@eminent337/aery-ai 0.1.142 → 0.1.145

package/dist/models.generated.js

@@ -53,23 +53,6 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 8192,
         },
-        "amazon.nova-premier-v1:0": {
-            id: "amazon.nova-premier-v1:0",
-            name: "Nova Premier",
-            api: "bedrock-converse-stream",
-            provider: "amazon-bedrock",
-            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 2.5,
-                output: 12.5,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 16384,
-        },
         "amazon.nova-pro-v1:0": {
             id: "amazon.nova-pro-v1:0",
             name: "Nova Pro",
@@ -87,91 +70,6 @@ export const MODELS = {
             contextWindow: 300000,
             maxTokens: 8192,
         },
-        "anthropic.claude-3-5-haiku-20241022-v1:0": {
-            id: "anthropic.claude-3-5-haiku-20241022-v1:0",
-            name: "Claude Haiku 3.5",
-            api: "bedrock-converse-stream",
-            provider: "amazon-bedrock",
-            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.8,
-                output: 4,
-                cacheRead: 0.08,
-                cacheWrite: 1,
-            },
-            contextWindow: 200000,
-            maxTokens: 8192,
-        },
-        "anthropic.claude-3-5-sonnet-20240620-v1:0": {
-            id: "anthropic.claude-3-5-sonnet-20240620-v1:0",
-            name: "Claude Sonnet 3.5",
-            api: "bedrock-converse-stream",
-            provider: "amazon-bedrock",
-            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 8192,
-        },
-        "anthropic.claude-3-5-sonnet-20241022-v2:0": {
-            id: "anthropic.claude-3-5-sonnet-20241022-v2:0",
-            name: "Claude Sonnet 3.5 v2",
-            api: "bedrock-converse-stream",
-            provider: "amazon-bedrock",
-            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 8192,
-        },
-        "anthropic.claude-3-7-sonnet-20250219-v1:0": {
-            id: "anthropic.claude-3-7-sonnet-20250219-v1:0",
-            name: "Claude Sonnet 3.7",
-            api: "bedrock-converse-stream",
-            provider: "amazon-bedrock",
-            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 8192,
-        },
-        "anthropic.claude-3-haiku-20240307-v1:0": {
-            id: "anthropic.claude-3-haiku-20240307-v1:0",
-            name: "Claude Haiku 3",
-            api: "bedrock-converse-stream",
-            provider: "amazon-bedrock",
-            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.25,
-                output: 1.25,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 4096,
-        },
         "anthropic.claude-haiku-4-5-20251001-v1:0": {
             id: "anthropic.claude-haiku-4-5-20251001-v1:0",
             name: "Claude Haiku 4.5",
@@ -206,23 +104,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 32000,
         },
-        "anthropic.claude-opus-4-20250514-v1:0": {
-            id: "anthropic.claude-opus-4-20250514-v1:0",
-            name: "Claude Opus 4",
-            api: "bedrock-converse-stream",
-            provider: "amazon-bedrock",
-            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 15,
-                output: 75,
-                cacheRead: 1.5,
-                cacheWrite: 18.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 32000,
-        },
         "anthropic.claude-opus-4-5-20251101-v1:0": {
             id: "anthropic.claude-opus-4-5-20251101-v1:0",
             name: "Claude Opus 4.5",
@@ -276,9 +157,9 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "anthropic.claude-sonnet-4-20250514-v1:0": {
-            id: "anthropic.claude-sonnet-4-20250514-v1:0",
-            name: "Claude Sonnet 4",
+        "anthropic.claude-sonnet-4-5-20250929-v1:0": {
+            id: "anthropic.claude-sonnet-4-5-20250929-v1:0",
+            name: "Claude Sonnet 4.5",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -293,9 +174,9 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 64000,
         },
-        "anthropic.claude-sonnet-4-5-20250929-v1:0": {
-            id: "anthropic.claude-sonnet-4-5-20250929-v1:0",
-            name: "Claude Sonnet 4.5",
+        "anthropic.claude-sonnet-4-6": {
+            id: "anthropic.claude-sonnet-4-6",
+            name: "Claude Sonnet 4.6",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -307,24 +188,24 @@ export const MODELS = {
                 cacheRead: 0.3,
                 cacheWrite: 3.75,
             },
-            contextWindow: 200000,
+            contextWindow: 1000000,
             maxTokens: 64000,
         },
-        "anthropic.claude-sonnet-4-6": {
-            id: "anthropic.claude-sonnet-4-6",
-            name: "Claude Sonnet 4.6",
+        "au.anthropic.claude-haiku-4-5-20251001-v1:0": {
+            id: "au.anthropic.claude-haiku-4-5-20251001-v1:0",
+            name: "Claude Haiku 4.5 (AU)",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
+                input: 1,
+                output: 5,
+                cacheRead: 0.1,
+                cacheWrite: 1.25,
             },
-            contextWindow: 1000000,
+            contextWindow: 200000,
             maxTokens: 64000,
         },
         "au.anthropic.claude-opus-4-6-v1": {
@@ -345,6 +226,23 @@ export const MODELS = {
             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)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 3,
+                output: 15,
+                cacheRead: 0.3,
+                cacheWrite: 3.75,
+            },
+            contextWindow: 200000,
+            maxTokens: 64000,
+        },
         "au.anthropic.claude-sonnet-4-6": {
             id: "au.anthropic.claude-sonnet-4-6",
             name: "AU Anthropic Claude Sonnet 4.6",
@@ -483,23 +381,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "eu.anthropic.claude-sonnet-4-20250514-v1:0": {
-            id: "eu.anthropic.claude-sonnet-4-20250514-v1:0",
-            name: "Claude Sonnet 4 (EU)",
-            api: "bedrock-converse-stream",
-            provider: "amazon-bedrock",
-            baseUrl: "https://bedrock-runtime.eu-central-1.amazonaws.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 64000,
-        },
         "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)",
@@ -604,23 +485,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "global.anthropic.claude-sonnet-4-20250514-v1:0": {
-            id: "global.anthropic.claude-sonnet-4-20250514-v1:0",
