@dreb/ai 2.64.1 → 2.64.3

package/dist/models.generated.js

@@ -3072,27 +3072,28 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "claude-haiku-4.5": {
-            id: "claude-haiku-4.5",
-            name: "Claude Haiku 4.5 (latest)",
-            api: "anthropic-messages",
+        "claude-fable-5.1": {
+            id: "claude-fable-5.1",
+            name: "Claude Fable 5.1",
+            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: 1,
-                output: 5,
-                cacheRead: 0.1,
-                cacheWrite: 1.25,
+                input: 10,
+                output: 50,
+                cacheRead: 0.25,
+                cacheWrite: 12.5,
             },
-            contextWindow: 200000,
-            maxTokens: 64000,
+            contextWindow: 1000000,
+            maxTokens: 128000,
         },
-        "claude-opus-4.5": {
-            id: "claude-opus-4.5",
-            name: "Claude Opus 4.5 (latest)",
+        "claude-haiku-4.5": {
+            id: "claude-haiku-4.5",
+            name: "Claude Haiku 4.5 (latest)",
             api: "anthropic-messages",
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
@@ -3100,31 +3101,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 25,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 1,
+                output: 5,
+                cacheRead: 0.1,
+                cacheWrite: 1.25,
             },
             contextWindow: 200000,
-            maxTokens: 32000,
-        },
-        "claude-opus-4.6": {
-            id: "claude-opus-4.6",
-            name: "Claude Opus 4.6",
-            api: "anthropic-messages",
-            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" },
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 5,
-                output: 25,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
-            },
-            contextWindow: 1000000,
-            maxTokens: 32000,
+            maxTokens: 64000,
         },
         "claude-opus-4.7": {
             id: "claude-opus-4.7",
@@ -3181,42 +3164,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
-        "claude-sonnet-4": {
-            id: "claude-sonnet-4",
-            name: "Claude Sonnet 4 (latest)",
-            api: "anthropic-messages",
-            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" },
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
-            },
-            contextWindow: 216000,
-            maxTokens: 16000,
-        },
-        "claude-sonnet-4.5": {
-            id: "claude-sonnet-4.5",
-            name: "Claude Sonnet 4.5 (latest)",
-            api: "anthropic-messages",
-            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" },
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 32000,
-        },
         "claude-sonnet-4.6": {
             id: "claude-sonnet-4.6",
             name: "Claude Sonnet 4.6",
@@ -3254,25 +3201,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "gemini-3.1-pro-preview": {
-            id: "gemini-3.1-pro-preview",
-            name: "Gemini 3.1 Pro Preview",
-            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: 12,
-                cacheRead: 0.2,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 64000,
-        },
         "gemini-3.5-flash": {
             id: "gemini-3.5-flash",
             name: "Gemini 3.5 Flash",
@@ -3330,24 +3258,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
-        "gpt-4.1": {
-            id: "gpt-4.1",
-            name: "GPT-4.1",
+        "gemini-3.8-flash": {
+            id: "gemini-3.8-flash",
+            name: "Gemini 3.8 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: false,
+            reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 8,
-                cacheRead: 0.5,
+                input: 0.75,
+                output: 3.75,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 16384,
+            contextWindow: 1000000,
+            maxTokens: 64000,
         },
         "gpt-5-mini": {
             id: "gpt-5-mini",
@@ -3367,42 +3295,6 @@ export const MODELS = {
             contextWindow: 264000,
             maxTokens: 64000,
         },
-        "gpt-5.2": {
-            id: "gpt-5.2",
-            name: "GPT-5.2",
-            api: "openai-responses",
-            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" },
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1.75,
-                output: 14,
-                cacheRead: 0.175,
-                cacheWrite: 0,
-            },
-            contextWindow: 400000,
-            maxTokens: 128000,
-        },
-        "gpt-5.2-codex": {
-            id: "gpt-5.2-codex",
-            name: "GPT-5.2 Codex",
-            api: "openai-responses",
-            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" },
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1.75,
