@asm-agent/ai 0.8.6 → 0.8.7

package/dist/models.generated.js

@@ -88,6 +88,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "anthropic.claude-fable-5-1": {
+            id: "anthropic.claude-fable-5-1",
+            name: "Claude Fable 5.1",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 10,
+                output: 50,
+                cacheRead: 0.25,
+                cacheWrite: 12.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "anthropic.claude-haiku-4-5-20251001-v1:0": {
             id: "anthropic.claude-haiku-4-5-20251001-v1:0",
             name: "Claude Haiku 4.5",
@@ -634,6 +652,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "global.anthropic.claude-fable-5-1": {
+            id: "global.anthropic.claude-fable-5-1",
+            name: "Claude Fable 5.1 (Global)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 10,
+                output: 50,
+                cacheRead: 0.25,
+                cacheWrite: 12.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "global.anthropic.claude-haiku-4-5-20251001-v1:0": {
             id: "global.anthropic.claude-haiku-4-5-20251001-v1:0",
             name: "Claude Haiku 4.5 (Global)",
@@ -1725,6 +1761,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "us.anthropic.claude-fable-5-1": {
+            id: "us.anthropic.claude-fable-5-1",
+            name: "Claude Fable 5.1 (US)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 11,
+                output: 55,
+                cacheRead: 0.275,
+                cacheWrite: 13.75,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "us.anthropic.claude-haiku-4-5-20251001-v1:0": {
             id: "us.anthropic.claude-haiku-4-5-20251001-v1:0",
             name: "Claude Haiku 4.5 (US)",
@@ -2091,6 +2145,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "claude-fable-5-1": {
+            id: "claude-fable-5-1",
+            name: "Claude Fable 5.1",
+            api: "anthropic-messages",
+            provider: "anthropic",
+            baseUrl: "https://api.anthropic.com",
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 10,
+                output: 50,
+                cacheRead: 0.25,
+                cacheWrite: 12.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "claude-haiku-4-5": {
             id: "claude-haiku-4-5",
             name: "Claude Haiku 4.5 (latest)",
@@ -3988,9 +4060,26 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.14,
-                output: 0.28,
-                cacheRead: 0.028,
+                input: 0.22,
+                output: 0.66,
+                cacheRead: 0.007,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
+        "accounts/fireworks/models/deepseek-v4-flash-vision-exp": {
+            id: "accounts/fireworks/models/deepseek-v4-flash-vision-exp",
+            name: "DeepSeek V4 Flash Vision Exp",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.22,
+                output: 0.66,
+                cacheRead: 0.007,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -4058,7 +4147,7 @@ export const MODELS = {
             cost: {
                 input: 0.15,
                 output: 0.5,
-                cacheRead: 0.029,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -5131,13 +5220,14 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "gemini-flash-latest": {
-            id: "gemini-flash-latest",
-            name: "Gemini Flash Latest",
+        "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,
+            thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
                 input: 0.75,
@@ -5148,38 +5238,38 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "gemini-flash-lite-latest": {
-            id: "gemini-flash-lite-latest",
-            name: "Gemini Flash-Lite Latest",
+        "gemini-flash-latest": {
+            id: "gemini-flash-latest",
+            name: "Gemini Flash Latest",
             api: "google-generative-ai",
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.3,
-                output: 2.5,
-                cacheRead: 0.03,
+                input: 0.75,
+                output: 3.75,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "gemini-robotics-er-1.6-preview": {
-            id: "gemini-robotics-er-1.6-preview",
-            name: "Gemini Robotics-ER 1.6 Preview",
+        "gemini-flash-lite-latest": {
+            id: "gemini-flash-lite-latest",
+            name: "Gemini Flash-Lite Latest",
             api: "google-generative-ai",
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 5,
-                cacheRead: 0,
+                input: 0.3,
+                output: 2.5,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 1048576,
             maxTokens: 65536,
         },
         "gemma-4-26b-a4b-it": {
@@ -5549,6 +5639,23 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 16384,
         },
+        "qwen/qwen3.8-27b": {
+            id: "qwen/qwen3.8-27b",