-            name: "Claude Sonnet 4 (Global)",
-            api: "bedrock-converse-stream",
-            provider: "amazon-bedrock",
-            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 64000,
-        },
         "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)",
@@ -689,119 +553,86 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 4096,
         },
-        "meta.llama3-1-405b-instruct-v1:0": {
-            id: "meta.llama3-1-405b-instruct-v1:0",
-            name: "Llama 3.1 405B Instruct",
+        "jp.anthropic.claude-opus-4-7": {
+            id: "jp.anthropic.claude-opus-4-7",
+            name: "Claude Opus 4.7 (JP)",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 2.4,
-                output: 2.4,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 4096,
-        },
-        "meta.llama3-1-70b-instruct-v1:0": {
-            id: "meta.llama3-1-70b-instruct-v1:0",
-            name: "Llama 3.1 70B Instruct",
-            api: "bedrock-converse-stream",
-            provider: "amazon-bedrock",
-            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: false,
-            input: ["text"],
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
             cost: {
-                input: 0.72,
-                output: 0.72,
-                cacheRead: 0,
-                cacheWrite: 0,
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
             },
-            contextWindow: 128000,
-            maxTokens: 4096,
+            contextWindow: 1000000,
+            maxTokens: 128000,
         },
-        "meta.llama3-1-8b-instruct-v1:0": {
-            id: "meta.llama3-1-8b-instruct-v1:0",
-            name: "Llama 3.1 8B Instruct",
+        "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)",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: false,
-            input: ["text"],
+            reasoning: true,
+            input: ["text", "image"],
             cost: {
-                input: 0.22,
-                output: 0.22,
-                cacheRead: 0,
-                cacheWrite: 0,
+                input: 3,
+                output: 15,
+                cacheRead: 0.3,
+                cacheWrite: 3.75,
             },
-            contextWindow: 128000,
-            maxTokens: 4096,
+            contextWindow: 200000,
+            maxTokens: 64000,
         },
-        "meta.llama3-2-11b-instruct-v1:0": {
-            id: "meta.llama3-2-11b-instruct-v1:0",
-            name: "Llama 3.2 11B Instruct",
+        "jp.anthropic.claude-sonnet-4-6": {
+            id: "jp.anthropic.claude-sonnet-4-6",
+            name: "Claude Sonnet 4.6 (JP)",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: false,
+            reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.16,
-                output: 0.16,
-                cacheRead: 0,
-                cacheWrite: 0,
+                input: 3,
+                output: 15,
+                cacheRead: 0.3,
+                cacheWrite: 3.75,
             },
-            contextWindow: 128000,
-            maxTokens: 4096,
+            contextWindow: 1000000,
+            maxTokens: 64000,
         },
-        "meta.llama3-2-1b-instruct-v1:0": {
-            id: "meta.llama3-2-1b-instruct-v1:0",
-            name: "Llama 3.2 1B Instruct",
+        "meta.llama3-1-70b-instruct-v1:0": {
+            id: "meta.llama3-1-70b-instruct-v1:0",
+            name: "Llama 3.1 70B Instruct",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.1,
-                output: 0.1,
+                input: 0.72,
+                output: 0.72,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131000,
+            contextWindow: 128000,
             maxTokens: 4096,
         },
-        "meta.llama3-2-3b-instruct-v1:0": {
-            id: "meta.llama3-2-3b-instruct-v1:0",
-            name: "Llama 3.2 3B Instruct",
+        "meta.llama3-1-8b-instruct-v1:0": {
+            id: "meta.llama3-1-8b-instruct-v1:0",
+            name: "Llama 3.1 8B Instruct",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.15,
-                output: 0.15,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131000,
-            maxTokens: 4096,
-        },
-        "meta.llama3-2-90b-instruct-v1:0": {
-            id: "meta.llama3-2-90b-instruct-v1:0",
-            name: "Llama 3.2 90B Instruct",
-            api: "bedrock-converse-stream",
-            provider: "amazon-bedrock",
-            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.72,
-                output: 0.72,
+                input: 0.22,
+                output: 0.22,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -1180,7 +1011,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "openai.gpt-oss-20b-1:0": {
             id: "openai.gpt-oss-20b-1:0",
@@ -1197,7 +1028,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "openai.gpt-oss-safeguard-120b": {
             id: "openai.gpt-oss-safeguard-120b",
@@ -1214,7 +1045,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "openai.gpt-oss-safeguard-20b": {
             id: "openai.gpt-oss-safeguard-20b",
@@ -1231,7 +1062,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "qwen.qwen3-235b-a22b-2507-v1:0": {
             id: "qwen.qwen3-235b-a22b-2507-v1:0",
@@ -1386,23 +1217,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 32000,
         },
-        "us.anthropic.claude-opus-4-20250514-v1:0": {
-            id: "us.anthropic.claude-opus-4-20250514-v1:0",
-            name: "Claude Opus 4 (US)",
-            api: "bedrock-converse-stream",
-            provider: "amazon-bedrock",
-            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 15,
-                output: 75,
-                cacheRead: 1.5,
-                cacheWrite: 18.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 32000,
-        },
         "us.anthropic.claude-opus-4-5-20251101-v1:0": {
             id: "us.anthropic.claude-opus-4-5-20251101-v1:0",
             name: "Claude Opus 4.5 (US)",
@@ -1456,9 +1270,9 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "us.anthropic.claude-sonnet-4-20250514-v1:0": {
-            id: "us.anthropic.claude-sonnet-4-20250514-v1:0",
-            name: "Claude Sonnet 4 (US)",
+        "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)",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -1473,9 +1287,9 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 64000,
         },
-        "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)",
