@dreb/ai 2.56.0 → 2.57.1

package/dist/models.generated.js

@@ -3175,6 +3175,25 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "gemini-3.7-flash": {
+            id: "gemini-3.7-flash",
+            name: "Gemini 3.7 Flash",
+            api: "openai-completions",
+            provider: "github-copilot",
+            baseUrl: "https://api.individual.githubcopilot.com",
+            headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.75,
+                output: 3.75,
+                cacheRead: 0.075,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 64000,
+        },
         "gpt-4.1": {
             id: "gpt-4.1",
             name: "GPT-4.1",
@@ -3411,6 +3430,25 @@ export const MODELS = {
             contextWindow: 500000,
             maxTokens: 128000,
         },
+        "grok-4.6": {
+            id: "grok-4.6",
+            name: "Grok 4.6",
+            api: "openai-completions",
+            provider: "github-copilot",
+            baseUrl: "https://api.individual.githubcopilot.com",
+            headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 6,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 500000,
+            maxTokens: 128000,
+        },
         "kimi-k2.7-code": {
             id: "kimi-k2.7-code",
             name: "Kimi K2.7 Code",
@@ -3761,6 +3799,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
+        "gemini-3.7-flash": {
+            id: "gemini-3.7-flash",
+            name: "Gemini 3.7 Flash",
+            api: "google-generative-ai",
+            provider: "google",
+            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.75,
+                output: 3.75,
+                cacheRead: 0.075,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
         "gemini-flash-latest": {
             id: "gemini-flash-latest",
             name: "Gemini Flash Latest",
@@ -4507,6 +4562,24 @@ export const MODELS = {
             contextWindow: 524288,
             maxTokens: 128000,
         },
+        "Qwen/Qwen2.5-Coder-32B-Instruct": {
+            id: "Qwen/Qwen2.5-Coder-32B-Instruct",
+            name: "Qwen2.5-Coder-32B-Instruct",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.06,
+                output: 0.2,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 8192,
+        },
         "Qwen/Qwen3-235B-A22B": {
             id: "Qwen/Qwen3-235B-A22B",
             name: "Qwen3 235B-A22B",
@@ -4561,6 +4634,24 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 131072,
         },
+        "Qwen/Qwen3-30B-A3B": {
+            id: "Qwen/Qwen3-30B-A3B",
+            name: "Qwen3 30B A3B",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.12,
+                output: 0.5,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 40960,
+            maxTokens: 16384,
+        },
         "Qwen/Qwen3-32B": {
             id: "Qwen/Qwen3-32B",
             name: "Qwen3 32B",
@@ -4903,6 +4994,24 @@ export const MODELS = {
             contextWindow: 64000,
             maxTokens: 8192,
         },
+        "deepseek-ai/DeepSeek-V3-0324": {
+            id: "deepseek-ai/DeepSeek-V3-0324",
+            name: "DeepSeek V3 0324",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.27,
+                output: 1.12,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 163840,
+            maxTokens: 163840,
+        },
         "deepseek-ai/DeepSeek-V3.1": {
             id: "deepseek-ai/DeepSeek-V3.1",
             name: "DeepSeek-V3.1",
@@ -4993,6 +5102,24 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 393216,
         },
+        "deepseek-ai/DeepSeek-V4-Pro-0813": {
+            id: "deepseek-ai/DeepSeek-V4-Pro-0813",
+            name: "DeepSeek V4 Pro 0813",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.32,
+                output: 3.96,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
         "google/gemma-4-26B-A4B-it": {
             id: "google/gemma-4-26B-A4B-it",
             name: "Gemma 4 26B A4B IT",
@@ -5029,6 +5156,24 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
+        "meta-llama/Llama-3.1-8B-Instruct": {
+            id: "meta-llama/Llama-3.1-8B-Instruct",
+            name: "Llama-3.1-8B-Instruct",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.06,
+                output: 0.06,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 4096,
+        },
         "meta-llama/Llama-3.3-70B-Instruct": {
             id: "meta-llama/Llama-3.3-70B-Instruct",
             name: "Llama-3.3-70B-Instruct",
@@ -7435,6 +7580,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
+        "gemini-3.7-flash": {
+            id: "gemini-3.7-flash",
+            name: "Gemini 3.7 Flash",
+            api: "google-generative-ai",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.5,
+                output: 7.5,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
         "glm-5": {
             id: "glm-5",
             name: "GLM-5",
@@ -7962,23 +8124,6 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 32000,
         },
-        "ling-3.0-tiny-free": {
-            id: "ling-3.0-tiny-free",
-            name: "Ling-3.0-tiny 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",
@@ -8047,6 +8192,23 @@ export const MODELS = {
             contextWindow: 512000,
             maxTokens: 128000,
         },
+        "muse-spark-1.2": {
+            id: "muse-spark-1.2",
+            name: "Muse Spark 1.2",
+            api: "openai-responses",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.25,
+                output: 4.25,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
         "nemotron-3-ultra-free": {
             id: "nemotron-3-ultra-free",
             name: "Nemotron 3 Ultra Free",
@@ -8185,6 +8347,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 131072,
         },
+        "glm-5.3": {
+            id: "glm-5.3",
+            name: "GLM-5.3",
+            api: "openai-completions",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.4,
