@kolisachint/hoocode-ai 0.2.4 → 0.2.6

package/dist/models.generated.js

@@ -157,6 +157,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "anthropic.claude-opus-4-8": {
+            id: "anthropic.claude-opus-4-8",
+            name: "Claude Opus 4.8",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "anthropic.claude-sonnet-4-5-20250929-v1:0": {
             id: "anthropic.claude-sonnet-4-5-20250929-v1:0",
             name: "Claude Sonnet 4.5",
@@ -226,6 +243,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "au.anthropic.claude-opus-4-8": {
+            id: "au.anthropic.claude-opus-4-8",
+            name: "Claude Opus 4.8 (AU)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "au.anthropic.claude-sonnet-4-5-20250929-v1:0": {
             id: "au.anthropic.claude-sonnet-4-5-20250929-v1:0",
             name: "Claude Sonnet 4.5 (AU)",
@@ -381,6 +415,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "eu.anthropic.claude-opus-4-8": {
+            id: "eu.anthropic.claude-opus-4-8",
+            name: "Claude Opus 4.8 (EU)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "eu.anthropic.claude-sonnet-4-5-20250929-v1:0": {
             id: "eu.anthropic.claude-sonnet-4-5-20250929-v1:0",
             name: "Claude Sonnet 4.5 (EU)",
@@ -485,6 +536,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "global.anthropic.claude-opus-4-8": {
+            id: "global.anthropic.claude-opus-4-8",
+            name: "Claude Opus 4.8 (Global)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "global.anthropic.claude-sonnet-4-5-20250929-v1:0": {
             id: "global.anthropic.claude-sonnet-4-5-20250929-v1:0",
             name: "Claude Sonnet 4.5 (Global)",
@@ -571,6 +639,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "jp.anthropic.claude-opus-4-8": {
+            id: "jp.anthropic.claude-opus-4-8",
+            name: "Claude Opus 4.8 (JP)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "jp.anthropic.claude-sonnet-4-5-20250929-v1:0": {
             id: "jp.anthropic.claude-sonnet-4-5-20250929-v1:0",
             name: "Claude Sonnet 4.5 (JP)",
@@ -908,8 +993,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 256000,
+            contextWindow: 262143,
+            maxTokens: 16000,
         },
         "moonshotai.kimi-k2.5": {
             id: "moonshotai.kimi-k2.5",
@@ -925,8 +1010,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 256000,
+            contextWindow: 262143,
+            maxTokens: 16000,
         },
         "nvidia.nemotron-nano-12b-v2": {
             id: "nvidia.nemotron-nano-12b-v2",
@@ -1270,6 +1355,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "us.anthropic.claude-opus-4-8": {
+            id: "us.anthropic.claude-opus-4-8",
+            name: "Claude Opus 4.8 (US)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "us.anthropic.claude-sonnet-4-5-20250929-v1:0": {
             id: "us.anthropic.claude-sonnet-4-5-20250929-v1:0",
             name: "Claude Sonnet 4.5 (US)",
@@ -1750,6 +1852,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "claude-opus-4-8": {
+            id: "claude-opus-4-8",
+            name: "Claude Opus 4.8",
+            api: "anthropic-messages",
+            provider: "anthropic",
+            baseUrl: "https://api.anthropic.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "claude-sonnet-4-0": {
             id: "claude-sonnet-4-0",
             name: "Claude Sonnet 4 (latest)",
@@ -1916,7 +2035,7 @@ export const MODELS = {
             cost: {
                 input: 0.1,
                 output: 0.4,
-                cacheRead: 0.03,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 1047576,
@@ -2001,7 +2120,7 @@ export const MODELS = {
             cost: {
                 input: 0.15,
                 output: 0.6,
-                cacheRead: 0.08,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -2127,7 +2246,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.13,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -2552,7 +2671,7 @@ export const MODELS = {
             cost: {
                 input: 1.1,
                 output: 4.4,
-                cacheRead: 0.28,
+                cacheRead: 0.275,
                 cacheWrite: 0,
             },
             contextWindow: 200000,
@@ -2611,23 +2730,6 @@ export const MODELS = {
             contextWindow: 32000,
             maxTokens: 8000,
         },
-        "qwen-3-235b-a22b-instruct-2507": {
-            id: "qwen-3-235b-a22b-instruct-2507",
-            name: "Qwen 3 235B Instruct",
-            api: "openai-completions",
-            provider: "cerebras",
-            baseUrl: "https://api.cerebras.ai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.6,
-                output: 1.2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131000,
-            maxTokens: 32000,
-        },
         "zai-glm-4.7": {
             id: "zai-glm-4.7",
             name: "Z.AI GLM-4.7",
@@ -3275,6 +3377,42 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 16384,
         },
+        "@cf/ibm-granite/granite-4.0-h-micro": {
+            id: "@cf/ibm-granite/granite-4.0-h-micro",
+            name: "Granite 4.0 H Micro",
+            api: "openai-completions",
+            provider: "cloudflare-workers-ai",
+            baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+            compat: { "sendSessionAffinityHeaders": true },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.017,
+                output: 0.112,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131000,
+            maxTokens: 131000,
+        },
+        "@cf/meta/llama-3.3-70b-instruct-fp8-fast": {
+            id: "@cf/meta/llama-3.3-70b-instruct-fp8-fast",
+            name: "Llama 3.3 70B Instruct fp8 Fast",
+            api: "openai-completions",
+            provider: "cloudflare-workers-ai",
+            baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+            compat: { "sendSessionAffinityHeaders": true },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.293,
+                output: 2.253,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 24000,
+            maxTokens: 24000,
+        },
         "@cf/meta/llama-4-scout-17b-16e-instruct": {
             id: "@cf/meta/llama-4-scout-17b-16e-instruct",
             name: "Llama 4 Scout 17B 16E Instruct",
@@ -3290,9 +3428,27 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 131000,
             maxTokens: 16384,
         },
+        "@cf/mistralai/mistral-small-3.1-24b-instruct": {
+            id: "@cf/mistralai/mistral-small-3.1-24b-instruct",
+            name: "Mistral Small 3.1 24B Instruct",
+            api: "openai-completions",
+            provider: "cloudflare-workers-ai",
+            baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+            compat: { "sendSessionAffinityHeaders": true },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.351,
+                output: 0.555,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 128000,
+        },
         "@cf/moonshotai/kimi-k2.5": {
             id: "@cf/moonshotai/kimi-k2.5",
             name: "Kimi K2.5",
@@ -3326,7 +3482,7 @@ export const MODELS = {
                 cacheRead: 0.16,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
+            contextWindow: 262144,
             maxTokens: 256000,
         },
         "@cf/nvidia/nemotron-3-120b-a12b": {
@@ -3383,6 +3539,24 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 16384,
         },
+        "@cf/qwen/qwen3-30b-a3b-fp8": {
+            id: "@cf/qwen/qwen3-30b-a3b-fp8",
+            name: "Qwen3 30B A3b fp8",
+            api: "openai-completions",
+            provider: "cloudflare-workers-ai",
+            baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+            compat: { "sendSessionAffinityHeaders": true },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.0509,
+                output: 0.335,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 32768,
+            maxTokens: 32768,
+        },
         "@cf/zai-org/glm-4.7-flash": {
             id: "@cf/zai-org/glm-4.7-flash",
             name: "GLM-4.7-Flash",
@@ -3393,7 +3567,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.06,
+                input: 0.0605,
                 output: 0.4,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -3443,39 +3617,22 @@ export const MODELS = {
         },
     },
     "fireworks": {
-        "accounts/fireworks/models/deepseek-v3p1": {
-            id: "accounts/fireworks/models/deepseek-v3p1",
-            name: "DeepSeek V3.1",
-            api: "anthropic-messages",
-            provider: "fireworks",
-            baseUrl: "https://api.fireworks.ai/inference",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.56,
-                output: 1.68,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 163840,