+        "us.anthropic.claude-sonnet-4-6": {
+            id: "us.anthropic.claude-sonnet-4-6",
+            name: "Claude Sonnet 4.6 (US)",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -1487,25 +1301,59 @@ export const MODELS = {
                 cacheRead: 0.3,
                 cacheWrite: 3.75,
             },
-            contextWindow: 200000,
+            contextWindow: 1000000,
             maxTokens: 64000,
         },
-        "us.anthropic.claude-sonnet-4-6": {
-            id: "us.anthropic.claude-sonnet-4-6",
-            name: "Claude Sonnet 4.6 (US)",
+        "us.deepseek.r1-v1:0": {
+            id: "us.deepseek.r1-v1:0",
+            name: "DeepSeek-R1 (US)",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
             reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.35,
+                output: 5.4,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 32768,
+        },
+        "us.meta.llama4-maverick-17b-instruct-v1:0": {
+            id: "us.meta.llama4-maverick-17b-instruct-v1:0",
+            name: "Llama 4 Maverick 17B Instruct (US)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
+                input: 0.24,
+                output: 0.97,
+                cacheRead: 0,
+                cacheWrite: 0,
             },
             contextWindow: 1000000,
-            maxTokens: 64000,
+            maxTokens: 16384,
+        },
+        "us.meta.llama4-scout-17b-instruct-v1:0": {
+            id: "us.meta.llama4-scout-17b-instruct-v1:0",
+            name: "Llama 4 Scout 17B Instruct (US)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.17,
+                output: 0.66,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 3500000,
+            maxTokens: 16384,
         },
         "writer.palmyra-x4-v1:0": {
             id: "writer.palmyra-x4-v1:0",
@@ -3601,6 +3449,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -3611,12 +3460,6 @@ export const MODELS = {
             },
             contextWindow: 163840,
             maxTokens: 163840,
-            compat: {
-                sendSessionAffinityHeaders: true,
-                supportsEagerToolInputStreaming: false,
-                supportsCacheControlOnTools: false,
-                supportsLongCacheRetention: false,
-            },
         },
         "accounts/fireworks/models/deepseek-v3p2": {
             id: "accounts/fireworks/models/deepseek-v3p2",
@@ -3624,6 +3467,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -3634,12 +3478,6 @@ export const MODELS = {
             },
             contextWindow: 160000,
             maxTokens: 160000,
-            compat: {
-                sendSessionAffinityHeaders: true,
-                supportsEagerToolInputStreaming: false,
-                supportsCacheControlOnTools: false,
-                supportsLongCacheRetention: false,
-            },
         },
         "accounts/fireworks/models/deepseek-v4-pro": {
             id: "accounts/fireworks/models/deepseek-v4-pro",
@@ -3647,6 +3485,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -3657,12 +3496,6 @@ export const MODELS = {
             },
             contextWindow: 1000000,
             maxTokens: 384000,
-            compat: {
-                sendSessionAffinityHeaders: true,
-                supportsEagerToolInputStreaming: false,
-                supportsCacheControlOnTools: false,
-                supportsLongCacheRetention: false,
-            },
         },
         "accounts/fireworks/models/glm-4p5": {
             id: "accounts/fireworks/models/glm-4p5",
@@ -3670,6 +3503,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -3680,12 +3514,6 @@ export const MODELS = {
             },
             contextWindow: 131072,
             maxTokens: 131072,
-            compat: {
-                sendSessionAffinityHeaders: true,
-                supportsEagerToolInputStreaming: false,
-                supportsCacheControlOnTools: false,
-                supportsLongCacheRetention: false,
-            },
         },
         "accounts/fireworks/models/glm-4p5-air": {
             id: "accounts/fireworks/models/glm-4p5-air",
@@ -3693,6 +3521,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -3703,12 +3532,6 @@ export const MODELS = {
             },
             contextWindow: 131072,
             maxTokens: 131072,
-            compat: {
-                sendSessionAffinityHeaders: true,
-                supportsEagerToolInputStreaming: false,
-                supportsCacheControlOnTools: false,
-                supportsLongCacheRetention: false,
-            },
         },
         "accounts/fireworks/models/glm-4p7": {
             id: "accounts/fireworks/models/glm-4p7",
@@ -3716,6 +3539,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -3726,12 +3550,6 @@ export const MODELS = {
             },
             contextWindow: 198000,
             maxTokens: 198000,
-            compat: {
-                sendSessionAffinityHeaders: true,
-                supportsEagerToolInputStreaming: false,
-                supportsCacheControlOnTools: false,
-                supportsLongCacheRetention: false,
-            },
         },
         "accounts/fireworks/models/glm-5": {
             id: "accounts/fireworks/models/glm-5",
@@ -3739,6 +3557,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -3749,12 +3568,6 @@ export const MODELS = {
             },
             contextWindow: 202752,
             maxTokens: 131072,
-            compat: {
-                sendSessionAffinityHeaders: true,
-                supportsEagerToolInputStreaming: false,
-                supportsCacheControlOnTools: false,
-                supportsLongCacheRetention: false,
-            },
         },
         "accounts/fireworks/models/glm-5p1": {
             id: "accounts/fireworks/models/glm-5p1",
@@ -3762,6 +3575,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -3772,12 +3586,6 @@ export const MODELS = {
             },
             contextWindow: 202800,
             maxTokens: 131072,
-            compat: {
-                sendSessionAffinityHeaders: true,
-                supportsEagerToolInputStreaming: false,
-                supportsCacheControlOnTools: false,
-                supportsLongCacheRetention: false,
-            },
         },
         "accounts/fireworks/models/gpt-oss-120b": {
             id: "accounts/fireworks/models/gpt-oss-120b",
@@ -3785,6 +3593,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -3795,12 +3604,6 @@ export const MODELS = {