+                output: 4.4,
+                cacheRead: 0.26,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
         "gpt-5.6-luna": {
             id: "gpt-5.6-luna",
             name: "GPT-5.6 Luna (2x usage)",
@@ -9323,7 +9502,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 163840,
+            contextWindow: 64000,
             maxTokens: 16000,
         },
         "deepseek/deepseek-r1-0528": {
@@ -9403,13 +9582,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.14,
-                output: 0.28,
-                cacheRead: 0.028,
+                input: 0.06426,
+                output: 0.12852,
+                cacheRead: 0.012852,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 393216,
+            maxTokens: 384000,
         },
         "deepseek/deepseek-v4-flash-0731": {
             id: "deepseek/deepseek-v4-flash-0731",
@@ -9420,13 +9599,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.08,
-                output: 0.18,
-                cacheRead: 0.016,
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.028,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 384000,
+            maxTokens: 393216,
         },
         "deepseek/deepseek-v4-pro": {
             id: "deepseek/deepseek-v4-pro",
@@ -9462,6 +9641,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 384000,
         },
+        "dots-studio/dots-3-note-preview:free": {
+            id: "dots-studio/dots-3-note-preview:free",
+            name: "Dots Studio: Dots3-Note Preview (free)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 512000,
+            maxTokens: 512000,
+        },
         "google/gemini-2.5-flash": {
             id: "google/gemini-2.5-flash",
             name: "Google: Gemini 2.5 Flash",
@@ -9828,10 +10024,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1.5,
-                output: 7.5,
-                cacheRead: 0.15,
-                cacheWrite: 0.0833333333333333,
+                input: 0.75,
+                output: 3.75,
+                cacheRead: 0.075,
+                cacheWrite: 0.0416666666666667,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -9845,10 +10041,44 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.75,
-                output: 3.75,
-                cacheRead: 0.075,
-                cacheWrite: 0.0833333333333333,
+                input: 0.375,
+                output: 1.875,
+                cacheRead: 0.0375,
+                cacheWrite: 0.0416666666666667,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
+        "google/gemini-3.7-flash": {
+            id: "google/gemini-3.7-flash",
+            name: "Google: Gemini 3.7 Flash",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.375,
+                output: 1.875,
+                cacheRead: 0.0375,
+                cacheWrite: 0.0208333333333333,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
+        "google/gemini-3.7-flash:batch": {
+            id: "google/gemini-3.7-flash:batch",
+            name: "Google: Gemini 3.7 Flash (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.1875,
+                output: 0.9375,
+                cacheRead: 0.01875,
+                cacheWrite: 0.0208333333333333,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -10040,23 +10270,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
-        "inclusionai/ling-3.0-tiny:free": {
-            id: "inclusionai/ling-3.0-tiny:free",
-            name: "inclusionAI: Ling 3.0 Tiny (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,
-        },
         "inclusionai/ring-2.6-1t": {
             id: "inclusionai/ring-2.6-1t",
             name: "inclusionAI: Ring-2.6-1T",
@@ -10140,7 +10353,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 32768,
+            maxTokens: 8192,
         },
         "meituan/longcat-2.0": {
             id: "meituan/longcat-2.0",
@@ -10220,12 +10433,12 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.19999999999999998,
-                output: 0.696,
+                output: 0.7999999999999999,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "meta-llama/llama-4-scout": {
             id: "meta-llama/llama-4-scout",
@@ -10763,9 +10976,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.5795,
-                output: 2.44,
-                cacheRead: 0.0976,
+                input: 0.5415,
+                output: 2.2800000000000002,
+                cacheRead: 0.09119999999999999,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -10780,8 +10993,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.67,
-                output: 3.4,
+                input: 0.71,
+                output: 3.5,
                 cacheRead: 0.15,
                 cacheWrite: 0,
             },
@@ -10992,6 +11205,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 65536,
         },
+        "nvidia/nemotron-3.5-lightning": {
+            id: "nvidia/nemotron-3.5-lightning",
+            name: "NVIDIA: Nemotron 3.5 Lightning",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.09999999999999999,
+                output: 0.25,
+                cacheRead: 0.049999999999999996,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 262144,
+        },
         "nvidia/nemotron-3.5-lightning:free": {
             id: "nvidia/nemotron-3.5-lightning:free",
             name: "NVIDIA: Nemotron 3.5 Lightning (free)",
@@ -12735,10 +12965,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.39999999999999997,
-                output: 1.2,
+                input: 0.26,
+                output: 0.78,
                 cacheRead: 0,
-                cacheWrite: 0.5,
+                cacheWrite: 0,
             },
             contextWindow: 1000000,
             maxTokens: 32768,
@@ -13024,13 +13254,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09,
+                input: 0.09999999999999999,
                 output: 1.1,
-                cacheRead: 0,
+                cacheRead: 0.07,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 262144,