-            maxTokens: 163840,
-        },
-        "accounts/fireworks/models/deepseek-v3p2": {
-            id: "accounts/fireworks/models/deepseek-v3p2",
-            name: "DeepSeek V3.2",
+        "accounts/fireworks/models/deepseek-v4-flash": {
+            id: "accounts/fireworks/models/deepseek-v4-flash",
+            name: "DeepSeek V4 Flash",
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.56,
-                output: 1.68,
-                cacheRead: 0.28,
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
-            contextWindow: 160000,
-            maxTokens: 160000,
+            contextWindow: 1000000,
+            maxTokens: 384000,
         },
         "accounts/fireworks/models/deepseek-v4-pro": {
             id: "accounts/fireworks/models/deepseek-v4-pro",
@@ -3488,177 +3645,75 @@ export const MODELS = {
             cost: {
                 input: 1.74,
                 output: 3.48,
-                cacheRead: 0.15,
+                cacheRead: 0.145,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
             maxTokens: 384000,
         },
-        "accounts/fireworks/models/glm-4p5": {
-            id: "accounts/fireworks/models/glm-4p5",
-            name: "GLM 4.5",
+        "accounts/fireworks/models/glm-5p1": {
+            id: "accounts/fireworks/models/glm-5p1",
+            name: "GLM 5.1",
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.55,
-                output: 2.19,
-                cacheRead: 0,
+                input: 1.4,
+                output: 4.4,
+                cacheRead: 0.26,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 202800,
             maxTokens: 131072,
         },
-        "accounts/fireworks/models/glm-4p5-air": {
-            id: "accounts/fireworks/models/glm-4p5-air",
-            name: "GLM 4.5 Air",
+        "accounts/fireworks/models/gpt-oss-120b": {
+            id: "accounts/fireworks/models/gpt-oss-120b",
+            name: "GPT OSS 120B",
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.22,
-                output: 0.88,
-                cacheRead: 0,
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0.015,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 131072,
+            maxTokens: 32768,
         },
-        "accounts/fireworks/models/glm-4p7": {
-            id: "accounts/fireworks/models/glm-4p7",
-            name: "GLM 4.7",
+        "accounts/fireworks/models/gpt-oss-20b": {
+            id: "accounts/fireworks/models/gpt-oss-20b",
+            name: "GPT OSS 20B",
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.6,
-                output: 2.2,
-                cacheRead: 0.3,
+                input: 0.07,
+                output: 0.3,
+                cacheRead: 0.035,
                 cacheWrite: 0,
             },
-            contextWindow: 198000,
-            maxTokens: 198000,
+            contextWindow: 131072,
+            maxTokens: 32768,
         },
-        "accounts/fireworks/models/glm-5": {
-            id: "accounts/fireworks/models/glm-5",
-            name: "GLM 5",
+        "accounts/fireworks/models/kimi-k2p5": {
+            id: "accounts/fireworks/models/kimi-k2p5",
+            name: "Kimi K2.5",
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 3.2,
-                cacheRead: 0.5,
-                cacheWrite: 0,
-            },
-            contextWindow: 202752,
-            maxTokens: 131072,
-        },
-        "accounts/fireworks/models/glm-5p1": {
-            id: "accounts/fireworks/models/glm-5p1",
-            name: "GLM 5.1",
-            api: "anthropic-messages",
-            provider: "fireworks",
-            baseUrl: "https://api.fireworks.ai/inference",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 1.4,
-                output: 4.4,
-                cacheRead: 0.26,
-                cacheWrite: 0,
-            },
-            contextWindow: 202800,
-            maxTokens: 131072,
-        },
-        "accounts/fireworks/models/gpt-oss-120b": {
-            id: "accounts/fireworks/models/gpt-oss-120b",
-            name: "GPT OSS 120B",
-            api: "anthropic-messages",
-            provider: "fireworks",
-            baseUrl: "https://api.fireworks.ai/inference",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 32768,
-        },
-        "accounts/fireworks/models/gpt-oss-20b": {
-            id: "accounts/fireworks/models/gpt-oss-20b",
-            name: "GPT OSS 20B",
-            api: "anthropic-messages",
-            provider: "fireworks",
-            baseUrl: "https://api.fireworks.ai/inference",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.05,
-                output: 0.2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 32768,
-        },
-        "accounts/fireworks/models/kimi-k2-instruct": {
-            id: "accounts/fireworks/models/kimi-k2-instruct",
-            name: "Kimi K2 Instruct",
-            api: "anthropic-messages",
-            provider: "fireworks",
-            baseUrl: "https://api.fireworks.ai/inference",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 1,
-                output: 3,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 16384,
-        },
-        "accounts/fireworks/models/kimi-k2-thinking": {
-            id: "accounts/fireworks/models/kimi-k2-thinking",
-            name: "Kimi K2 Thinking",
-            api: "anthropic-messages",
-            provider: "fireworks",
-            baseUrl: "https://api.fireworks.ai/inference",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.6,
-                output: 2.5,
-                cacheRead: 0.3,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 256000,
-        },
-        "accounts/fireworks/models/kimi-k2p5": {
-            id: "accounts/fireworks/models/kimi-k2p5",
-            name: "Kimi K2.5",
-            api: "anthropic-messages",
-            provider: "fireworks",
-            baseUrl: "https://api.fireworks.ai/inference",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.6,
-                output: 3,
-                cacheRead: 0.1,
+                input: 0.6,
+                output: 3,
+                cacheRead: 0.1,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
@@ -3681,23 +3736,6 @@ export const MODELS = {
             contextWindow: 262000,
             maxTokens: 262000,
         },
-        "accounts/fireworks/models/minimax-m2p1": {
-            id: "accounts/fireworks/models/minimax-m2p1",
-            name: "MiniMax-M2.1",
-            api: "anthropic-messages",
-            provider: "fireworks",
-            baseUrl: "https://api.fireworks.ai/inference",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 1.2,
-                cacheRead: 0.03,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 200000,
-        },
         "accounts/fireworks/models/minimax-m2p5": {
             id: "accounts/fireworks/models/minimax-m2p5",
             name: "MiniMax-M2.5",
@@ -3726,7 +3764,7 @@ export const MODELS = {
             cost: {
                 input: 0.3,
                 output: 1.2,
-                cacheRead: 0.03,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
             contextWindow: 196608,
@@ -3749,22 +3787,39 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 8192,
         },
-        "accounts/fireworks/routers/kimi-k2p5-turbo": {
-            id: "accounts/fireworks/routers/kimi-k2p5-turbo",
-            name: "Kimi K2.5 Turbo",
+        "accounts/fireworks/routers/glm-5p1-fast": {
+            id: "accounts/fireworks/routers/glm-5p1-fast",
+            name: "GLM 5.1 Fast",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 2.8,
+                output: 8.8,
+                cacheRead: 0.52,
+                cacheWrite: 0,
+            },
+            contextWindow: 202800,
+            maxTokens: 131072,
+        },
+        "accounts/fireworks/routers/kimi-k2p6-turbo": {
+            id: "accounts/fireworks/routers/kimi-k2p6-turbo",
+            name: "Kimi K2.6 Turbo",
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 2,
+                output: 8,
+                cacheRead: 0.3,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 256000,
+            contextWindow: 262000,
+            maxTokens: 262000,
         },
     },
     "github-copilot": {
@@ -3784,8 +3839,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 144000,
-            maxTokens: 32000,
+            contextWindow: 200000,
+            maxTokens: 64000,
         },
         "claude-opus-4.5": {
             id: "claude-opus-4.5",
@@ -3802,7 +3857,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 160000,
+            contextWindow: 200000,
             maxTokens: 32000,
         },
         "claude-opus-4.6": {
@@ -3822,7 +3877,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
-            maxTokens: 64000,
+            maxTokens: 32000,