             },
             contextWindow: 131072,
             maxTokens: 32768,
-            compat: {
-                sendSessionAffinityHeaders: true,
-                supportsEagerToolInputStreaming: false,
-                supportsCacheControlOnTools: false,
-                supportsLongCacheRetention: false,
-            },
         },
         "accounts/fireworks/models/gpt-oss-20b": {
             id: "accounts/fireworks/models/gpt-oss-20b",
@@ -3808,6 +3611,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -3818,12 +3622,6 @@ export const MODELS = {
             },
             contextWindow: 131072,
             maxTokens: 32768,
-            compat: {
-                sendSessionAffinityHeaders: true,
-                supportsEagerToolInputStreaming: false,
-                supportsCacheControlOnTools: false,
-                supportsLongCacheRetention: false,
-            },
         },
         "accounts/fireworks/models/kimi-k2-instruct": {
             id: "accounts/fireworks/models/kimi-k2-instruct",
@@ -3831,6 +3629,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
             reasoning: false,
             input: ["text"],
             cost: {
@@ -3841,12 +3640,6 @@ export const MODELS = {
             },
             contextWindow: 128000,
             maxTokens: 16384,
-            compat: {
-                sendSessionAffinityHeaders: true,
-                supportsEagerToolInputStreaming: false,
-                supportsCacheControlOnTools: false,
-                supportsLongCacheRetention: false,
-            },
         },
         "accounts/fireworks/models/kimi-k2-thinking": {
             id: "accounts/fireworks/models/kimi-k2-thinking",
@@ -3854,6 +3647,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -3864,12 +3658,6 @@ export const MODELS = {
             },
             contextWindow: 256000,
             maxTokens: 256000,
-            compat: {
-                sendSessionAffinityHeaders: true,
-                supportsEagerToolInputStreaming: false,
-                supportsCacheControlOnTools: false,
-                supportsLongCacheRetention: false,
-            },
         },
         "accounts/fireworks/models/kimi-k2p5": {
             id: "accounts/fireworks/models/kimi-k2p5",
@@ -3877,6 +3665,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -3887,12 +3676,6 @@ export const MODELS = {
             },
             contextWindow: 256000,
             maxTokens: 256000,
-            compat: {
-                sendSessionAffinityHeaders: true,
-                supportsEagerToolInputStreaming: false,
-                supportsCacheControlOnTools: false,
-                supportsLongCacheRetention: false,
-            },
         },
         "accounts/fireworks/models/kimi-k2p6": {
             id: "accounts/fireworks/models/kimi-k2p6",
@@ -3900,6 +3683,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -3910,12 +3694,6 @@ export const MODELS = {
             },
             contextWindow: 262000,
             maxTokens: 262000,
-            compat: {
-                sendSessionAffinityHeaders: true,
-                supportsEagerToolInputStreaming: false,
-                supportsCacheControlOnTools: false,
-                supportsLongCacheRetention: false,
-            },
         },
         "accounts/fireworks/models/minimax-m2p1": {
             id: "accounts/fireworks/models/minimax-m2p1",
@@ -3923,6 +3701,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -3933,12 +3712,6 @@ export const MODELS = {
             },
             contextWindow: 200000,
             maxTokens: 200000,
-            compat: {
-                sendSessionAffinityHeaders: true,
-                supportsEagerToolInputStreaming: false,
-                supportsCacheControlOnTools: false,
-                supportsLongCacheRetention: false,
-            },
         },
         "accounts/fireworks/models/minimax-m2p5": {
             id: "accounts/fireworks/models/minimax-m2p5",
@@ -3946,6 +3719,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -3956,12 +3730,6 @@ export const MODELS = {
             },
             contextWindow: 196608,
             maxTokens: 196608,
-            compat: {
-                sendSessionAffinityHeaders: true,
-                supportsEagerToolInputStreaming: false,
-                supportsCacheControlOnTools: false,
-                supportsLongCacheRetention: false,
-            },
         },
         "accounts/fireworks/models/minimax-m2p7": {
             id: "accounts/fireworks/models/minimax-m2p7",
@@ -3969,6 +3737,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -3979,12 +3748,6 @@ export const MODELS = {
             },
             contextWindow: 196608,
             maxTokens: 196608,
-            compat: {
-                sendSessionAffinityHeaders: true,
-                supportsEagerToolInputStreaming: false,
-                supportsCacheControlOnTools: false,
-                supportsLongCacheRetention: false,
-            },
         },
         "accounts/fireworks/models/qwen3p6-plus": {
             id: "accounts/fireworks/models/qwen3p6-plus",
@@ -3992,6 +3755,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -4002,12 +3766,6 @@ export const MODELS = {
             },
             contextWindow: 128000,
             maxTokens: 8192,
-            compat: {
-                sendSessionAffinityHeaders: true,
-                supportsEagerToolInputStreaming: false,
-                supportsCacheControlOnTools: false,
-                supportsLongCacheRetention: false,
-            },
         },
         "accounts/fireworks/routers/kimi-k2p5-turbo": {
             id: "accounts/fireworks/routers/kimi-k2p5-turbo",
@@ -4015,6 +3773,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -4025,12 +3784,6 @@ export const MODELS = {
             },
             contextWindow: 256000,
             maxTokens: 256000,
-            compat: {
-                sendSessionAffinityHeaders: true,
-                supportsEagerToolInputStreaming: false,
-                supportsCacheControlOnTools: false,
-                supportsLongCacheRetention: false,
-            },
         },
     },
     "github-copilot": {
@@ -4109,25 +3862,6 @@ export const MODELS = {
             contextWindow: 144000,
             maxTokens: 64000,
         },
-        "claude-sonnet-4": {
-            id: "claude-sonnet-4",
-            name: "Claude Sonnet 4",
