5": {
             id: "XiaomiMiMo/MiMo-V2.5",
             name: "MiMo-V2.5",
@@ -6843,6 +6795,42 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 131072,
         },
+        "zai-org/GLM-5.3": {
+            id: "zai-org/GLM-5.3",
+            name: "GLM-5.3",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.4,
+                output: 4.4,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            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": {
         "k3": {
@@ -6967,8 +6955,8 @@ export const MODELS = {
                 cacheRead: 0.06,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 128000,
+            contextWindow: 1048576,
+            maxTokens: 512000,
         },
     },
     "minimax-cn": {
@@ -7020,8 +7008,8 @@ export const MODELS = {
                 cacheRead: 0.06,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 128000,
+            contextWindow: 1048576,
+            maxTokens: 512000,
         },
     },
     "mistral": {
@@ -7552,18 +7540,35 @@ export const MODELS = {
             contextWindow: 32000,
             maxTokens: 32000,
         },
-    },
-    "moonshotai": {
-        "kimi-k2-0711-preview": {
-            id: "kimi-k2-0711-preview",
-            name: "Kimi K2 0711",
-            api: "openai-completions",
-            provider: "moonshotai",
-            baseUrl: "https://api.moonshot.ai/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
-            reasoning: false,
-            input: ["text"],
-            cost: {
+        "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,
+        },
+    },
+    "moonshotai": {
+        "kimi-k2-0711-preview": {
+            id: "kimi-k2-0711-preview",
+            name: "Kimi K2 0711",
+            api: "openai-completions",
+            provider: "moonshotai",
+            baseUrl: "https://api.moonshot.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            reasoning: false,
+            input: ["text"],
+            cost: {
                 input: 0.6,
                 output: 2.5,
                 cacheRead: 0.15,
@@ -9511,7 +9516,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0.5,
+                cacheRead: 0.3,
                 cacheWrite: 0,
             },
             contextWindow: 500000,
@@ -9636,6 +9641,23 @@ 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",
@@ -9806,23 +9828,6 @@ 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": {
@@ -9933,6 +9938,23 @@ 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",
@@ -9951,9 +9973,9 @@ 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",
@@ -9985,6 +10007,23 @@ 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",
@@ -10138,23 +10177,6 @@ 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",
@@ -10207,6 +10229,23 @@ 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",
@@ -10863,24 +10902,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
-        },
-        "arcee-ai/virtuoso-large": {
-            id: "arcee-ai/virtuoso-large",
-            name: "Arcee AI: Virtuoso Large",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.75,
-                output: 1.2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 64000,
+            maxTokens: 235929,
         },
         "auto": {
             id: "auto",
@@ -10948,7 +10970,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 235929,
         },
         "bytedance-seed/seed-2.0-code": {
             id: "bytedance-seed/seed-2.0-code",
@@ -11084,7 +11106,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 163840,
+            maxTokens: 147456,
         },
         "deepseek/deepseek-chat-v3.1": {
             id: "deepseek/deepseek-chat-v3.1",
@@ -11101,7 +11123,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 161000,
+            maxTokens: 144900,
         },
         "deepseek/deepseek-r1": {
             id: "deepseek/deepseek-r1",
@@ -11163,13 +11185,13 @@ 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: 163840,
+            maxTokens: 65536,
         },
         "deepseek/deepseek-v3.2-exp": {
             id: "deepseek/deepseek-v3.2-exp",
@@ -11199,9 +11221,9 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
             cost: {
-                input: 0.0854,
-                output: 0.1708,
-                cacheRead: 0.01708,
+                input: 0.08316,
+                output: 0.16632,
+                cacheRead: 0.016632,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -11217,14 +11239,33 @@ export const MODELS = {
             reasoning: true,
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
+            cost: {
+                input: 0.045,
+                output: 0.09,
+                cacheRead: 0.009,
+                cacheWrite: 0,
+            },
+            contextWindow: 1310720,
+            maxTokens: 943718,
+        },
+        "deepseek/deepseek-v4-flash-0731:batch": {
+            id: "deepseek/deepseek-v4-flash-0731:batch",
+            name: "DeepSeek: DeepSeek V4 Flash 0731 (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
+            input: ["text"],
             cost: {
                 input: 0.14,
                 output: 0.28,
-                cacheRead: 0.028,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