+            name: "Qwen3.8 27B",
+            api: "openai-completions",
+            provider: "groq",
+            baseUrl: "https://api.groq.com/openai/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.8,
+                output: 4,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131042,
+            maxTokens: 16384,
+        },
     },
     "huggingface": {
         "MiniMaxAI/MiniMax-M2": {
@@ -6235,6 +6342,24 @@ 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",
@@ -6558,7 +6683,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 64000,
+            maxTokens: 128000,
         },
         "thinkingmachines/Inkling": {
             id: "thinkingmachines/Inkling",
@@ -8866,6 +8991,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "claude-fable-5-1": {
+            id: "claude-fable-5-1",
+            name: "Claude Fable 5.1",
+            api: "anthropic-messages",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen",
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 10,
+                output: 50,
+                cacheRead: 0.25,
+                cacheWrite: 12.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "claude-haiku-4-5": {
             id: "claude-haiku-4-5",
             name: "Claude Haiku 4.5",
@@ -9188,6 +9331,24 @@ 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,
+            thinkingLevelMap: { "off": null },
+            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",
@@ -9820,6 +9981,23 @@ 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",
@@ -10065,7 +10243,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 256000,
-            maxTokens: 64000,
+            maxTokens: 128000,
         },
         "hy4-preview": {
             id: "hy4-preview",
@@ -10238,6 +10416,23 @@ 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,
+        },
         "qwen3.6-plus": {
             id: "qwen3.6-plus",
             name: "Qwen3.6 Plus",
@@ -10505,6 +10700,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "anthropic/claude-fable-5.1": {
+            id: "anthropic/claude-fable-5.1",
+            name: "Anthropic: Claude Fable 5.1",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 10,
+                output: 50,
+                cacheRead: 0.25,
+                cacheWrite: 12.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "anthropic/claude-haiku-4.5": {
             id: "anthropic/claude-haiku-4.5",
             name: "Anthropic: Claude Haiku 4.5",
@@ -10617,24 +10830,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "anthropic/claude-opus-4.7-fast": {
-            id: "anthropic/claude-opus-4.7-fast",
-            name: "Anthropic: Claude Opus 4.7 (Fast)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            thinkingLevelMap: { "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
-            input: ["text", "image"],
-            cost: {
-                input: 30,
-                output: 150,
-                cacheRead: 3,
-                cacheWrite: 37.5,
-            },
-            contextWindow: 1000000,
-            maxTokens: 128000,
-        },
         "anthropic/claude-opus-4.8": {
             id: "anthropic/claude-opus-4.8",
             name: "Anthropic: Claude Opus 4.8",
@@ -10653,24 +10848,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "anthropic/claude-opus-4.8-fast": {
-            id: "anthropic/claude-opus-4.8-fast",
-            name: "Anthropic: Claude Opus 4.8 (Fast)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            thinkingLevelMap: { "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
-            input: ["text", "image"],
-            cost: {
-                input: 10,
-                output: 50,
-                cacheRead: 1,
-                cacheWrite: 12.5,
-            },
-            contextWindow: 1000000,
-            maxTokens: 128000,
-        },
         "anthropic/claude-opus-5": {
             id: "anthropic/claude-opus-5",
             name: "Claude Opus 5",
@@ -10689,33 +10866,15 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "anthropic/claude-opus-5-fast": {
-            id: "anthropic/claude-opus-5-fast",
-            name: "Claude Opus 5 (Fast)",
+        "anthropic/claude-sonnet-4": {
+            id: "anthropic/claude-sonnet-4",
+            name: "Anthropic: Claude Sonnet 4",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
+            compat: { "supportsReasoningEffort": false },
             reasoning: true,
-            thinkingLevelMap: { "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": "max" },
-            input: ["text", "image"],
-            cost: {
-                input: 10,
-                output: 50,
-                cacheRead: 1,
-                cacheWrite: 12.5,
-            },
-            contextWindow: 1000000,
-            maxTokens: 128000,
-        },
-        "anthropic/claude-sonnet-4": {