-                output: 14,
-                cacheRead: 0.175,
-                cacheWrite: 0,
-            },
-            contextWindow: 400000,
-            maxTokens: 128000,
-        },
         "gpt-5.3-codex": {
             id: "gpt-5.3-codex",
             name: "GPT-5.3 Codex",
@@ -3521,10 +3413,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 0.2,
-                cacheWrite: 2.5,
+                input: 4,
+                output: 20,
+                cacheRead: 0.4,
+                cacheWrite: 5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -3952,6 +3844,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
+        "gemini-3.8-flash": {
+            id: "gemini-3.8-flash",
+            name: "Gemini 3.8 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",
@@ -5292,6 +5201,24 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 384000,
         },
+        "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp": {
+            id: "deepseek-ai/DeepSeek-V4-Flash-Vision-Exp",
+            name: "DeepSeek V4 Flash Vision Exp",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.44,
+                output: 1.32,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 384000,
+        },
         "deepseek-ai/DeepSeek-V4-Pro": {
             id: "deepseek-ai/DeepSeek-V4-Pro",
             name: "DeepSeek V4 Pro",
@@ -5614,7 +5541,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 64000,
+            maxTokens: 128000,
         },
         "thinkingmachines/Inkling": {
             id: "thinkingmachines/Inkling",
@@ -7876,6 +7803,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
+        "gemini-3.8-flash": {
+            id: "gemini-3.8-flash",
+            name: "Gemini 3.8 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",
@@ -8488,6 +8432,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 131072,
         },
+        "muse-spark-1.3-contributor-free": {
+            id: "muse-spark-1.3-contributor-free",
+            name: "Muse Spark 1.3 Free",
+            api: "openai-responses",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
         "nemotron-3-ultra-free": {
             id: "nemotron-3-ultra-free",
             name: "Nemotron 3 Ultra Free",
@@ -8726,7 +8687,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 256000,
-            maxTokens: 64000,
+            maxTokens: 128000,
         },
         "hy4-preview": {
             id: "hy4-preview",
@@ -8898,6 +8859,40 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 131072,
         },
+        "muse-spark-1.3-contributor": {
+            id: "muse-spark-1.3-contributor",
+            name: "Muse Spark 1.3 Contributor",
+            api: "openai-responses",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.1,
+                output: 0.2,
+                cacheRead: 0.002,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
+        "omen-alpha": {
+            id: "omen-alpha",
+            name: "Omen Alpha",
+            api: "openai-completions",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.2,
+                output: 0.66,
+                cacheRead: 0.04,
+                cacheWrite: 0,
+            },
+            contextWindow: 500000,
+            maxTokens: 128000,
+        },
         "qwen3.6-plus": {
             id: "qwen3.6-plus",
             name: "Qwen3.6 Plus",
@@ -9172,6 +9167,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "anthropic/claude-fable-5.1:batch": {
+            id: "anthropic/claude-fable-5.1:batch",
+            name: "Anthropic: Claude Fable 5.1 (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.125,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "anthropic/claude-fable-5:batch": {
             id: "anthropic/claude-fable-5:batch",
             name: "Anthropic: Claude Fable 5 (batch)",
@@ -9759,13 +9771,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.2574,
-                output: 1.0287,
+                input: 0.32,
+                output: 0.8899999999999999,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 16000,
+            maxTokens: 16384,
         },
         "deepseek/deepseek-chat-v3-0324": {
             id: "deepseek/deepseek-chat-v3-0324",
@@ -9895,9 +9907,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.07168000000000001,
-                output: 0.14336000000000002,
-                cacheRead: 0.014336,
+                input: 0.0875,
+                output: 0.175,
+                cacheRead: 0.0175,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -9963,9 +9975,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.0274699999999999,
-                output: 2.0549399999999998,
-                cacheRead: 0.0856225,
+                input: 0.9918,
+                output: 1.9836,