-            contextWindow: 1310720,
-            maxTokens: 131072,
+            contextWindow: 1048576,
+            maxTokens: 943718,
         },
         "deepseek/deepseek-v4-flash-vision-exp": {
             id: "deepseek/deepseek-v4-flash-vision-exp",
@@ -11256,9 +11297,9 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
             cost: {
-                input: 0.5790719999999999,
-                output: 1.1581439999999998,
-                cacheRead: 0.048256,
+                input: 0.57942,
+                output: 1.15884,
+                cacheRead: 0.048285,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -11275,13 +11316,32 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             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: 4096,
+            maxTokens: 384000,
+        },
+        "deepseek/deepseek-v4-pro-0813:batch": {
+            id: "deepseek/deepseek-v4-pro-0813:batch",
+            name: "DeepSeek: DeepSeek V4 Pro 0813 (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
+            input: ["text"],
+            cost: {
+                input: 1.32,
+                output: 3.9600000000000004,
+                cacheRead: 0.13,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 943718,
         },
         "dots-studio/dots-3-note-preview:free": {
             id: "dots-studio/dots-3-note-preview:free",
@@ -11298,7 +11358,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 512000,
-            maxTokens: 512000,
+            maxTokens: 460800,
         },
         "google/gemini-2.5-flash": {
             id: "google/gemini-2.5-flash",
@@ -11700,10 +11760,10 @@ 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,
@@ -11756,8 +11816,8 @@ export const MODELS = {
                 cacheRead: 0.04,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 131072,
+            contextWindow: 131072,
+            maxTokens: 117964,
         },
         "google/gemma-4-26b-a4b-it": {
             id: "google/gemma-4-26b-a4b-it",
@@ -11802,13 +11862,30 @@ 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:batch": {
+            id: "google/gemma-4-31b-it:batch",
+            name: "Google: Gemma 4 31B (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.39,
+                output: 0.9700000000000001,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 235929,
         },
         "google/gemma-4-31b-it:free": {
             id: "google/gemma-4-31b-it:free",
@@ -11842,7 +11919,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 131072,
+            maxTokens: 117964,
         },
         "inception/mercury-2": {
             id: "inception/mercury-2",
@@ -11878,6 +11955,23 @@ 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",
@@ -11926,7 +12020,7 @@ export const MODELS = {
                 cacheRead: 0.15,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
+            contextWindow: 262144,
             maxTokens: 80000,
         },
         "liquid/lfm-2.5-2.6b:free": {
@@ -11995,7 +12089,7 @@ 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",
@@ -12006,13 +12100,13 @@ 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",
@@ -12040,13 +12134,13 @@ 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",
@@ -12056,6 +12150,23 @@ export const MODELS = {
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
             input: ["text", "image"],
+            cost: {
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.04,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 16384,
+        },
+        "meta/muse-glimmer-30b:batch": {
+            id: "meta/muse-glimmer-30b:batch",
+            name: "Meta: Muse Glimmer 30B (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
             cost: {
                 input: 0.35,
                 output: 1.5,
@@ -12063,7 +12174,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 4096,
+            maxTokens: 117964,
         },
         "meta/muse-spark-1.1": {
             id: "meta/muse-spark-1.1",
@@ -12080,7 +12191,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 4096,
+            maxTokens: 943718,
         },
         "meta/muse-spark-1.2": {
             id: "meta/muse-spark-1.2",
@@ -12097,7 +12208,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 4096,
+            maxTokens: 943718,
         },
         "meta/muse-spark-1.2-contributor": {
             id: "meta/muse-spark-1.2-contributor",
@@ -12114,7 +12225,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 4096,
+            maxTokens: 943718,
         },
         "minimax/minimax-m1": {
             id: "minimax/minimax-m1",
@@ -12199,7 +12310,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 204800,
-            maxTokens: 4096,
+            maxTokens: 131072,
         },
         "minimax/minimax-m2.7:free": {
             id: "minimax/minimax-m2.7:free",
@@ -12216,7 +12327,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 196608,
-            maxTokens: 4096,
+            maxTokens: 176947,
         },
         "minimax/minimax-m3": {
             id: "minimax/minimax-m3",
@@ -12250,7 +12361,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 524288,
-            maxTokens: 4096,
+            maxTokens: 471859,
         },
         "minimax/minimax-m3:free": {