-            id: "anthropic/claude-sonnet-4",
-            name: "Anthropic: Claude Sonnet 4",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            compat: { "supportsReasoningEffort": false },
-            reasoning: true,
-            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null, "max": null },
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null, "max": null },
             input: ["text", "image"],
             cost: {
                 input: 3,
@@ -10990,13 +11149,13 @@ 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",
@@ -11026,13 +11185,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null, "max": null },
             input: ["text"],
             cost: {
-                input: 0.55,
-                output: 1.6500000000000001,
-                cacheRead: 0.55,
+                input: 0.25,
+                output: 0.95,
+                cacheRead: 0.13,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 144900,
+            maxTokens: 32768,
         },
         "deepseek/deepseek-r1": {
             id: "deepseek/deepseek-r1",
@@ -11140,9 +11299,9 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max", "max": null },
             input: ["text"],
             cost: {
-                input: 0.088606,
-                output: 0.177212,
-                cacheRead: 0.017721200000000003,
+                input: 0.08553999999999999,
+                output: 0.17107999999999998,
+                cacheRead: 0.017108,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -11178,9 +11337,9 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max", "max": null },
             input: ["text", "image"],
             cost: {
-                input: 0.44,
-                output: 1.32,
-                cacheRead: 0.014,
+                input: 0.22,
+                output: 0.66,
+                cacheRead: 0.007,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -11197,13 +11356,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max", "max": null },
             input: ["text"],
             cost: {
-                input: 1.5999999999999999,
-                output: 3.1999999999999997,
-                cacheRead: 0.135,
+                input: 1.035996,
+                output: 2.071992,
+                cacheRead: 0.086333,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 393216,
+            maxTokens: 384000,
         },
         "deepseek/deepseek-v4-pro-0813": {
             id: "deepseek/deepseek-v4-pro-0813",
@@ -11216,9 +11375,9 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max", "max": null },
             input: ["text"],
             cost: {
-                input: 1.32,
-                output: 3.9600000000000004,
-                cacheRead: 0.044,
+                input: 0.66,
+                output: 1.9800000000000002,
+                cacheRead: 0.022,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -11519,6 +11678,24 @@ export const MODELS = {
             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,
+            thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": null, "max": null },
+            input: ["text", "image"],
+            cost: {
+                input: 0.75,
+                output: 3.75,
+                cacheRead: 0.075,
+                cacheWrite: 0.0416666666666667,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
         "google/gemma-3-12b-it": {
             id: "google/gemma-3-12b-it",
             name: "Google: Gemma 3 12B",
@@ -11646,6 +11823,24 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 117964,
         },
+        "ibm-granite/granite-4.2-8b": {
+            id: "ibm-granite/granite-4.2-8b",
+            name: "IBM: Granite 4.2 8B",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": null },
+            input: ["text"],
+            cost: {
+                input: 0.09999999999999999,
+                output: 0.15,
+                cacheRead: 0.049999999999999996,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 117964,
+        },
         "inception/mercury-2": {
             id: "inception/mercury-2",
             name: "Inception: Mercury 2",
@@ -11664,6 +11859,24 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 50000,
         },
+        "inception/mercury-2.5-preview": {
+            id: "inception/mercury-2.5-preview",
+            name: "Inception: Mercury 2.5 Preview",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": "low", "medium": "medium", "high": "high", "xhigh": null, "max": null },
+            input: ["text"],
+            cost: {
+                input: 0.04,
+                output: 0.15,
+                cacheRead: 0.004,
+                cacheWrite: 0,
+            },
+            contextWindow: 260000,
+            maxTokens: 65536,
+        },
         "inclusionai/ling-3.0-flash": {
             id: "inclusionai/ling-3.0-flash",