         },
         "claude-opus-4.7": {
             id: "claude-opus-4.7",
@@ -3840,7 +3895,25 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 144000,
+            contextWindow: 200000,
+            maxTokens: 32000,
+        },
+        "claude-opus-4.8": {
+            id: "claude-opus-4.8",
+            name: "Claude Opus 4.8",
+            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: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
             maxTokens: 64000,
         },
         "claude-sonnet-4.5": {
@@ -3859,7 +3932,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 144000,
+            contextWindow: 200000,
             maxTokens: 32000,
         },
         "claude-sonnet-4.6": {
@@ -3934,7 +4007,26 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 200000,
+            maxTokens: 64000,
+        },
+        "gemini-3.5-flash": {
+            id: "gemini-3.5-flash",
+            name: "Gemini 3.5 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,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
             maxTokens: 64000,
         },
         "gpt-4.1": {
@@ -4010,8 +4102,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 264000,
-            maxTokens: 64000,
+            contextWindow: 400000,
+            maxTokens: 128000,
         },
         "gpt-5.2-codex": {
             id: "gpt-5.2-codex",
@@ -4129,57 +4221,6 @@ export const MODELS = {
         },
     },
     "google": {
-        "gemini-1.5-flash": {
-            id: "gemini-1.5-flash",
-            name: "Gemini 1.5 Flash",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.075,
-                output: 0.3,
-                cacheRead: 0.01875,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 8192,
-        },
-        "gemini-1.5-flash-8b": {
-            id: "gemini-1.5-flash-8b",
-            name: "Gemini 1.5 Flash-8B",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.0375,
-                output: 0.15,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 8192,
-        },
-        "gemini-1.5-pro": {
-            id: "gemini-1.5-pro",
-            name: "Gemini 1.5 Pro",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 1.25,
-                output: 5,
-                cacheRead: 0.3125,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 8192,
-        },
         "gemini-2.0-flash": {
             id: "gemini-2.0-flash",
             name: "Gemini 2.0 Flash",
@@ -4199,7 +4240,7 @@ export const MODELS = {
         },
         "gemini-2.0-flash-lite": {
             id: "gemini-2.0-flash-lite",
-            name: "Gemini 2.0 Flash Lite",
+            name: "Gemini 2.0 Flash-Lite",
             api: "google-generative-ai",
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
@@ -4233,7 +4274,7 @@ export const MODELS = {
         },
         "gemini-2.5-flash-lite": {
             id: "gemini-2.5-flash-lite",
-            name: "Gemini 2.5 Flash Lite",
+            name: "Gemini 2.5 Flash-Lite",
             api: "google-generative-ai",
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
@@ -4248,168 +4289,49 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "gemini-2.5-flash-lite-preview-06-17": {
-            id: "gemini-2.5-flash-lite-preview-06-17",
-            name: "Gemini 2.5 Flash Lite Preview 06-17",
+        "gemini-2.5-pro": {
+            id: "gemini-2.5-pro",
+            name: "Gemini 2.5 Pro",
             api: "google-generative-ai",
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.1,
-                output: 0.4,
-                cacheRead: 0.025,
+                input: 1.25,
+                output: 10,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "gemini-2.5-flash-lite-preview-09-2025": {
-            id: "gemini-2.5-flash-lite-preview-09-2025",
-            name: "Gemini 2.5 Flash Lite Preview 09-25",
+        "gemini-3-flash-preview": {
+            id: "gemini-3-flash-preview",
+            name: "Gemini 3 Flash Preview",
             api: "google-generative-ai",
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
             reasoning: true,
+            thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 0.1,
-                output: 0.4,
-                cacheRead: 0.025,
+                input: 0.5,
+                output: 3,
+                cacheRead: 0.05,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "gemini-2.5-flash-preview-04-17": {
-            id: "gemini-2.5-flash-preview-04-17",
-            name: "Gemini 2.5 Flash Preview 04-17",
+        "gemini-3-pro-preview": {
+            id: "gemini-3-pro-preview",
+            name: "Gemini 3 Pro Preview",
             api: "google-generative-ai",
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
             reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0.0375,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
-        "gemini-2.5-flash-preview-05-20": {
-            id: "gemini-2.5-flash-preview-05-20",
-            name: "Gemini 2.5 Flash Preview 05-20",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0.0375,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
-        "gemini-2.5-flash-preview-09-2025": {
-            id: "gemini-2.5-flash-preview-09-2025",
-            name: "Gemini 2.5 Flash Preview 09-25",
-            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: 0.075,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
-        "gemini-2.5-pro": {
-            id: "gemini-2.5-pro",
-            name: "Gemini 2.5 Pro",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1.25,
-                output: 10,
-                cacheRead: 0.125,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
-        "gemini-2.5-pro-preview-05-06": {
-            id: "gemini-2.5-pro-preview-05-06",
-            name: "Gemini 2.5 Pro Preview 05-06",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1.25,
-                output: 10,
-                cacheRead: 0.31,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
-        "gemini-2.5-pro-preview-06-05": {
-            id: "gemini-2.5-pro-preview-06-05",
-            name: "Gemini 2.5 Pro Preview 06-05",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1.25,
-                output: 10,
-                cacheRead: 0.31,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
-        "gemini-3-flash-preview": {
-            id: "gemini-3-flash-preview",
-            name: "Gemini 3 Flash Preview",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            thinkingLevelMap: { "off": null },
-            input: ["text", "image"],
-            cost: {
-                input: 0.5,
-                output: 3,
-                cacheRead: 0.05,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
-        "gemini-3-pro-preview": {
-            id: "gemini-3-pro-preview",
-            name: "Gemini 3 Pro Preview",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": null, "high": "HIGH" },
+            thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": null, "high": "HIGH" },
             input: ["text", "image"],
             cost: {
                 input: 2,
@@ -4417,8 +4339,8 @@ export const MODELS = {
                 cacheRead: 0.2,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 64000,
+            contextWindow: 1048576,
+            maxTokens: 65536,
         },
         "gemini-3.1-flash-lite": {
             id: "gemini-3.1-flash-lite",
@@ -4492,6 +4414,24 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
+        "gemini-3.5-flash": {
+            id: "gemini-3.5-flash",
+            name: "Gemini 3.5 Flash",
+            api: "google-generative-ai",
+            provider: "google",
+            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+            reasoning: true,
+            thinkingLevelMap: { "off": null },
+            input: ["text", "image"],
+            cost: {
+                input: 1.5,
+                output: 9,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
         "gemini-flash-latest": {
             id: "gemini-flash-latest",
             name: "Gemini Flash Latest",
@@ -4526,60 +4466,9 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "gemini-live-2.5-flash": {
-            id: "gemini-live-2.5-flash",
-            name: "Gemini Live 2.5 Flash",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.5,
-                output: 2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 8000,
-        },
-        "gemini-live-2.5-flash-preview-native-audio": {
-            id: "gemini-live-2.5-flash-preview-native-audio",
-            name: "Gemini Live 2.5 Flash Preview Native Audio",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.5,
-                output: 2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 65536,
-        },
-        "gemma-3-27b-it": {
-            id: "gemma-3-27b-it",