             id: "minimax/minimax-m3:free",
@@ -12267,7 +12378,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 4096,
+            maxTokens: 943718,
         },
         "mistralai/codestral-2508": {
             id: "mistralai/codestral-2508",
@@ -12284,7 +12395,24 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 256000,
-            maxTokens: 4096,
+            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",
@@ -12301,7 +12429,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 209715,
         },
         "mistralai/ministral-14b-2512": {
             id: "mistralai/ministral-14b-2512",
@@ -12318,7 +12446,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 209715,
         },
         "mistralai/ministral-3b-2512": {
             id: "mistralai/ministral-3b-2512",
@@ -12335,7 +12463,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 4096,
+            maxTokens: 104857,
         },
         "mistralai/ministral-8b-2512": {
             id: "mistralai/ministral-8b-2512",
@@ -12352,7 +12480,24 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 209715,
+        },
+        "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", "image"],
+            cost: {
+                input: 0.15,
+                output: 0.15,
+                cacheRead: 0.015,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 209715,
         },
         "mistralai/mistral-large": {
             id: "mistralai/mistral-large",
@@ -12369,7 +12514,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 4096,
+            maxTokens: 102400,
         },
         "mistralai/mistral-large-2407": {
             id: "mistralai/mistral-large-2407",
@@ -12386,7 +12531,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 4096,
+            maxTokens: 104857,
         },
         "mistralai/mistral-large-2512": {
             id: "mistralai/mistral-large-2512",
@@ -12403,7 +12548,24 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            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",
@@ -12420,7 +12582,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 4096,
+            maxTokens: 104857,
         },
         "mistralai/mistral-medium-3-5": {
             id: "mistralai/mistral-medium-3-5",
@@ -12437,7 +12599,24 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            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",
@@ -12454,7 +12633,24 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 4096,
+            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",
@@ -12488,7 +12684,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 32768,
-            maxTokens: 4096,
+            maxTokens: 26214,
         },
         "mistralai/mistral-small-2603": {
             id: "mistralai/mistral-small-2603",
@@ -12505,7 +12701,24 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            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",
@@ -12539,7 +12752,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 65536,
-            maxTokens: 4096,
+            maxTokens: 52428,
         },
         "mistralai/voxtral-small-24b-2507": {
             id: "mistralai/voxtral-small-24b-2507",
@@ -12555,8 +12768,8 @@ export const MODELS = {
                 cacheRead: 0.01,
                 cacheWrite: 0,
             },
-            contextWindow: 32000,
-            maxTokens: 4096,
+            contextWindow: 32768,
+            maxTokens: 26214,
         },
         "moonshotai/kimi-k2": {
             id: "moonshotai/kimi-k2",
@@ -12641,7 +12854,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 235929,
         },
         "moonshotai/kimi-k2.7-code": {
             id: "moonshotai/kimi-k2.7-code",
@@ -12652,34 +12865,34 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.67,
+                input: 0.66,
                 output: 3.4,
-                cacheRead: 0.19,
+                cacheRead: 0.18,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 235929,
         },
-        "moonshotai/kimi-k2.7-code:batch": {
-            id: "moonshotai/kimi-k2.7-code:batch",
-            name: "MoonshotAI: Kimi K2.7 Code (batch)",
+        "moonshotai/kimi-k3": {
+            id: "moonshotai/kimi-k3",
+            name: "MoonshotAI: Kimi K3",
             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,
+                input: 3,
+                output: 15,
+                cacheRead: 0.3,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 4096,
+            contextWindow: 1048576,
+            maxTokens: 943718,
         },
-        "moonshotai/kimi-k3": {
-            id: "moonshotai/kimi-k3",
-            name: "MoonshotAI: Kimi K3",
+        "moonshotai/kimi-k3:batch": {
+            id: "moonshotai/kimi-k3:batch",
+            name: "MoonshotAI: Kimi K3 (batch)",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
@@ -12692,7 +12905,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 1048576,
+            maxTokens: 943718,
         },
         "nex-agi/nex-n2-mini": {
             id: "nex-agi/nex-n2-mini",
@@ -12709,7 +12922,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 235929,
         },
         "nex-agi/nex-n2-pro": {
             id: "nex-agi/nex-n2-pro",