+                cacheRead: 0.08265,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -9980,9 +9992,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.66,
-                output: 1.9800000000000002,
-                cacheRead: 0.022,
+                input: 0.57948,
+                output: 1.73844,
+                cacheRead: 0.019316,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -10439,10 +10451,44 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.1875,
-                output: 0.9375,
-                cacheRead: 0.01875,
-                cacheWrite: 0.0208333333333333,
+                input: 0.375,
+                output: 1.875,
+                cacheRead: 0.0375,
+                cacheWrite: 0.0416666666666667,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
+        "google/gemini-3.8-flash": {
+            id: "google/gemini-3.8-flash",
+            name: "Google: Gemini 3.8 Flash",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.75,
+                output: 3.75,
+                cacheRead: 0.075,
+                cacheWrite: 0.0416666666666667,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
+        "google/gemini-3.8-flash:batch": {
+            id: "google/gemini-3.8-flash:batch",
+            name: "Google: Gemini 3.8 Flash (batch)",
+            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: 0.0416666666666667,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -10566,23 +10612,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
-        "ibm-granite/granite-4.1-8b": {
-            id: "ibm-granite/granite-4.1-8b",
-            name: "IBM: Granite 4.1 8B",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.049999999999999996,
-                output: 0.09999999999999999,
-                cacheRead: 0.049999999999999996,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 117964,
-        },
         "ibm-granite/granite-4.2-8b": {
             id: "ibm-granite/granite-4.2-8b",
             name: "IBM: Granite 4.2 8B",
@@ -10636,7 +10665,7 @@ export const MODELS = {
         },
         "inclusionai/ling-3.0-flash": {
             id: "inclusionai/ling-3.0-flash",
-            name: "Ling-3.0-flash",
+            name: "inclusionAI: Ling 3.0 Flash",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
@@ -10651,9 +10680,43 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
+        "inclusionai/ling-3.0-flash-fin": {
+            id: "inclusionai/ling-3.0-flash-fin",
+            name: "inclusionAI: Ling 3.0 Flash Fin",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.06,
+                output: 0.18,
+                cacheRead: 0.012,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 235929,
+        },
         "inclusionai/ling-3.0-flash-fin:free": {
             id: "inclusionai/ling-3.0-flash-fin:free",
-            name: "Ling 3.0 Flash Fin (free)",
+            name: "inclusionAI: 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,
+        },
+        "inclusionai/ling-3.0-flash-sante:free": {
+            id: "inclusionai/ling-3.0-flash-sante:free",
+            name: "inclusionAI: Ling 3.0 Flash Sante (free)",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
@@ -10779,13 +10842,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.71,
-                output: 0.71,
-                cacheRead: 0.71,
+                input: 0.09999999999999999,
+                output: 0.32,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 115200,
+            maxTokens: 16384,
         },
         "meta-llama/llama-4-maverick": {
             id: "meta-llama/llama-4-maverick",
@@ -10831,12 +10894,12 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.3,
-                output: 1.2,
+                output: 1.1,
                 cacheRead: 0.04,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 16384,
+            maxTokens: 117964,
         },
         "meta/muse-glimmer-30b:batch": {
             id: "meta/muse-glimmer-30b:batch",
@@ -10906,6 +10969,40 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 943718,
         },
+        "meta/muse-spark-1.3": {
+            id: "meta/muse-spark-1.3",
+            name: "Meta: Muse Spark 1.3",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.25,
+                output: 4.25,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 943718,
+        },
+        "meta/muse-spark-1.3-contributor": {
+            id: "meta/muse-spark-1.3-contributor",
+            name: "Meta: Muse Spark 1.3 Contributor",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.09999999999999999,
+                output: 0.19999999999999998,
+                cacheRead: 0.002,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 943718,
+        },
         "minimax/minimax-m1": {
             id: "minimax/minimax-m1",
             name: "MiniMax: MiniMax M1",
@@ -11243,8 +11340,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 209715,