-            name: "Gemma 3 27B",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
         "gemma-4-26b-a4b-it": {
             id: "gemma-4-26b-a4b-it",
-            name: "Gemma 4 26B",
+            name: "Gemma 4 26B A4B IT",
             api: "google-generative-ai",
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
@@ -4592,12 +4481,12 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 8192,
+            contextWindow: 262144,
+            maxTokens: 32768,
         },
         "gemma-4-31b-it": {
             id: "gemma-4-31b-it",
-            name: "Gemma 4 31B",
+            name: "Gemma 4 31B IT",
             api: "google-generative-ai",
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
@@ -4610,8 +4499,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 8192,
+            contextWindow: 262144,
+            maxTokens: 32768,
         },
     },
     "google-vertex": {
@@ -5057,7 +4946,7 @@ export const MODELS = {
             cost: {
                 input: 1,
                 output: 3,
-                cacheRead: 0,
+                cacheRead: 0.5,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -5074,7 +4963,7 @@ export const MODELS = {
             cost: {
                 input: 0.15,
                 output: 0.6,
-                cacheRead: 0,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -5091,7 +4980,7 @@ export const MODELS = {
             cost: {
                 input: 0.075,
                 output: 0.3,
-                cacheRead: 0,
+                cacheRead: 0.0375,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -5377,9 +5266,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.74,
-                output: 3.48,
-                cacheRead: 0.145,
+                input: 0.435,
+                output: 0.87,
+                cacheRead: 0.003625,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -6474,7 +6363,7 @@ export const MODELS = {
             cost: {
                 input: 0.14,
                 output: 0.28,
-                cacheRead: 0.028,
+                cacheRead: 0.0028,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -6491,9 +6380,9 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
             cost: {
-                input: 1.74,
-                output: 3.48,
-                cacheRead: 0.145,
+                input: 0.435,
+                output: 0.87,
+                cacheRead: 0.003625,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -7362,7 +7251,7 @@ export const MODELS = {
             cost: {
                 input: 0.1,
                 output: 0.4,
-                cacheRead: 0.03,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 1047576,
@@ -7447,7 +7336,7 @@ export const MODELS = {
             cost: {
                 input: 0.15,
                 output: 0.6,
-                cacheRead: 0.08,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -7573,7 +7462,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.13,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -7998,7 +7887,7 @@ export const MODELS = {
             cost: {
                 input: 1.1,
                 output: 4.4,
-                cacheRead: 0.28,
+                cacheRead: 0.275,
                 cacheWrite: 0,
             },
             contextWindow: 200000,
@@ -8218,7 +8107,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 200000,
-            maxTokens: 128000,
+            maxTokens: 32000,
         },
         "claude-haiku-4-5": {
             id: "claude-haiku-4-5",
@@ -8307,6 +8196,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "claude-opus-4-8": {
+            id: "claude-opus-4-8",
+            name: "Claude Opus 4.8",
+            api: "anthropic-messages",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "claude-sonnet-4": {
             id: "claude-sonnet-4",
             name: "Claude Sonnet 4",
@@ -8374,8 +8280,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 384000,
+            contextWindow: 200000,
+            maxTokens: 128000,
         },
         "gemini-3-flash": {
             id: "gemini-3-flash",
@@ -8413,6 +8319,24 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
+        "gemini-3.5-flash": {
+            id: "gemini-3.5-flash",
+            name: "Gemini 3.5 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: 9,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
         "glm-5": {
             id: "glm-5",
             name: "GLM-5",
@@ -8735,6 +8659,23 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "grok-build-0.1": {
+            id: "grok-build-0.1",
+            name: "Grok Build 0.1",
+            api: "openai-completions",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1,
+                output: 2,
+                cacheRead: 0.2,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
         "kimi-k2.5": {
             id: "kimi-k2.5",
             name: "Kimi K2.5",
@@ -8769,35 +8710,35 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
-        "minimax-m2.5": {
-            id: "minimax-m2.5",
-            name: "MiniMax M2.5",
+        "mimo-v2.5-free": {
+            id: "mimo-v2.5-free",
+            name: "MiMo V2.5 Free",
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
-                input: 0.3,
-                output: 1.2,
-                cacheRead: 0.06,
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 204800,
-            maxTokens: 131072,
+            contextWindow: 1000000,
+            maxTokens: 128000,
         },
-        "minimax-m2.5-free": {
-            id: "minimax-m2.5-free",
-            name: "MiniMax M2.5 Free",
-            api: "anthropic-messages",
+        "minimax-m2.5": {
+            id: "minimax-m2.5",
+            name: "MiniMax M2.5",
+            api: "openai-completions",
             provider: "opencode",
-            baseUrl: "https://opencode.ai/zen",
+            baseUrl: "https://opencode.ai/zen/v1",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
@@ -8871,23 +8812,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
-        "qwen3.6-plus-free": {
-            id: "qwen3.6-plus-free",
-            name: "Qwen3.6 Plus Free",
-            api: "anthropic-messages",
-            provider: "opencode",
-            baseUrl: "https://opencode.ai/zen",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 65536,
-        },
     },
     "opencode-go": {
         "deepseek-v4-flash": {
@@ -9005,9 +8929,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.4,
-                output: 2,
-                cacheRead: 0.08,
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.0028,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -9022,9 +8946,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1,
-                output: 3,
-                cacheRead: 0.2,
+                input: 1.74,
+                output: 3.48,
+                cacheRead: 0.0145,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -9064,24 +8988,6 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131072,
         },
-        "qwen3.5-plus": {
-            id: "qwen3.5-plus",
-            name: "Qwen3.5 Plus",
-            api: "openai-completions",
-            provider: "opencode-go",
-            baseUrl: "https://opencode.ai/zen/go/v1",
-            compat: { "thinkingFormat": "qwen" },
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.2,
-                output: 1.2,
-                cacheRead: 0.02,
-                cacheWrite: 0.25,
-            },
-            contextWindow: 262144,
-            maxTokens: 65536,
-        },
         "qwen3.6-plus": {
             id: "qwen3.6-plus",
             name: "Qwen3.6 Plus",
@@ -9100,6 +9006,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
+        "qwen3.7-max": {
+            id: "qwen3.7-max",
+            name: "Qwen3.7 Max",
+            api: "anthropic-messages",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 2.5,
+                output: 7.5,
+                cacheRead: 0.5,
+                cacheWrite: 3.125,
+            },
+            contextWindow: 1000000,
+            maxTokens: 65536,
+        },
     },
     "openrouter": {
         "ai21/jamba-large-1.7": {
@@ -9119,23 +9042,6 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 4096,
         },
-        "alibaba/tongyi-deepresearch-30b-a3b": {
-            id: "alibaba/tongyi-deepresearch-30b-a3b",
-            name: "Tongyi DeepResearch 30B A3B",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.09,
-                output: 0.44999999999999996,
-                cacheRead: 0.09,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
         "amazon/nova-2-lite-v1": {
             id: "amazon/nova-2-lite-v1",
             name: "Amazon: Nova 2 Lite",
@@ -9395,6 +9301,40 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "anthropic/claude-opus-4.8": {