@@ -12726,7 +12939,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 235929,
         },
         "nvidia/nemotron-3-nano-30b-a3b": {
             id: "nvidia/nemotron-3-nano-30b-a3b",
@@ -12739,11 +12952,11 @@ export const MODELS = {
             cost: {
                 input: 0.049999999999999996,
                 output: 0.19999999999999998,
-                cacheRead: 0.03,
+                cacheRead: 0.024999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 228000,
         },
         "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": {
             id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
@@ -12794,7 +13007,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 235929,
         },
         "nvidia/nemotron-3-ultra-550b-a55b": {
             id: "nvidia/nemotron-3-ultra-550b-a55b",
@@ -12805,13 +13018,13 @@ 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: 4096,
+            contextWindow: 262144,
+            maxTokens: 16384,
         },
         "nvidia/nemotron-3-ultra-550b-a55b:batch": {
             id: "nvidia/nemotron-3-ultra-550b-a55b:batch",
@@ -12828,7 +13041,7 @@ 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",
@@ -12913,7 +13126,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 4095,
-            maxTokens: 4096,
+            maxTokens: 3685,
         },
         "openai/gpt-3.5-turbo-16k": {
             id: "openai/gpt-3.5-turbo-16k",
@@ -12932,23 +13145,6 @@ 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",
@@ -12966,23 +13162,6 @@ export const MODELS = {
             contextWindow: 8191,
             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",
@@ -13017,23 +13196,6 @@ 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",
@@ -13045,45 +13207,11 @@ 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",
@@ -13119,40 +13247,6 @@ 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",
@@ -13170,23 +13264,6 @@ 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",
@@ -13204,52 +13281,18 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
-        "openai/gpt-5-mini:batch": {
-            id: "openai/gpt-5-mini:batch",
-            name: "OpenAI: GPT-5 Mini (batch)",
+        "openai/gpt-5-nano": {
+            id: "openai/gpt-5-nano",
+            name: "OpenAI: GPT-5 Nano",
             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",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.049999999999999996,
-                output: 0.39999999999999997,
-                cacheRead: 0.005,
-                cacheWrite: 0,
-            },
-            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,
+                input: 0.049999999999999996,
+                output: 0.39999999999999997,
+                cacheRead: 0.005,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -13272,23 +13315,6 @@ 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",
@@ -13357,23 +13383,6 @@ 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",
@@ -13446,42 +13455,6 @@ 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,
-            thinkingLevelMap: { "xhigh": "xhigh" },
-            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,
-            thinkingLevelMap: { "xhigh": "xhigh" },
-            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",
@@ -13536,24 +13509,6 @@ 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,
-            thinkingLevelMap: { "xhigh": "xhigh" },
-            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",
@@ -13572,24 +13527,6 @@ 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,
-            thinkingLevelMap: { "xhigh": "xhigh" },
-            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",
@@ -13608,42 +13545,6 @@ 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,
-            thinkingLevelMap: { "xhigh": "xhigh" },
-            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,
-            thinkingLevelMap: { "xhigh": "xhigh" },
-            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",
@@ -13680,42 +13581,6 @@ 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,
-            thinkingLevelMap: { "xhigh": "xhigh" },
-            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,
-            thinkingLevelMap: { "xhigh": "xhigh" },
-            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",
@@ -13750,128 +13615,9 @@ 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",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 0.19999999999999998,
-                cacheWrite: 2.5,
-            },
-            contextWindow: 1050000,
-            maxTokens: 128000,
-        },
-        "openai/gpt-5.6-sol-pro": {
-            id: "openai/gpt-5.6-sol-pro",
-            name: "OpenAI: GPT-5.6 Sol Pro",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 0.19999999999999998,
-                cacheWrite: 2.5,
-            },
-            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",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 12,
-                cacheRead: 0.19999999999999998,
-                cacheWrite: 2.5,
-            },
-            contextWindow: 1050000,
-            maxTokens: 128000,
-        },
-        "openai/gpt-5.6-terra-pro": {
-            id: "openai/gpt-5.6-terra-pro",