+            contextWindow: 32768,
+            maxTokens: 26214,
         },
         "mistralai/mistral-medium-3.1": {
             id: "mistralai/mistral-medium-3.1",
@@ -11546,11 +11643,11 @@ export const MODELS = {
             cost: {
                 input: 0.049999999999999996,
                 output: 0.19999999999999998,
-                cacheRead: 0.024999999999999998,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 228000,
+            maxTokens: 235929,
         },
         "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": {
             id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
@@ -11612,30 +11709,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.5,
-                output: 2.2,
-                cacheRead: 0.09999999999999999,
+                input: 0.625,
+                output: 3.125,
+                cacheRead: 0.1875,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
-        },
-        "nvidia/nemotron-3-ultra-550b-a55b:batch": {
-            id: "nvidia/nemotron-3-ultra-550b-a55b:batch",
-            name: "NVIDIA: Nemotron 3 Ultra (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.6,
-                output: 3.5999999999999996,
-                cacheRead: 0.19999999999999998,
-                cacheWrite: 0,
-            },
-            contextWindow: 512288,
-            maxTokens: 461059,
+            maxTokens: 32768,
         },
         "nvidia/nemotron-3-ultra-550b-a55b:free": {
             id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -13754,13 +13834,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.25,
-                output: 1.25,
-                cacheRead: 0.25,
+                input: 0.08,
+                output: 0.75,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 235929,
+            maxTokens: 16384,
         },
         "qwen/qwen3.5-397b-a17b": {
             id: "qwen/qwen3.5-397b-a17b",
@@ -13771,13 +13851,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.39,
-                output: 2.34,
-                cacheRead: 0,
+                input: 0.55,
+                output: 3.5,
+                cacheRead: 0.22499999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 65536,
+            maxTokens: 235929,
         },
         "qwen/qwen3.5-9b": {
             id: "qwen/qwen3.5-9b",
@@ -13873,13 +13953,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.6,
-                output: 3.5999999999999996,
-                cacheRead: 0.12,
+                input: 0.3,
+                output: 2,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 235929,
+            maxTokens: 65536,
         },
         "qwen/qwen3.6-35b-a3b": {
             id: "qwen/qwen3.6-35b-a3b",
@@ -14026,9 +14106,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 2.5,
-                output: 6.25,
-                cacheRead: 0.5,
+                input: 2,
+                output: 6,
+                cacheRead: 0.25,
                 cacheWrite: 0,
             },
             contextWindow: 1010000,
@@ -14043,10 +14123,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.425,
-                output: 2.5500000000000003,
+                input: 0.42,
+                output: 3,
                 cacheRead: 0.08499999999999999,
-                cacheWrite: 0.53125,
+                cacheWrite: 0,
             },
             contextWindow: 1000000,
             maxTokens: 131072,
@@ -14442,6 +14522,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 900000,
         },
+        "x-ai/grok-4.3:batch": {
+            id: "x-ai/grok-4.3:batch",
+            name: "SpaceXAI: Grok 4.3 (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1,
+                output: 2,
+                cacheRead: 0.16,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 900000,
+        },
         "x-ai/grok-4.5": {
             id: "x-ai/grok-4.5",
             name: "SpaceXAI: Grok 4.5",
@@ -14587,13 +14684,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.43,
-                output: 1.75,
-                cacheRead: 0.08,
+                input: 0.55,
+                output: 2.2,
+                cacheRead: 0.11,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
-            maxTokens: 16384,
+            maxTokens: 131072,
         },
         "z-ai/glm-4.6v": {
             id: "z-ai/glm-4.6v",
@@ -14706,13 +14803,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.19,
-                output: 3.74,
-                cacheRead: 0.221,
+                input: 0.966,
+                output: 3.036,
+                cacheRead: 0.1932,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 262144,
+            maxTokens: 131072,
         },
         "z-ai/glm-5.2:free": {
             id: "z-ai/glm-5.2:free",
@@ -14742,11 +14839,11 @@ export const MODELS = {
             cost: {
                 input: 1.4,