+            id: "anthropic/claude-opus-4.8",
+            name: "Anthropic: Claude Opus 4.8",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            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,
+            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",
@@ -9446,23 +9386,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "arcee-ai/trinity-large-preview": {
-            id: "arcee-ai/trinity-large-preview",
-            name: "Arcee AI: Trinity Large Preview",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.15,
-                output: 0.44999999999999996,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131000,
-            maxTokens: 4096,
-        },
         "arcee-ai/trinity-large-thinking": {
             id: "arcee-ai/trinity-large-thinking",
             name: "Arcee AI: Trinity Large Thinking",
@@ -9480,23 +9403,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 262144,
         },
-        "arcee-ai/trinity-large-thinking:free": {
-            id: "arcee-ai/trinity-large-thinking:free",
-            name: "Arcee AI: Trinity Large Thinking (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: 80000,
-        },
         "arcee-ai/trinity-mini": {
             id: "arcee-ai/trinity-mini",
             name: "Arcee AI: Trinity Mini",
@@ -9548,23 +9454,6 @@ export const MODELS = {
             contextWindow: 2000000,
             maxTokens: 30000,
         },
-        "baidu/cobuddy:free": {
-            id: "baidu/cobuddy:free",
-            name: "Baidu Qianfan: CoBuddy (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: 131072,
-            maxTokens: 65536,
-        },
         "baidu/ernie-4.5-21b-a3b": {
             id: "baidu/ernie-4.5-21b-a3b",
             name: "Baidu: ERNIE 4.5 21B A3B",
@@ -9579,7 +9468,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 120000,
+            contextWindow: 131072,
             maxTokens: 8000,
         },
         "baidu/ernie-4.5-vl-28b-a3b": {
@@ -9596,7 +9485,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 30000,
+            contextWindow: 131072,
             maxTokens: 8000,
         },
         "bytedance-seed/seed-1.6": {
@@ -9710,13 +9599,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.32,
-                output: 0.8899999999999999,
+                input: 0.2288,
+                output: 0.9144,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 163840,
-            maxTokens: 16384,
+            contextWindow: 131072,
+            maxTokens: 16000,
         },
         "deepseek/deepseek-chat-v3-0324": {
             id: "deepseek/deepseek-chat-v3-0324",
@@ -9766,7 +9655,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 64000,
+            contextWindow: 163840,
             maxTokens: 16000,
         },
         "deepseek/deepseek-r1-0528": {
@@ -9848,13 +9737,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
             cost: {
-                input: 0.126,
-                output: 0.252,
-                cacheRead: 0.0252,
+                input: 0.09999999999999999,
+                output: 0.19999999999999998,
+                cacheRead: 0.02,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 131072,
+            maxTokens: 16384,
         },
         "deepseek/deepseek-v4-flash:free": {
             id: "deepseek/deepseek-v4-flash:free",
@@ -10129,6 +10018,23 @@ export const MODELS = {
                 cacheRead: 0.19999999999999998,
                 cacheWrite: 0.375,
             },
+            contextWindow: 1048756,
+            maxTokens: 65536,
+        },
+        "google/gemini-3.5-flash": {
+            id: "google/gemini-3.5-flash",
+            name: "Google: Gemini 3.5 Flash",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.5,
+                output: 9,
+                cacheRead: 0.15,
+                cacheWrite: 0.08333333333333334,
+            },
             contextWindow: 1048576,
             maxTokens: 65536,
         },
@@ -10277,9 +10183,9 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.3,
-                output: 2.5,
-                cacheRead: 0.06,
+                input: 0.075,
+                output: 0.625,
+                cacheRead: 0.015,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -10302,18 +10208,18 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
-        "inclusionai/ring-2.6-1t:free": {
-            id: "inclusionai/ring-2.6-1t:free",
-            name: "inclusionAI: Ring-2.6-1T (free)",
+        "inclusionai/ring-2.6-1t": {
+            id: "inclusionai/ring-2.6-1t",
+            name: "inclusionAI: Ring-2.6-1T",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 0.075,
+                output: 0.625,
+                cacheRead: 0.015,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -10367,7 +10273,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 16384,
+            contextWindow: 131072,
             maxTokens: 16384,
         },
         "meta-llama/llama-3.3-70b-instruct": {
@@ -10401,7 +10307,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 65536,
+            contextWindow: 131072,
             maxTokens: 4096,
         },
         "meta-llama/llama-4-scout": {
@@ -10418,7 +10324,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 327680,
+            contextWindow: 10000000,
             maxTokens: 16384,
         },
         "minimax/minimax-m1": {
@@ -10452,7 +10358,7 @@ export const MODELS = {
                 cacheRead: 0.03,
                 cacheWrite: 0,
             },
-            contextWindow: 196608,
+            contextWindow: 204800,
             maxTokens: 196608,
         },
         "minimax/minimax-m2.1": {
@@ -10469,7 +10375,7 @@ export const MODELS = {
                 cacheRead: 0.03,
                 cacheWrite: 0,
             },
-            contextWindow: 196608,
+            contextWindow: 204800,
             maxTokens: 196608,
         },
         "minimax/minimax-m2.5": {
@@ -10486,7 +10392,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 196608,
+            contextWindow: 204800,
             maxTokens: 196608,
         },
         "minimax/minimax-m2.5:free": {
@@ -10503,7 +10409,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 196608,
+            contextWindow: 204800,
             maxTokens: 8192,
         },
         "minimax/minimax-m2.7": {
@@ -10520,7 +10426,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 196608,
+            contextWindow: 204800,
             maxTokens: 131072,
         },
         "mistralai/codestral-2508": {
@@ -10925,7 +10831,7 @@ export const MODELS = {
             cost: {
                 input: 0.6,
                 output: 2.5,
-                cacheRead: 0.15,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -10962,9 +10868,26 @@ export const MODELS = {
                 cacheRead: 0.25,
                 cacheWrite: 0,
             },
-            contextWindow: 262142,
+            contextWindow: 262144,
             maxTokens: 262142,
         },
+        "moonshotai/kimi-k2.6:free": {
+            id: "moonshotai/kimi-k2.6:free",
+            name: "MoonshotAI: Kimi K2.6 (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: 262144,
+            maxTokens: 4096,
+        },
         "nex-agi/deepseek-v3.1-nex-n1": {
             id: "nex-agi/deepseek-v3.1-nex-n1",
             name: "Nex AGI: DeepSeek V3.1 Nex N1",
@@ -11064,7 +10987,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
+            contextWindow: 1000000,
             maxTokens: 4096,
         },
         "nvidia/nemotron-3-super-120b-a12b:free": {
@@ -11081,7 +11004,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
+            contextWindow: 1000000,
             maxTokens: 262144,
         },
         "nvidia/nemotron-nano-12b-v2-vl:free": {
@@ -11554,11 +11477,11 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.125,
+                cacheRead: 0.13,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 16384,
+            maxTokens: 32000,
         },
         "openai/gpt-5.1-codex": {
             id: "openai/gpt-5.1-codex",
@@ -11571,7 +11494,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.125,
+                cacheRead: 0.13,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -11605,11 +11528,11 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 2,
-                cacheRead: 0.03,
+                cacheRead: 0.024999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
-            maxTokens: 128000,
+            maxTokens: 100000,
         },
         "openai/gpt-5.2": {
             id: "openai/gpt-5.2",
@@ -11645,7 +11568,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 32000,
+            maxTokens: 16384,
         },
         "openai/gpt-5.2-codex": {
             id: "openai/gpt-5.2-codex",
@@ -12181,8 +12104,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 8192,