-            name: "OpenAI: GPT-5.6 Terra Pro",
+            name: "OpenAI: GPT-5.6 Sol",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
@@ -13879,62 +13625,62 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 2,
-                output: 12,
+                output: 10,
                 cacheRead: 0.19999999999999998,
                 cacheWrite: 2.5,
             },
             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)",
+        "openai/gpt-5.6-sol-pro": {
+            id: "openai/gpt-5.6-sol-pro",
+            name: "OpenAI: GPT-5.6 Sol Pro",
             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,
+                input: 2,
+                output: 10,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 2.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
         },
-        "openai/gpt-5.6-terra:batch": {
-            id: "openai/gpt-5.6-terra:batch",
-            name: "OpenAI: GPT-5.6 Terra (batch)",
+        "openai/gpt-5.6-terra": {
+            id: "openai/gpt-5.6-terra",
+            name: "OpenAI: GPT-5.6 Terra",
             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,
+                input: 2,
+                output: 12,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 2.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
         },
-        "openai/gpt-5:batch": {
-            id: "openai/gpt-5:batch",
-            name: "OpenAI: GPT-5 (batch)",
+        "openai/gpt-5.6-terra-pro": {
+            id: "openai/gpt-5.6-terra-pro",
+            name: "OpenAI: GPT-5.6 Terra Pro",
             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,
+                input: 2,
+                output: 12,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 2.5,
             },
-            contextWindow: 400000,
+            contextWindow: 1050000,
             maxTokens: 128000,
         },
         "openai/gpt-audio": {
@@ -14003,7 +13749,24 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 131072,
+            maxTokens: 117964,
+        },
+        "openai/gpt-oss-120b:batch": {
+            id: "openai/gpt-oss-120b:batch",
+            name: "OpenAI: gpt-oss-120b (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 117964,
         },
         "openai/gpt-oss-20b": {
             id: "openai/gpt-oss-20b",
@@ -14020,7 +13783,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 131072,
+            maxTokens: 117964,
         },
         "openai/gpt-oss-safeguard-20b": {
             id: "openai/gpt-oss-safeguard-20b",
@@ -14056,23 +13819,6 @@ 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",
@@ -14124,40 +13870,6 @@ 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",
@@ -14175,40 +13887,6 @@ export const MODELS = {
             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)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1,
-                output: 4,
-                cacheRead: 0.25,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 100000,
-        },
         "openai/o4-mini": {
             id: "openai/o4-mini",
             name: "OpenAI: o4 Mini",
@@ -14243,40 +13921,6 @@ 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",
@@ -14428,7 +14072,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 32768,
-            maxTokens: 32768,
+            maxTokens: 29491,
         },
         "qwen/qwen-plus": {
             id: "qwen/qwen-plus",
@@ -14464,23 +14108,6 @@ 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",
@@ -14524,13 +14151,13 @@ 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",
@@ -14547,7 +14174,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 4096,
+            maxTokens: 117964,
         },
         "qwen/qwen3-30b-a3b": {
             id: "qwen/qwen3-30b-a3b",
@@ -14666,7 +14293,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 235929,
         },
         "qwen/qwen3-coder-flash": {
             id: "qwen/qwen3-coder-flash",
@@ -14700,7 +14327,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 235929,
         },
         "qwen/qwen3-coder-plus": {
             id: "qwen/qwen3-coder-plus",
@@ -14768,7 +14395,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 235929,
         },
         "qwen/qwen3-next-80b-a3b-thinking": {
             id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -14830,13 +14457,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.13,
-                output: 0.52,
+                input: 0.15,
+                output: 0.6,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 32768,
+            maxTokens: 16384,
         },
         "qwen/qwen3-vl-30b-a3b-thinking": {
             id: "qwen/qwen3-vl-30b-a3b-thinking",
@@ -14915,13 +14542,13 @@ 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: 262144,
+            maxTokens: 81920,
         },
         "qwen/qwen3.5-27b": {
             id: "qwen/qwen3.5-27b",
@@ -14955,7 +14582,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 235929,
         },
         "qwen/qwen3.5-397b-a17b": {
             id: "qwen/qwen3.5-397b-a17b",
@@ -14966,13 +14593,13 @@ 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: 262144,
+            maxTokens: 65536,
         },
         "qwen/qwen3.5-9b": {
             id: "qwen/qwen3.5-9b",