         },
         "qwen/qwen3-next-80b-a3b-thinking": {
             id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -13047,7 +13277,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 32768,
         },
         "qwen/qwen3-vl-235b-a22b-instruct": {
             id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -13092,13 +13322,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.15,
-                output: 0.6,
+                input: 0.13,
+                output: 0.52,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 32768,
         },
         "qwen/qwen3-vl-30b-a3b-thinking": {
             id: "qwen/qwen3-vl-30b-a3b-thinking",
@@ -13211,13 +13441,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.14,
-                output: 1,
-                cacheRead: 0,
+                input: 0.22499999999999998,
+                output: 1.7999999999999998,
+                cacheRead: 0.22499999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 65536,
         },
         "qwen/qwen3.5-397b-a17b": {
             id: "qwen/qwen3.5-397b-a17b",
@@ -13228,13 +13458,13 @@ 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",
@@ -13451,11 +13681,28 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0.19999999999999998,
+                cacheRead: 0.25,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 262144,
+        },
+        "qwen/qwen3.8-27b": {
+            id: "qwen/qwen3.8-27b",
+            name: "Qwen: Qwen3.8 27B",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.44999999999999996,
+                output: 3.1999999999999997,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 52429,
+            maxTokens: 131072,
         },
         "qwen/qwen3.8-max": {
             id: "qwen/qwen3.8-max",
@@ -13619,9 +13866,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.063,
-                output: 0.21,
-                cacheRead: 0.020999999999999998,
+                input: 0.18,
+                output: 0.6,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -13976,13 +14223,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.95,
-                output: 2.5500000000000003,
-                cacheRead: 0.19999999999999998,
+                input: 0.6,
+                output: 1.92,
+                cacheRead: 0.12,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
-            maxTokens: 131072,
+            maxTokens: 128000,
         },
         "z-ai/glm-5-turbo": {
             id: "z-ai/glm-5-turbo",
@@ -14010,13 +14257,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.4,
-                output: 4.4,
-                cacheRead: 0.26,
+                input: 0.966,
+                output: 3.036,
+                cacheRead: 0.1794,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
-            maxTokens: 131072,
+            maxTokens: 128000,
         },
         "z-ai/glm-5.2": {
             id: "z-ai/glm-5.2",
@@ -14027,9 +14274,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.49,
-                output: 1.54,
-                cacheRead: 0.091,
+                input: 0.46199999999999997,
+                output: 1.452,
+                cacheRead: 0.0858,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -14146,13 +14393,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.079996,
-                output: 0.252,
-                cacheRead: 0.0252,
+                input: 0.0675,
+                output: 0.135,
+                cacheRead: 0.0135,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 4096,
+            maxTokens: 262144,
         },
         "~google/gemini-flash-latest": {
             id: "~google/gemini-flash-latest",
@@ -14163,10 +14410,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1.5,
-                output: 7.5,
-                cacheRead: 0.15,
-                cacheWrite: 0.0833333333333333,
+                input: 0.375,
+                output: 1.875,
+                cacheRead: 0.0375,
+                cacheWrite: 0.0208333333333333,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -14683,6 +14930,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "alibaba/qwen3.8-2.4t-a95b": {
+            id: "alibaba/qwen3.8-2.4t-a95b",
+            name: "Qwen3.8 2.4T A95B",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 2,
+                output: 6,
+                cacheRead: 0.25,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 131072,
+        },
         "alibaba/qwen3.8-max": {
             id: "alibaba/qwen3.8-max",
             name: "Qwen 3.8 Max",
@@ -15270,9 +15534,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.435,
-                output: 0.87,
-                cacheRead: 0.0036,
+                input: 1.32,
+                output: 3.9600000000000004,
+                cacheRead: 0.13199999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -15431,6 +15695,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "google/gemini-3.7-flash": {
+            id: "google/gemini-3.7-flash",
+            name: "Gemini 3.7 Flash",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.75,
+                output: 3.75,
+                cacheRead: 0.075,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 65536,
+        },
         "google/gemma-4-26b-a4b-it": {
             id: "google/gemma-4-26b-a4b-it",
             name: "Google Gemma 4 26B A4B",
@@ -15462,7 +15743,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
+            contextWindow: 262144,
             maxTokens: 131072,
         },
         "inception/mercury-2": {
@@ -15516,23 +15797,6 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 32000,
         },
-        "inclusionai/ling-3.0-tiny-free": {
-            id: "inclusionai/ling-3.0-tiny-free",
-            name: "Ling 3.0 Tiny (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",
@@ -17342,7 +17606,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 2,
                 output: 6,