+            contextWindow: 262144,
+            maxTokens: 32768,
         },
         "poolside/laguna-xs.2:free": {
             id: "poolside/laguna-xs.2:free",
@@ -12198,8 +12121,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 8192,
+            contextWindow: 262144,
+            maxTokens: 32768,
         },
         "prime-intellect/intellect-3": {
             id: "prime-intellect/intellect-3",
@@ -12232,7 +12155,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 32768,
+            contextWindow: 131072,
             maxTokens: 16384,
         },
         "qwen/qwen-2.5-7b-instruct": {
@@ -12249,7 +12172,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 32768,
+            contextWindow: 131072,
             maxTokens: 32768,
         },
         "qwen/qwen-plus": {
@@ -12281,7 +12204,7 @@ export const MODELS = {
                 input: 0.26,
                 output: 0.78,
                 cacheRead: 0,
-                cacheWrite: 0.325,
+                cacheWrite: 0,
             },
             contextWindow: 1000000,
             maxTokens: 32768,
@@ -12317,7 +12240,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 40960,
+            contextWindow: 131702,
             maxTokens: 40960,
         },
         "qwen/qwen3-235b-a22b": {
@@ -12368,7 +12291,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 262144,
             maxTokens: 4096,
         },
         "qwen/qwen3-30b-a3b": {
@@ -12385,7 +12308,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 40960,
+            contextWindow: 131072,
             maxTokens: 20000,
         },
         "qwen/qwen3-30b-a3b-instruct-2507": {
@@ -12436,7 +12359,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 40960,
+            contextWindow: 131072,
             maxTokens: 16384,
         },
         "qwen/qwen3-8b": {
@@ -12453,7 +12376,7 @@ export const MODELS = {
                 cacheRead: 0.049999999999999996,
                 cacheWrite: 0,
             },
-            contextWindow: 40960,
+            contextWindow: 131072,
             maxTokens: 8192,
         },
         "qwen/qwen3-coder": {
@@ -12470,7 +12393,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
+            contextWindow: 1048576,
             maxTokens: 65536,
         },
         "qwen/qwen3-coder-30b-a3b-instruct": {
@@ -12555,7 +12478,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262000,
+            contextWindow: 1048576,
             maxTokens: 262000,
         },
         "qwen/qwen3-max": {
@@ -12640,7 +12563,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 262144,
             maxTokens: 32768,
         },
         "qwen/qwen3-vl-235b-a22b-instruct": {
@@ -12691,7 +12614,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 262144,
             maxTokens: 32768,
         },
         "qwen/qwen3-vl-30b-a3b-thinking": {
@@ -12725,7 +12648,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 262144,
             maxTokens: 32768,
         },
         "qwen/qwen3-vl-8b-instruct": {
@@ -12742,7 +12665,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 256000,
             maxTokens: 32768,
         },
         "qwen/qwen3-vl-8b-thinking": {
@@ -12759,7 +12682,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 256000,
             maxTokens: 32768,
         },
         "qwen/qwen3.5-122b-a10b": {
@@ -12777,7 +12700,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 65536,
+            maxTokens: 262144,
         },
         "qwen/qwen3.5-27b": {
             id: "qwen/qwen3.5-27b",
@@ -12805,13 +12728,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.14,
+                input: 0.13899999999999998,
                 output: 1,
-                cacheRead: 0.049999999999999996,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 81920,
+            maxTokens: 4096,
         },
         "qwen/qwen3.5-397b-a17b": {
             id: "qwen/qwen3.5-397b-a17b",
@@ -12824,7 +12747,7 @@ export const MODELS = {
             cost: {
                 input: 0.39,
                 output: 2.34,
-                cacheRead: 0.195,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -12859,7 +12782,7 @@ export const MODELS = {
                 input: 0.065,
                 output: 0.26,
                 cacheRead: 0,
-                cacheWrite: 0.08125,
+                cacheWrite: 0,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
@@ -12876,7 +12799,7 @@ export const MODELS = {
                 input: 0.26,
                 output: 1.56,
                 cacheRead: 0,
-                cacheWrite: 0.325,
+                cacheWrite: 0,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
@@ -12893,7 +12816,7 @@ export const MODELS = {
                 input: 0.3,
                 output: 1.7999999999999998,
                 cacheRead: 0,
-                cacheWrite: 0,
+                cacheWrite: 0.375,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
@@ -12907,13 +12830,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.32,
+                input: 0.29,
                 output: 3.1999999999999997,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 81920,
+            maxTokens: 262140,
         },
         "qwen/qwen3.6-35b-a3b": {
             id: "qwen/qwen3.6-35b-a3b",
@@ -12924,13 +12847,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.15,
+                input: 0.14,
                 output: 1,
-                cacheRead: 0.049999999999999996,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 262140,
         },
         "qwen/qwen3.6-flash": {
             id: "qwen/qwen3.6-flash",
@@ -12983,6 +12906,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 65536,
         },
+        "qwen/qwen3.7-max": {
+            id: "qwen/qwen3.7-max",
+            name: "Qwen: Qwen3.7 Max",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.25,
+                output: 3.75,
+                cacheRead: 0.25,
+                cacheWrite: 1.5625,
+            },
+            contextWindow: 1000000,
+            maxTokens: 65536,
+        },
         "rekaai/reka-edge": {
             id: "rekaai/reka-edge",
             name: "Reka Edge",
@@ -13060,13 +13000,30 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
+                input: 0.09,
                 output: 0.3,
-                cacheRead: 0,
+                cacheRead: 0.02,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 65536,
+            maxTokens: 16384,
+        },
+        "stepfun/step-3.7-flash": {
+            id: "stepfun/step-3.7-flash",
+            name: "StepFun: Step 3.7 Flash",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.19999999999999998,
+                output: 1.15,
+                cacheRead: 0.04,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
         },
         "tencent/hy3-preview": {
             id: "tencent/hy3-preview",
@@ -13077,13 +13034,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.06599999999999999,
-                output: 0.26,
-                cacheRead: 0.029,
+                input: 0.063,
+                output: 0.21,
+                cacheRead: 0.020999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 4096,
         },
         "thedrummer/rocinante-12b": {
             id: "thedrummer/rocinante-12b",
@@ -13136,125 +13093,6 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 4096,
         },
-        "x-ai/grok-3": {
-            id: "x-ai/grok-3",
-            name: "xAI: Grok 3",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.75,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 4096,
-        },
-        "x-ai/grok-3-beta": {
-            id: "x-ai/grok-3-beta",
-            name: "xAI: Grok 3 Beta",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.75,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 4096,
-        },
-        "x-ai/grok-3-mini": {
-            id: "x-ai/grok-3-mini",
-            name: "xAI: Grok 3 Mini",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 0.5,
-                cacheRead: 0.075,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 4096,
-        },
-        "x-ai/grok-3-mini-beta": {
-            id: "x-ai/grok-3-mini-beta",
-            name: "xAI: Grok 3 Mini Beta",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 0.5,
-                cacheRead: 0.075,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 4096,
-        },
-        "x-ai/grok-4": {
-            id: "x-ai/grok-4",
-            name: "xAI: Grok 4",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.75,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 4096,
-        },
-        "x-ai/grok-4-fast": {
-            id: "x-ai/grok-4-fast",
-            name: "xAI: Grok 4 Fast",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.19999999999999998,
-                output: 0.5,
-                cacheRead: 0.049999999999999996,