@@ -14989,7 +14616,24 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 235929,
+        },
+        "qwen/qwen3.5-9b:batch": {
+            id: "qwen/qwen3.5-9b:batch",
+            name: "Qwen: Qwen3.5-9B (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.16999999999999998,
+                output: 0.25,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 235929,
         },
         "qwen/qwen3.5-flash-02-23": {
             id: "qwen/qwen3.5-flash-02-23",
@@ -15051,13 +14695,13 @@ 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",
@@ -15068,13 +14712,13 @@ 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",
@@ -15193,7 +14837,24 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 131072,
+            maxTokens: 262144,
+        },
+        "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: 2.5,
+                output: 6.25,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 1010000,
+            maxTokens: 909000,
         },
         "qwen/qwen3.8-27b": {
             id: "qwen/qwen3.8-27b",
@@ -15212,6 +14873,23 @@ 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",
@@ -15244,7 +14922,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 16384,
-            maxTokens: 16384,
+            maxTokens: 14745,
         },
         "relace/relace-search": {
             id: "relace/relace-search",
@@ -15305,31 +14983,14 @@ export const MODELS = {
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: false,
             input: ["text"],
-            cost: {
-                input: 0.85,
-                output: 0.85,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            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,
+            cost: {
+                input: 0.85,
+                output: 0.85,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 1048576,
-            maxTokens: 131072,
+            contextWindow: 131072,
+            maxTokens: 16384,
         },
         "stepfun/step-3.5-flash": {
             id: "stepfun/step-3.5-flash",
@@ -15363,7 +15024,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 256000,
+            maxTokens: 230400,
         },
         "tencent/hy3": {
             id: "tencent/hy3",
@@ -15374,14 +15035,31 @@ 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,
             maxTokens: 128000,
         },
+        "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",
@@ -15397,7 +15075,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1024000,
-            maxTokens: 32768,
+            maxTokens: 26214,
         },
         "thinkingmachines/inkling": {
             id: "thinkingmachines/inkling",
@@ -15433,6 +15111,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 262144,
         },
+        "thinkingmachines/inkling-small:batch": {
+            id: "thinkingmachines/inkling-small:batch",
+            name: "Thinking Machines: Inkling Small (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.5,
+                output: 1.2,
+                cacheRead: 0.09999999999999999,
+                cacheWrite: 0,
+            },
+            contextWindow: 524288,
+            maxTokens: 471859,
+        },
         "thinkingmachines/inkling-small:free": {
             id: "thinkingmachines/inkling-small:free",
             name: "Thinking Machines: Inkling Small (free)",
@@ -15465,7 +15160,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 524288,
-            maxTokens: 4096,
+            maxTokens: 471859,
         },
         "thinkingmachines/inkling:free": {
             id: "thinkingmachines/inkling:free",
@@ -15499,7 +15194,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 131072,
+            maxTokens: 117964,
         },
         "upstage/solar-pro4": {
             id: "upstage/solar-pro4",
@@ -15533,7 +15228,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 2000000,
-            maxTokens: 4096,
+            maxTokens: 1800000,
         },
         "x-ai/grok-4.3": {
             id: "x-ai/grok-4.3",
@@ -15550,7 +15245,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
-            maxTokens: 4096,
+            maxTokens: 900000,
         },
         "x-ai/grok-4.5": {
             id: "x-ai/grok-4.5",
@@ -15567,7 +15262,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 500000,
-            maxTokens: 4096,
+            maxTokens: 450000,
         },
         "x-ai/grok-4.6": {
             id: "x-ai/grok-4.6",
@@ -15584,7 +15279,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 500000,
-            maxTokens: 4096,
+            maxTokens: 450000,
         },
         "x-ai/grok-build-0.1": {
             id: "x-ai/grok-build-0.1",
@@ -15601,7 +15296,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 256000,
-            maxTokens: 4096,
+            maxTokens: 230400,
         },
         "xiaomi/mimo-v2.5": {
             id: "xiaomi/mimo-v2.5",
@@ -15697,13 +15392,13 @@ 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",
@@ -15805,7 +15500,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 204800,
-            maxTokens: 202752,
+            maxTokens: 182476,
         },
         "z-ai/glm-5.2": {
             id: "z-ai/glm-5.2",
@@ -15824,23 +15519,6 @@ 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: 4096,