                 output: 4.4,
-                cacheRead: 0.26,
+                cacheRead: 0.14,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
-            maxTokens: 131072,
+            maxTokens: 262144,
         },
         "z-ai/glm-5.3-flash": {
             id: "z-ai/glm-5.3-flash",
@@ -14927,9 +15024,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2.5500000000000003,
-                output: 12.75,
-                cacheRead: 0.25599998999999996,
+                input: 2.5,
+                output: 14,
+                cacheRead: 0.29,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -14986,6 +15083,23 @@ export const MODELS = {
             contextWindow: 500000,
             maxTokens: 450000,
         },
+        "~z-ai/glm-flash-latest": {
+            id: "~z-ai/glm-flash-latest",
+            name: "Z.ai: GLM Flash Latest",
+            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: 943718,
+        },
         "~z-ai/glm-latest": {
             id: "~z-ai/glm-latest",
             name: "Z.ai: GLM Latest",
@@ -14995,13 +15109,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.17,
-                output: 3.9600000000000004,
-                cacheRead: 0.234,
+                input: 1.15,
+                output: 3.5,
+                cacheRead: 0.09999999999999999,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
-            maxTokens: 943718,
+            maxTokens: 235929,
         },
     },
     "vercel-ai-gateway": {
@@ -15515,6 +15629,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "alibaba/qwen3.8-max-0902": {
+            id: "alibaba/qwen3.8-max-0902",
+            name: "Qwen3.8 Max 0902",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 6,
+                cacheRead: 0.25,
+                cacheWrite: 2.5,
+            },
+            contextWindow: 991000,
+            maxTokens: 128000,
+        },
         "amazon/nova-2-lite": {
             id: "amazon/nova-2-lite",
             name: "Nova 2 Lite",
@@ -16263,6 +16394,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 65536,
         },
+        "google/gemini-3.8-flash": {
+            id: "google/gemini-3.8-flash",
+            name: "Gemini 3.8 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",
@@ -16382,6 +16530,40 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 32000,
         },
+        "inclusionai/ling-3.0-flash-sante": {
+            id: "inclusionai/ling-3.0-flash-sante",
+            name: "Ling 3.0 Flash Sante",
+            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-sante-free": {
+            id: "inclusionai/ling-3.0-flash-sante-free",
+            name: "Ling 3.0 Flash Sante (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",
@@ -16620,6 +16802,40 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 1048576,
         },
+        "meta/muse-spark-1.3": {
+            id: "meta/muse-spark-1.3",
+            name: "Muse Spark 1.3",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.25,
+                output: 4.25,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 1048576,
+        },
+        "meta/muse-spark-1.3-contributor": {
+            id: "meta/muse-spark-1.3-contributor",
+            name: "Muse Spark 1.3 Contributor",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.09999999999999999,
+                output: 0.19999999999999998,
+                cacheRead: 0.002,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 1048576,
+        },
         "minimax/minimax-m2": {
             id: "minimax/minimax-m2",
             name: "MiniMax M2",
@@ -18822,14 +19038,31 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.4,
-                output: 4.4,
-                cacheRead: 0.14,
+                input: 0.7,
+                output: 2.2,
+                cacheRead: 0.13,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
             maxTokens: 1000000,
         },
+        "zai/glm-5.3-fast": {
+            id: "zai/glm-5.3-fast",
+            name: "GLM 5.3 Fast",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 2.0999999999999996,
+                output: 6.6000000000000005,
+                cacheRead: 0.21,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 262144,
+        },
         "zai/glm-5.3-flash": {
             id: "zai/glm-5.3-flash",
             name: "GLM 5.3 Flash",
@@ -18847,6 +19080,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 131000,
         },
+        "zai/glm-5.3-promo-50": {
+            id: "zai/glm-5.3-promo-50",
+            name: "GLM 5.3 (50% off)",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.7,
+                output: 2.2,
+                cacheRead: 0.13,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 1048576,
+        },
         "zai/glm-5v-turbo": {
             id: "zai/glm-5v-turbo",
             name: "GLM 5V Turbo",