-            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" },
-            compat: { "supportsEagerToolInputStreaming": false },
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 216000,
-            maxTokens: 16000,
-        },
         "claude-sonnet-4.5": {
             id: "claude-sonnet-4.5",
             name: "Claude Sonnet 4.5",
@@ -4173,121 +3907,7 @@ export const MODELS = {
             baseUrl: "https://api.individual.githubcopilot.com",
             headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
             compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 64000,
-        },
-        "gemini-3-flash-preview": {
-            id: "gemini-3-flash-preview",
-            name: "Gemini 3 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: 128000,
-            maxTokens: 64000,
-        },
-        "gemini-3-pro-preview": {
-            id: "gemini-3-pro-preview",
-            name: "Gemini 3 Pro Preview",
-            api: "openai-completions",
-            provider: "github-copilot",
-            baseUrl: "https://api.individual.githubcopilot.com",
-            headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 64000,
-        },
-        "gemini-3.1-pro-preview": {
-            id: "gemini-3.1-pro-preview",
-            name: "Gemini 3.1 Pro Preview",
-            api: "openai-completions",
-            provider: "github-copilot",
-            baseUrl: "https://api.individual.githubcopilot.com",
-            headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 64000,
-        },
-        "gpt-4.1": {
-            id: "gpt-4.1",
-            name: "GPT-4.1",
-            api: "openai-completions",
-            provider: "github-copilot",
-            baseUrl: "https://api.individual.githubcopilot.com",
-            headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 16384,
-        },
-        "gpt-4o": {
-            id: "gpt-4o",
-            name: "GPT-4o",
-            api: "openai-completions",
-            provider: "github-copilot",
-            baseUrl: "https://api.individual.githubcopilot.com",
-            headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 4096,
-        },
-        "gpt-5": {
-            id: "gpt-5",
-            name: "GPT-5",
-            api: "openai-responses",
-            provider: "github-copilot",
-            baseUrl: "https://api.individual.githubcopilot.com",
-            headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
-            reasoning: true,
-            thinkingLevelMap: { "off": null },
+            reasoning: false,
             input: ["text", "image"],
             cost: {
                 input: 0,
@@ -4296,17 +3916,17 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 128000,
+            maxTokens: 64000,
         },
-        "gpt-5-mini": {
-            id: "gpt-5-mini",
-            name: "GPT-5-mini",
-            api: "openai-responses",
+        "gemini-3-flash-preview": {
+            id: "gemini-3-flash-preview",
+            name: "Gemini 3 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,
-            thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
                 input: 0,
@@ -4314,18 +3934,18 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 264000,
+            contextWindow: 128000,
             maxTokens: 64000,
         },
-        "gpt-5.1": {
-            id: "gpt-5.1",
-            name: "GPT-5.1",
-            api: "openai-responses",
+        "gemini-3.1-pro-preview": {
+            id: "gemini-3.1-pro-preview",
+            name: "Gemini 3.1 Pro Preview",
+            api: "openai-completions",
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
             headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
             reasoning: true,
-            thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
                 input: 0,
@@ -4333,18 +3953,18 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 264000,
+            contextWindow: 128000,
             maxTokens: 64000,
         },
-        "gpt-5.1-codex": {
-            id: "gpt-5.1-codex",
-            name: "GPT-5.1-Codex",
-            api: "openai-responses",
+        "gpt-4.1": {
+            id: "gpt-4.1",
+            name: "GPT-4.1",
+            api: "openai-completions",
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
             headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
-            reasoning: true,
-            thinkingLevelMap: { "off": null },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
+            reasoning: false,
             input: ["text", "image"],
             cost: {
                 input: 0,
@@ -4352,18 +3972,18 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 400000,
-            maxTokens: 128000,
+            contextWindow: 128000,
+            maxTokens: 16384,
         },
-        "gpt-5.1-codex-max": {
-            id: "gpt-5.1-codex-max",
-            name: "GPT-5.1-Codex-max",
-            api: "openai-responses",
+        "gpt-4o": {
+            id: "gpt-4o",
+            name: "GPT-4o",
+            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" },
-            reasoning: true,
-            thinkingLevelMap: { "off": null },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
+            reasoning: false,
             input: ["text", "image"],
             cost: {
                 input: 0,
@@ -4371,12 +3991,12 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 400000,
-            maxTokens: 128000,
+            contextWindow: 128000,
+            maxTokens: 4096,
         },
-        "gpt-5.1-codex-mini": {
-            id: "gpt-5.1-codex-mini",
-            name: "GPT-5.1-Codex-mini",
+        "gpt-5-mini": {
+            id: "gpt-5-mini",
+            name: "GPT-5-mini",
             api: "openai-responses",
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
@@ -4390,8 +4010,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 400000,
-            maxTokens: 128000,
+            contextWindow: 264000,
+            maxTokens: 64000,
         },
         "gpt-5.2": {
             id: "gpt-5.2",
@@ -4641,7 +4261,7 @@ export const MODELS = {
             cost: {
                 input: 0.1,
                 output: 0.4,
-                cacheRead: 0.025,
+                cacheRead: 0.01,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -4832,7 +4452,7 @@ export const MODELS = {
                 input: 0.25,