-                cacheWrite: 0,
-            },
-            contextWindow: 2000000,
-            maxTokens: 30000,
-        },
-        "x-ai/grok-4.1-fast": {
-            id: "x-ai/grok-4.1-fast",
-            name: "xAI: Grok 4.1 Fast",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.19999999999999998,
-                output: 0.5,
-                cacheRead: 0.049999999999999996,
-                cacheWrite: 0,
-            },
-            contextWindow: 2000000,
-            maxTokens: 30000,
-        },
         "x-ai/grok-4.20": {
             id: "x-ai/grok-4.20",
             name: "xAI: Grok 4.20",
@@ -13289,22 +13127,22 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 4096,
         },
-        "x-ai/grok-code-fast-1": {
-            id: "x-ai/grok-code-fast-1",
-            name: "xAI: Grok Code Fast 1",
+        "x-ai/grok-build-0.1": {
+            id: "x-ai/grok-build-0.1",
+            name: "xAI: Grok Build 0.1",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
-                input: 0.19999999999999998,
-                output: 1.5,
-                cacheRead: 0.02,
+                input: 1,
+                output: 2,
+                cacheRead: 0.19999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
-            maxTokens: 10000,
+            maxTokens: 4096,
         },
         "xiaomi/mimo-v2-flash": {
             id: "xiaomi/mimo-v2-flash",
@@ -13366,9 +13204,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.39999999999999997,
-                output: 2,
-                cacheRead: 0.08,
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.0028,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -13383,13 +13221,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1,
-                output: 3,
-                cacheRead: 0.19999999999999998,
+                input: 0.435,
+                output: 0.87,
+                cacheRead: 0.0036,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 16384,
+            maxTokens: 131072,
         },
         "z-ai/glm-4-32b": {
             id: "z-ai/glm-4-32b",
@@ -13434,13 +13272,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.13,
+                input: 0.125,
                 output: 0.85,
-                cacheRead: 0.024999999999999998,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 98304,
+            maxTokens: 131070,
         },
         "z-ai/glm-4.5-air:free": {
             id: "z-ai/glm-4.5-air:free",
@@ -13672,9 +13510,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.5,
-                output: 3,
-                cacheRead: 0.049999999999999996,
+                input: 1.5,
+                output: 9,
+                cacheRead: 0.15,
                 cacheWrite: 0.08333333333333334,
             },
             contextWindow: 1048576,
@@ -13711,7 +13549,7 @@ export const MODELS = {
                 cacheRead: 0.25,
                 cacheWrite: 0,
             },
-            contextWindow: 262142,
+            contextWindow: 262144,
             maxTokens: 262142,
         },
         "~openai/gpt-latest": {
@@ -13882,6 +13720,25 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 500000,
         },
+        "Qwen/Qwen3.7-Max": {
+            id: "Qwen/Qwen3.7-Max",
+            name: "Qwen3.7 Max",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
+            input: ["text"],
+            cost: {
+                input: 2.5,
+                output: 7.5,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 500000,
+        },
         "deepseek-ai/DeepSeek-V3": {
             id: "deepseek-ai/DeepSeek-V3",
             name: "DeepSeek V3",
@@ -14378,6 +14235,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "alibaba/qwen3.7-max": {
+            id: "alibaba/qwen3.7-max",
+            name: "Qwen 3.7 Max",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.25,
+                output: 3.75,
+                cacheRead: 0.25,
+                cacheWrite: 1.5625,
+            },
+            contextWindow: 991000,
+            maxTokens: 64000,
+        },
         "anthropic/claude-3-haiku": {
             id: "anthropic/claude-3-haiku",
             name: "Claude 3 Haiku",
@@ -14516,6 +14390,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "anthropic/claude-opus-4.8": {
+            id: "anthropic/claude-opus-4.8",
+            name: "Claude Opus 4.8",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "anthropic/claude-sonnet-4": {
             id: "anthropic/claude-sonnet-4",
             name: "Claude Sonnet 4",
@@ -14941,13 +14832,30 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
-        "google/gemma-4-26b-a4b-it": {
-            id: "google/gemma-4-26b-a4b-it",
-            name: "Gemma 4 26B A4B IT",
+        "google/gemini-3.5-flash": {
+            id: "google/gemini-3.5-flash",
+            name: "Gemini 3.5 Flash",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.5,
+                output: 9,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 64000,
+        },
+        "google/gemma-4-26b-a4b-it": {
+            id: "google/gemma-4-26b-a4b-it",
+            name: "Gemma 4 26B A4B IT",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: false,
             input: ["text", "image"],
             cost: {
                 input: 0.13,
@@ -15249,7 +15157,7 @@ export const MODELS = {
         },
         "minimax/minimax-m2.7": {
             id: "minimax/minimax-m2.7",
-            name: "Minimax M2.7",
+            name: "MiniMax M2.7",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
@@ -15400,6 +15308,23 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 64000,
         },
+        "mistral/mistral-medium-3.5": {
+            id: "mistral/mistral-medium-3.5",
+            name: "Mistral Medium Latest",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.5,
+                output: 7.5,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
         "mistral/mistral-small": {
             id: "mistral/mistral-small",
             name: "Mistral Small",
@@ -16262,125 +16187,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 8000,
         },
-        "xai/grok-3": {
-            id: "xai/grok-3",
-            name: "Grok 3 Beta",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.75,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
-        "xai/grok-3-fast": {
-            id: "xai/grok-3-fast",
-            name: "Grok 3 Fast Beta",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 5,
-                output: 25,
-                cacheRead: 1.25,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
-        "xai/grok-3-mini": {
-            id: "xai/grok-3-mini",
-            name: "Grok 3 Mini Beta",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 0.5,
-                cacheRead: 0.075,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
-        "xai/grok-3-mini-fast": {
-            id: "xai/grok-3-mini-fast",
-            name: "Grok 3 Mini Fast Beta",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.6,
-                output: 4,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
-        "xai/grok-4": {
-            id: "xai/grok-4",
-            name: "Grok 4",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.75,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 256000,
-        },
-        "xai/grok-4-fast-non-reasoning": {
-            id: "xai/grok-4-fast-non-reasoning",
-            name: "Grok 4 Fast Non-Reasoning",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.19999999999999998,
-                output: 0.5,
-                cacheRead: 0.049999999999999996,
-                cacheWrite: 0,
-            },
-            contextWindow: 2000000,
-            maxTokens: 256000,
-        },
-        "xai/grok-4-fast-reasoning": {
-            id: "xai/grok-4-fast-reasoning",
-            name: "Grok 4 Fast Reasoning",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.19999999999999998,
-                output: 0.5,
-                cacheRead: 0.049999999999999996,
-                cacheWrite: 0,
-            },
-            contextWindow: 2000000,
-            maxTokens: 256000,
-        },
         "xai/grok-4.1-fast-non-reasoning": {
             id: "xai/grok-4.1-fast-non-reasoning",
             name: "Grok 4.1 Fast Non-Reasoning",
@@ -16395,8 +16201,8 @@ export const MODELS = {
                 cacheRead: 0.049999999999999996,
                 cacheWrite: 0,
             },
-            contextWindow: 2000000,
-            maxTokens: 30000,
+            contextWindow: 1000000,
+            maxTokens: 1000000,
         },
         "xai/grok-4.1-fast-reasoning": {
             id: "xai/grok-4.1-fast-reasoning",
@@ -16412,8 +16218,8 @@ export const MODELS = {
                 cacheRead: 0.049999999999999996,
                 cacheWrite: 0,
             },