-        },
         "z-ai/glm-5.2:free": {
             id: "z-ai/glm-5.2:free",
             name: "Z.ai: GLM 5.2 (free)",
@@ -15856,7 +15534,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 256000,
-            maxTokens: 256000,
+            maxTokens: 230400,
         },
         "z-ai/glm-5.3": {
             id: "z-ai/glm-5.3",
@@ -15872,9 +15550,43 @@ 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-5.3-flash:batch": {
+            id: "z-ai/glm-5.3-flash:batch",
+            name: "Z.ai: GLM 5.3 Flash (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.15,
+                output: 0.5,
+                cacheRead: 0.03,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048575,
+            maxTokens: 943717,
+        },
         "z-ai/glm-5v-turbo": {
             id: "z-ai/glm-5v-turbo",
             name: "Z.ai: GLM 5V Turbo",
@@ -15972,13 +15684,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
             cost: {
-                input: 0.035,
+                input: 0.03,
                 output: 0.09999999999999999,
-                cacheRead: 0.008,
+                cacheRead: 0.007,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
-            maxTokens: 1048576,
+            maxTokens: 131072,
         },
         "~google/gemini-flash-latest": {
             id: "~google/gemini-flash-latest",
@@ -15989,10 +15701,10 @@ 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,
@@ -16023,13 +15735,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2.8,
-                output: 14,
-                cacheRead: 0.29,
+                input: 2.5500000000000003,
+                output: 12.75,
+                cacheRead: 0.25599998999999996,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 1048576,
+            maxTokens: 943718,
         },
         "~openai/gpt-latest": {
             id: "~openai/gpt-latest",
@@ -16080,7 +15792,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 500000,
-            maxTokens: 4096,
+            maxTokens: 450000,
         },
         "~z-ai/glm-latest": {
             id: "~z-ai/glm-latest",
@@ -16091,12 +15803,12 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.4,
-                output: 4.4,
-                cacheRead: 0.26,
+                input: 1.1875,
+                output: 4.18,
+                cacheRead: 0.24699999999999997,
                 cacheWrite: 0,
             },
-            contextWindow: 1048576,
+            contextWindow: 1310720,
             maxTokens: 131072,
         },
     },
@@ -16459,6 +16171,25 @@ export const MODELS = {
             contextWindow: 512000,
             maxTokens: 164000,
         },
+        "zai-org/GLM-5.3-Flash": {
+            id: "zai-org/GLM-5.3-Flash",
+            name: "GLM-5.3-Flash",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
+            input: ["text", "image"],
+            cost: {
+                input: 0.15,
+                output: 0.5,
+                cacheRead: 0.03,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048575,
+            maxTokens: 400000,
+        },
     },
     "vercel-ai-gateway": {
         "alibaba/qwen-3-14b": {
@@ -16897,11 +16628,11 @@ 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",
@@ -16912,14 +16643,31 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.55,
-                output: 3.3000000000000003,
-                cacheRead: 0.11,
-                cacheWrite: 0,
+                input: 0.5,
+                output: 3,
+                cacheRead: 0.09999999999999999,
+                cacheWrite: 0.625,
             },
             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",
@@ -17495,13 +17243,13 @@ 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",
@@ -17775,6 +17523,40 @@ 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",
@@ -18100,7 +17882,7 @@ 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",
@@ -18117,7 +17899,7 @@ 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",
@@ -18163,8 +17945,8 @@ 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",
@@ -18466,7 +18248,7 @@ export const MODELS = {
             cost: {
                 input: 0.95,
                 output: 4,
-                cacheRead: 0.19,
+                cacheRead: 0.16,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
@@ -19890,13 +19672,30 @@ 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",
@@ -20181,11 +19980,28 @@ 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",
@@ -20629,6 +20445,42 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 131072,
         },
+        "glm-5.3-flash": {
+            id: "glm-5.3-flash",
+            name: "GLM-5.3-Flash",
+            api: "openai-completions",
+            provider: "zai",
+            baseUrl: "https://api.z.ai/api/coding/paas/v4",
+            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
+        "glm-5.3-highspeed": {
+            id: "glm-5.3-highspeed",
+            name: "GLM-5.3 Highspeed",
+            api: "openai-completions",
+            provider: "zai",
+            baseUrl: "https://api.z.ai/api/coding/paas/v4",
+            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
     },
 };
 //# sourceMappingURL=models.generated.js.map