             name: "Ling-3.0-flash",
@@ -11702,23 +11915,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
-        "kwaipilot/kat-coder-air-v2.5": {
-            id: "kwaipilot/kat-coder-air-v2.5",
-            name: "Kwaipilot: KAT-Coder-Air V2.5",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0.03,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 80000,
-        },
         "kwaipilot/kat-coder-pro-v2": {
             id: "kwaipilot/kat-coder-pro-v2",
             name: "Kwaipilot: KAT-Coder-Pro V2",
@@ -11734,7 +11930,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 80000,
+            maxTokens: 144000,
         },
         "kwaipilot/kat-coder-pro-v2.5": {
             id: "kwaipilot/kat-coder-pro-v2.5",
@@ -11751,7 +11947,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 80000,
+            maxTokens: 235929,
         },
         "liquid/lfm-2.5-2.6b:free": {
             id: "liquid/lfm-2.5-2.6b:free",
@@ -11834,13 +12030,13 @@ 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",
@@ -11868,13 +12064,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.11,
-                output: 0.33999999999999997,
-                cacheRead: 0.055,
+                input: 0.09999999999999999,
+                output: 0.3,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
-            maxTokens: 8192,
+            maxTokens: 16384,
         },
         "meta/muse-glimmer-30b": {
             id: "meta/muse-glimmer-30b",
@@ -11887,12 +12083,12 @@ 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-spark-1.1": {
             id: "meta/muse-spark-1.1",
@@ -11948,6 +12144,42 @@ 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,
+            thinkingLevelMap: { "off": null, "minimal": "minimal", "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": null },
+            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,
+            thinkingLevelMap: { "off": null, "minimal": "minimal", "low": "low", "medium": "medium", "high": "high", "xhigh": "xhigh", "max": null },
+            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",
@@ -12570,11 +12802,11 @@ 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",
@@ -12641,13 +12873,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": "medium", "high": "high", "xhigh": null, "max": null },
             input: ["text"],
             cost: {
-                input: 0.5,
-                output: 2.2,
-                cacheRead: 0.09999999999999999,
+                input: 0.6,
+                output: 2.4,
+                cacheRead: 0.12,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 182520,
         },
         "nvidia/nemotron-3-ultra-550b-a55b:free": {
             id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -14139,13 +14371,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09,
+                input: 0.09999999999999999,
                 output: 1.1,
-                cacheRead: 0,
+                cacheRead: 0.07,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 235929,
         },
         "qwen/qwen3-next-80b-a3b-thinking": {
             id: "qwen/qwen3-next-80b-a3b-thinking",
@@ -14359,13 +14591,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null, "max": null },
             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",
@@ -15171,13 +15403,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null, "max": null },
             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",
@@ -15303,13 +15535,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh", "max": null },
             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",
@@ -15341,11 +15573,11 @@ 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",
@@ -15396,7 +15628,7 @@ export const MODELS = {
             cost: {
                 input: 10,
                 output: 50,
-                cacheRead: 1,
+                cacheRead: 0.25,
                 cacheWrite: 12.5,
             },
             contextWindow: 1000000,
@@ -15468,7 +15700,7 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max", "max": null },
             input: ["text"],
             cost: {
-                input: 0.03,
+                input: 0.049999999999999996,
                 output: 0.16,
                 cacheRead: 0.013000000000000001,
                 cacheWrite: 0,
@@ -15584,6 +15816,24 @@ 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,
+            thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max" },
+            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",
@@ -15594,13 +15844,13 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "minimal": null, "low": "low", "medium": null, "high": "high", "xhigh": null, "max": "max" },
             input: ["text"],
             cost: {
-                input: 1.1875,
-                output: 4.18,
-                cacheRead: 0.24699999999999997,