-            contextWindow: 2000000,
-            maxTokens: 30000,
+            contextWindow: 1000000,
+            maxTokens: 1000000,
         },
         "xai/grok-4.20-multi-agent": {
             id: "xai/grok-4.20-multi-agent",
@@ -16534,18 +16340,18 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 1000000,
         },
-        "xai/grok-code-fast-1": {
-            id: "xai/grok-code-fast-1",
-            name: "Grok Code Fast 1",
+        "xai/grok-build-0.1": {
+            id: "xai/grok-build-0.1",
+            name: "Grok Build 0.1",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
-                input: 0.19999999999999998,
-                output: 1.5,
-                cacheRead: 0.02,
+                input: 1,
+                output: 2,
+                cacheRead: 0.19999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
@@ -16594,9 +16400,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.39999999999999997,
-                output: 2,
-                cacheRead: 0.08,
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.0028,
                 cacheWrite: 0,
             },
             contextWindow: 1050000,
@@ -16611,9 +16417,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 3,
-                cacheRead: 0.19999999999999998,
+                input: 0.435,
+                output: 0.87,
+                cacheRead: 0.0036,
                 cacheWrite: 0,
             },
             contextWindow: 1050000,
@@ -16842,329 +16648,6 @@ export const MODELS = {
         },
     },
     "xai": {
-        "grok-2": {
-            id: "grok-2",
-            name: "Grok 2",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 2,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "grok-2-1212": {
-            id: "grok-2-1212",
-            name: "Grok 2 (1212)",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 2,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "grok-2-latest": {
-            id: "grok-2-latest",
-            name: "Grok 2 Latest",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 2,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "grok-2-vision": {
-            id: "grok-2-vision",
-            name: "Grok 2 Vision",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 2,
-                cacheWrite: 0,
-            },
-            contextWindow: 8192,
-            maxTokens: 4096,
-        },
-        "grok-2-vision-1212": {
-            id: "grok-2-vision-1212",
-            name: "Grok 2 Vision (1212)",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 2,
-                cacheWrite: 0,
-            },
-            contextWindow: 8192,
-            maxTokens: 4096,
-        },
-        "grok-2-vision-latest": {
-            id: "grok-2-vision-latest",
-            name: "Grok 2 Vision Latest",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 2,
-                cacheWrite: 0,
-            },
-            contextWindow: 8192,
-            maxTokens: 4096,
-        },
-        "grok-3": {
-            id: "grok-3",
-            name: "Grok 3",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.75,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "grok-3-fast": {
-            id: "grok-3-fast",
-            name: "Grok 3 Fast",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 5,
-                output: 25,
-                cacheRead: 1.25,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "grok-3-fast-latest": {
-            id: "grok-3-fast-latest",
-            name: "Grok 3 Fast Latest",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 5,
-                output: 25,
-                cacheRead: 1.25,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "grok-3-latest": {
-            id: "grok-3-latest",
-            name: "Grok 3 Latest",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.75,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "grok-3-mini": {
-            id: "grok-3-mini",
-            name: "Grok 3 Mini",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 0.5,
-                cacheRead: 0.075,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "grok-3-mini-fast": {
-            id: "grok-3-mini-fast",
-            name: "Grok 3 Mini Fast",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.6,
-                output: 4,
-                cacheRead: 0.15,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "grok-3-mini-fast-latest": {
-            id: "grok-3-mini-fast-latest",
-            name: "Grok 3 Mini Fast Latest",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.6,
-                output: 4,
-                cacheRead: 0.15,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "grok-3-mini-latest": {
-            id: "grok-3-mini-latest",
-            name: "Grok 3 Mini Latest",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 0.5,
-                cacheRead: 0.075,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "grok-4": {
-            id: "grok-4",
-            name: "Grok 4",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.75,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 64000,
-        },
-        "grok-4-1-fast": {
-            id: "grok-4-1-fast",
-            name: "Grok 4.1 Fast",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.2,
-                output: 0.5,
-                cacheRead: 0.05,
-                cacheWrite: 0,
-            },
-            contextWindow: 2000000,
-            maxTokens: 30000,
-        },
-        "grok-4-1-fast-non-reasoning": {
-            id: "grok-4-1-fast-non-reasoning",
-            name: "Grok 4.1 Fast (Non-Reasoning)",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.2,
-                output: 0.5,
-                cacheRead: 0.05,
-                cacheWrite: 0,
-            },
-            contextWindow: 2000000,
-            maxTokens: 30000,
-        },
-        "grok-4-fast": {
-            id: "grok-4-fast",
-            name: "Grok 4 Fast",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.2,
-                output: 0.5,
-                cacheRead: 0.05,
-                cacheWrite: 0,
-            },
-            contextWindow: 2000000,
-            maxTokens: 30000,
-        },
-        "grok-4-fast-non-reasoning": {
-            id: "grok-4-fast-non-reasoning",
-            name: "Grok 4 Fast (Non-Reasoning)",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.2,
-                output: 0.5,
-                cacheRead: 0.05,
-                cacheWrite: 0,
-            },
-            contextWindow: 2000000,
-            maxTokens: 30000,
-        },
         "grok-4.20-0309-non-reasoning": {
             id: "grok-4.20-0309-non-reasoning",
             name: "Grok 4.20 (Non-Reasoning)",
@@ -17174,8 +16657,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 6,
+                input: 1.25,
+                output: 2.5,
                 cacheRead: 0.2,
                 cacheWrite: 0,
             },
@@ -17191,8 +16674,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 6,
+                input: 1.25,
+                output: 2.5,
                 cacheRead: 0.2,
                 cacheWrite: 0,
             },
@@ -17216,22 +16699,22 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 30000,
         },
-        "grok-beta": {
-            id: "grok-beta",
-            name: "Grok Beta",
+        "grok-build-0.1": {
+            id: "grok-build-0.1",
+            name: "Grok Build 0.1",
             api: "openai-completions",
             provider: "xai",
             baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text"],
+            reasoning: true,
+            input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 15,
-                cacheRead: 5,
+                input: 1,
+                output: 2,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 4096,
+            contextWindow: 256000,
+            maxTokens: 256000,
         },
         "grok-code-fast-1": {
             id: "grok-code-fast-1",
@@ -17239,7 +16722,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "xai",
             baseUrl: "https://api.x.ai/v1",
-            reasoning: true,
+            reasoning: false,
             input: ["text"],
             cost: {
                 input: 0.2,
@@ -17247,25 +16730,8 @@ export const MODELS = {
                 cacheRead: 0.02,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 10000,
-        },
-        "grok-vision-beta": {
-            id: "grok-vision-beta",
-            name: "Grok Vision Beta",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 5,
-                output: 15,
-                cacheRead: 5,
-                cacheWrite: 0,
-            },
-            contextWindow: 8192,
-            maxTokens: 4096,
+            contextWindow: 32768,
+            maxTokens: 8192,
         },
     },
     "xiaomi": {