                 output: 1.5,
                 cacheRead: 0.025,
-                cacheWrite: 1,
+                cacheWrite: 0,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -4850,7 +4470,7 @@ export const MODELS = {
                 input: 0.25,
                 output: 1.5,
                 cacheRead: 0.025,
-                cacheWrite: 1,
+                cacheWrite: 0,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -4922,95 +4542,303 @@ export const MODELS = {
                 cacheRead: 0.025,
                 cacheWrite: 0,
             },
-            contextWindow: 1048576,
-            maxTokens: 65536,
+            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",
+            api: "google-generative-ai",
+            provider: "google",
+            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": null, "medium": null, "high": "HIGH" },
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 8192,
+        },
+        "gemma-4-31b-it": {
+            id: "gemma-4-31b-it",
+            name: "Gemma 4 31B",
+            api: "google-generative-ai",
+            provider: "google",
+            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": null, "medium": null, "high": "HIGH" },
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 8192,
+        },
+    },
+    "google-antigravity": {
+        "claude-opus-4": {
+            id: "claude-opus-4",
+            name: "Claude Opus 4",
+            api: "google-gemini-cli",
+            provider: "google-antigravity",
+            baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 32000,
+        },
+        "claude-sonnet-4": {
+            id: "claude-sonnet-4",
+            name: "Claude Sonnet 4",
+            api: "google-gemini-cli",
+            provider: "google-antigravity",
+            baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 16384,
+        },
+        "gemini-3-flash": {
+            id: "gemini-3-flash",
+            name: "Gemini 3 Flash",
+            api: "google-gemini-cli",
+            provider: "google-antigravity",
+            baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
+        "gemini-3-pro-preview": {
+            id: "gemini-3-pro-preview",
+            name: "Gemini 3 Pro Preview",
+            api: "google-gemini-cli",
+            provider: "google-antigravity",
+            baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
+        "gpt-oss-120b": {
+            id: "gpt-oss-120b",
+            name: "GPT OSS 120B",
+            api: "google-gemini-cli",
+            provider: "google-antigravity",
+            baseUrl: "https://daily-cloudcode-pa.sandbox.googleapis.com",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 16384,
+        },
+    },
+    "google-gemini-cli": {
+        "claude-opus-4": {
+            id: "claude-opus-4",
+            name: "Claude Opus 4",
+            api: "google-gemini-cli",
+            provider: "google-gemini-cli",
+            baseUrl: "https://cloudcode-pa.googleapis.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 15,
+                output: 75,
+                cacheRead: 1.5,
+                cacheWrite: 18.75,
+            },
+            contextWindow: 200000,
+            maxTokens: 32000,
+        },
+        "claude-sonnet-4": {
+            id: "claude-sonnet-4",
+            name: "Claude Sonnet 4",
+            api: "google-gemini-cli",
+            provider: "google-gemini-cli",
+            baseUrl: "https://cloudcode-pa.googleapis.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 3,
+                output: 15,
+                cacheRead: 0.3,
+                cacheWrite: 3.75,
+            },
+            contextWindow: 200000,
+            maxTokens: 16384,
         },
-        "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,
+        "gemini-2.0-flash": {
+            id: "gemini-2.0-flash",
+            name: "Gemini 2.0 Flash",
+            api: "google-gemini-cli",
+            provider: "google-gemini-cli",
+            baseUrl: "https://cloudcode-pa.googleapis.com",
+            reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.5,
-                output: 2,
+                input: 0.075,
+                output: 0.3,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 8000,
+            contextWindow: 1048576,
+            maxTokens: 8192,
         },
-        "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",
+        "gemini-2.5-flash": {
+            id: "gemini-2.5-flash",
+            name: "Gemini 2.5 Flash",
+            api: "google-gemini-cli",
+            provider: "google-gemini-cli",
+            baseUrl: "https://cloudcode-pa.googleapis.com",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
-                input: 0.5,
-                output: 2,
-                cacheRead: 0,
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0.0375,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 1048576,
             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,
+        "gemini-2.5-pro": {
+            id: "gemini-2.5-pro",
+            name: "Gemini 2.5 Pro",
+            api: "google-gemini-cli",
+            provider: "google-gemini-cli",
+            baseUrl: "https://cloudcode-pa.googleapis.com",
+            reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 1.25,
+                output: 10,
+                cacheRead: 0.3125,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 8192,
+            contextWindow: 1048576,
+            maxTokens: 65536,
         },
-        "gemma-4-26b-a4b-it": {
-            id: "gemma-4-26b-a4b-it",
-            name: "Gemma 4 26B",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+        "gemini-3-flash-preview": {
+            id: "gemini-3-flash-preview",
+            name: "Gemini 3 Flash Preview",
+            api: "google-gemini-cli",
+            provider: "google-gemini-cli",
+            baseUrl: "https://cloudcode-pa.googleapis.com",
             reasoning: true,
-            thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": null, "medium": null, "high": "HIGH" },
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0.0375,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 8192,
+            contextWindow: 1048576,
+            maxTokens: 65536,
         },
-        "gemma-4-31b-it": {
-            id: "gemma-4-31b-it",
-            name: "Gemma 4 31B",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+        "gemini-3-pro-preview": {