+                input: 1.1340000000000001,
+                output: 3.564,
+                cacheRead: 0.1863,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
-            maxTokens: 131072,
+            maxTokens: 943718,
         },
     },
     "prime-inference": {
@@ -15856,7 +16106,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 16000,
+            maxTokens: 16384,
         },
         "deepseek/deepseek-chat-v3-0324": {
             id: "deepseek/deepseek-chat-v3-0324",
@@ -15893,7 +16143,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 144900,
+            maxTokens: 32768,
         },
         "deepseek/deepseek-v3.1-terminus": {
             id: "deepseek/deepseek-v3.1-terminus",
@@ -16009,7 +16259,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 393216,
+            maxTokens: 384000,
             featured: true,
         },
         "google/gemini-2.5-flash": {
@@ -16234,7 +16484,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 115200,
+            maxTokens: 16384,
         },
         "meta-llama/llama-4-maverick": {
             id: "meta-llama/llama-4-maverick",
@@ -16517,7 +16767,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 228000,
+            maxTokens: 235929,
             featured: true,
         },
         "nvidia/nemotron-3-super-120b-a12b": {
@@ -17525,7 +17775,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 204800,
-            maxTokens: 16384,
+            maxTokens: 131072,
         },
         "z-ai/glm-4.7": {
             id: "z-ai/glm-4.7",
@@ -17622,7 +17872,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 262144,
+            maxTokens: 131072,
             featured: true,
         },
         "z-ai/glm-5.3": {
@@ -17642,7 +17892,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
-            maxTokens: 131072,
+            maxTokens: 262144,
         },
         "z-ai/glm-5.3-flash": {
             id: "z-ai/glm-5.3-flash",
@@ -18141,6 +18391,23 @@ export const MODELS = {
             contextWindow: 991000,
             maxTokens: 128000,
         },
+        "alibaba/qwen3.8-flash-next": {
+            id: "alibaba/qwen3.8-flash-next",
+            name: "Qwen 3.8 Flash Next",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.12,
+                output: 0.39999999999999997,
+                cacheRead: 0.01,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 1048576,
+        },
         "alibaba/qwen3.8-max": {
             id: "alibaba/qwen3.8-max",
             name: "Qwen 3.8 Max",
@@ -18158,6 +18425,23 @@ 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",
@@ -18261,6 +18545,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "anthropic/claude-fable-5.1": {
+            id: "anthropic/claude-fable-5.1",
+            name: "Claude Fable 5.1",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "xhigh": "xhigh", "max": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 10,
+                output: 50,
+                cacheRead: 0.25,
+                cacheWrite: 12.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "anthropic/claude-haiku-4.5": {
             id: "anthropic/claude-haiku-4.5",
             name: "Claude Haiku 4.5",
@@ -18575,23 +18877,6 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 8192,
         },
-        "deepseek/deepseek-v3": {
-            id: "deepseek/deepseek-v3",
-            name: "DeepSeek V3 0324",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.27,
-                output: 1.12,
-                cacheRead: 0.135,
-                cacheWrite: 0,
-            },
-            contextWindow: 163840,
-            maxTokens: 163840,
-        },
         "deepseek/deepseek-v3.1": {
             id: "deepseek/deepseek-v3.1",
             name: "DeepSeek V3.1",
@@ -18708,8 +18993,8 @@ export const MODELS = {
                 cacheRead: 0.007,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 384000,
+            contextWindow: 1048576,
+            maxTokens: 1048576,
         },
         "deepseek/deepseek-v4-pro": {
             id: "deepseek/deepseek-v4-pro",
@@ -18915,6 +19200,23 @@ 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",
@@ -19272,6 +19574,40 @@ 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",
@@ -21267,6 +21603,23 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 131000,
         },
+        "xiaomi/mimo-v2.5-pro-ultraspeed": {
+            id: "xiaomi/mimo-v2.5-pro-ultraspeed",
+            name: "MiMo V2.5 Pro UltraSpeed",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.305,
+                output: 2.61,
+                cacheRead: 0.0108,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
         "zai/glm-4.5": {
             id: "zai/glm-4.5",
             name: "GLM 4.5",
@@ -21480,14 +21833,31 @@ 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",
@@ -21505,6 +21875,23 @@ 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",