+            id: "gemini-3-pro-preview",
+            name: "Gemini 3 Pro Preview",
+            api: "google-gemini-cli",
+            provider: "google-gemini-cli",
+            baseUrl: "https://cloudcode-pa.googleapis.com",
             reasoning: true,
-            thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": null, "medium": null, "high": "HIGH" },
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 1.25,
+                output: 10,
+                cacheRead: 0.3125,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 8192,
+            contextWindow: 1048576,
+            maxTokens: 65536,
         },
     },
     "google-vertex": {
@@ -7867,6 +7695,25 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "deepseek-v4-flash-free": {
+            id: "deepseek-v4-flash-free",
+            name: "DeepSeek V4 Flash Free",
+            api: "openai-completions",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 128000,
+        },
         "gemini-3-flash": {
             id: "gemini-3-flash",
             name: "Gemini 3 Flash",
@@ -8225,23 +8072,6 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
-        "hy3-preview-free": {
-            id: "hy3-preview-free",
-            name: "Hy3 preview Free",
-            api: "openai-completions",
-            provider: "opencode",
-            baseUrl: "https://opencode.ai/zen/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 64000,
-        },
         "kimi-k2.5": {
             id: "kimi-k2.5",
             name: "Kimi K2.5",
@@ -8378,6 +8208,23 @@ 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": {
@@ -8523,9 +8370,9 @@ export const MODELS = {
         "minimax-m2.5": {
             id: "minimax-m2.5",
             name: "MiniMax M2.5",
-            api: "openai-completions",
+            api: "anthropic-messages",
             provider: "opencode-go",
-            baseUrl: "https://opencode.ai/zen/go/v1",
+            baseUrl: "https://opencode.ai/zen/go",
             reasoning: true,
             input: ["text"],
             cost: {
@@ -8745,40 +8592,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 8192,
         },
-        "anthropic/claude-3.7-sonnet": {
-            id: "anthropic/claude-3.7-sonnet",
-            name: "Anthropic: Claude 3.7 Sonnet",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 64000,
-        },
-        "anthropic/claude-3.7-sonnet:thinking": {
-            id: "anthropic/claude-3.7-sonnet:thinking",
-            name: "Anthropic: Claude 3.7 Sonnet (thinking)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 64000,
-        },
         "anthropic/claude-haiku-4.5": {
             id: "anthropic/claude-haiku-4.5",
             name: "Anthropic: Claude Haiku 4.5",
@@ -8901,6 +8714,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "anthropic/claude-opus-4.7-fast": {
+            id: "anthropic/claude-opus-4.7-fast",
+            name: "Anthropic: Claude Opus 4.7 (Fast)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 30,
+                output: 150,
+                cacheRead: 3,
+                cacheWrite: 37.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "anthropic/claude-sonnet-4": {
             id: "anthropic/claude-sonnet-4",
             name: "Anthropic: Claude Sonnet 4",
@@ -8986,6 +8817,23 @@ 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",
@@ -9068,7 +8916,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 120000,
+            contextWindow: 131072,
             maxTokens: 8000,
         },
         "baidu/ernie-4.5-vl-28b-a3b": {
@@ -9085,7 +8933,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 30000,
+            contextWindow: 131072,
             maxTokens: 8000,
         },
         "bytedance-seed/seed-1.6": {
@@ -9233,13 +9081,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.15,
-                output: 0.75,
-                cacheRead: 0,
+                input: 0.21,
+                output: 0.7899999999999999,
+                cacheRead: 0.13,
                 cacheWrite: 0,
             },
-            contextWindow: 32768,
-            maxTokens: 7168,
+            contextWindow: 163840,
+            maxTokens: 32768,
         },
         "deepseek/deepseek-r1": {
             id: "deepseek/deepseek-r1",
@@ -9255,7 +9103,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 64000,
+            contextWindow: 163840,
             maxTokens: 16000,
         },
         "deepseek/deepseek-r1-0528": {
@@ -9337,9 +9185,28 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
             cost: {
-                input: 0.14,
-                output: 0.28,
-                cacheRead: 0.0028,
+                input: 0.112,
+                output: 0.224,
+                cacheRead: 0.022,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 4096,
+        },
+        "deepseek/deepseek-v4-flash:free": {
+            id: "deepseek/deepseek-v4-flash:free",
+            name: "DeepSeek: DeepSeek V4 Flash (free)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -9599,7 +9466,7 @@ export const MODELS = {
                 cacheRead: 0.19999999999999998,
                 cacheWrite: 0.375,
             },
-            contextWindow: 1048576,
+            contextWindow: 1048756,
             maxTokens: 65536,
         },
         "google/gemma-3-12b-it": {
@@ -9679,8 +9546,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.13,
-                output: 0.38,
+                input: 0.12,
+                output: 0.37,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -9765,13 +9632,30 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.08,
-                output: 0.24,
-                cacheRead: 0.016,
+                input: 0.01,
+                output: 0.03,
+                cacheRead: 0.002,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 32768,
+        },
+        "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: 0.075,
+                output: 0.625,
+                cacheRead: 0.015,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 32768,
+            maxTokens: 65536,
         },
         "kwaipilot/kat-coder-pro-v2": {
             id: "kwaipilot/kat-coder-pro-v2",
@@ -9821,7 +9705,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 16384,
+            contextWindow: 131072,
             maxTokens: 16384,
         },
         "meta-llama/llama-3.3-70b-instruct": {
@@ -9855,7 +9739,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 65536,
+            contextWindow: 131072,
             maxTokens: 4096,
         },
         "meta-llama/llama-4-scout": {
@@ -9872,7 +9756,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 327680,
+            contextWindow: 10000000,
             maxTokens: 16384,
         },
         "minimax/minimax-m1": {
@@ -9906,7 +9790,7 @@ export const MODELS = {
                 cacheRead: 0.03,
                 cacheWrite: 0,
             },
-            contextWindow: 196608,
+            contextWindow: 204800,
             maxTokens: 196608,
         },
         "minimax/minimax-m2.1": {
@@ -9923,7 +9807,7 @@ export const MODELS = {
                 cacheRead: 0.03,
                 cacheWrite: 0,
             },
-            contextWindow: 196608,
+            contextWindow: 204800,
             maxTokens: 196608,
         },
         "minimax/minimax-m2.5": {
@@ -9937,11 +9821,11 @@ export const MODELS = {
             cost: {
                 input: 0.15,
                 output: 1.15,
-                cacheRead: 0.03,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 196608,
-            maxTokens: 131072,
+            contextWindow: 204800,
+            maxTokens: 196608,
         },
         "minimax/minimax-m2.5:free": {
             id: "minimax/minimax-m2.5:free",
@@ -9957,7 +9841,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 196608,
+            contextWindow: 204800,
             maxTokens: 8192,
         },
         "minimax/minimax-m2.7": {
@@ -9969,13 +9853,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.3,
+                input: 0.27899999999999997,
                 output: 1.2,
-                cacheRead: 0.059,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 196608,
-            maxTokens: 4096,
+            contextWindow: 204800,
+            maxTokens: 131072,
         },
         "mistralai/codestral-2508": {
             id: "mistralai/codestral-2508",
@@ -10360,8 +10244,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.39999999999999997,
-                output: 2,
+                input: 0.6,
+                output: 2.5,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -10379,7 +10263,7 @@ export const MODELS = {
             cost: {
                 input: 0.6,
                 output: 2.5,
-                cacheRead: 0.15,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -10411,13 +10295,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.75,
-                output: 3.5,
-                cacheRead: 0.15,
+                input: 0.73,
+                output: 3.49,
+                cacheRead: 0.25,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 262142,
         },
         "nex-agi/deepseek-v3.1-nex-n1": {
             id: "nex-agi/deepseek-v3.1-nex-n1",
@@ -10518,7 +10402,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
+            contextWindow: 1000000,
             maxTokens: 4096,
         },
         "nvidia/nemotron-3-super-120b-a12b:free": {
@@ -10535,7 +10419,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
+            contextWindow: 1000000,
             maxTokens: 262144,
         },
         "nvidia/nemotron-nano-12b-v2-vl:free": {
@@ -11686,7 +11570,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 32768,
+            contextWindow: 131072,
             maxTokens: 16384,
         },
         "qwen/qwen-2.5-7b-instruct": {
@@ -11703,26 +11587,9 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 32768,
+            contextWindow: 131072,
             maxTokens: 32768,
         },
-        "qwen/qwen-max": {
-            id: "qwen/qwen-max",
-            name: "Qwen: Qwen-Max ",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 1.04,
-                output: 4.16,
-                cacheRead: 0.20800000000000002,
-                cacheWrite: 0,
-            },
-            contextWindow: 32768,
-            maxTokens: 8192,
-        },
         "qwen/qwen-plus": {
             id: "qwen/qwen-plus",
             name: "Qwen: Qwen-Plus",
@@ -11774,40 +11641,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 32768,
         },
-        "qwen/qwen-turbo": {
-            id: "qwen/qwen-turbo",
-            name: "Qwen: Qwen-Turbo",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.0325,
-                output: 0.13,
-                cacheRead: 0.006500000000000001,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "qwen/qwen-vl-max": {
-            id: "qwen/qwen-vl-max",
-            name: "Qwen: Qwen VL Max",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.52,
-                output: 2.08,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 32768,
-        },
         "qwen/qwen3-14b": {
             id: "qwen/qwen3-14b",
             name: "Qwen: Qwen3 14B",
@@ -11817,12 +11650,12 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.06,
+                input: 0.09999999999999999,
                 output: 0.24,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 40960,
+            contextWindow: 131702,
             maxTokens: 40960,
         },
         "qwen/qwen3-235b-a22b": {
@@ -11873,7 +11706,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 262144,
             maxTokens: 4096,
         },
         "qwen/qwen3-30b-a3b": {
@@ -11890,7 +11723,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 40960,
+            contextWindow: 131072,
             maxTokens: 20000,
         },
         "qwen/qwen3-30b-a3b-instruct-2507": {
@@ -11937,12 +11770,12 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.08,
-                output: 0.24,
-                cacheRead: 0.04,
+                output: 0.28,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 40960,
-            maxTokens: 40960,
+            contextWindow: 131072,
+            maxTokens: 16384,
         },
         "qwen/qwen3-8b": {
             id: "qwen/qwen3-8b",
@@ -11958,7 +11791,7 @@ export const MODELS = {
                 cacheRead: 0.049999999999999996,
                 cacheWrite: 0,
             },
-            contextWindow: 40960,
+            contextWindow: 131072,
             maxTokens: 8192,
         },
         "qwen/qwen3-coder": {
@@ -11975,7 +11808,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
+            contextWindow: 1048576,
             maxTokens: 65536,
         },
         "qwen/qwen3-coder-30b-a3b-instruct": {
@@ -12060,7 +11893,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262000,
+            contextWindow: 1048576,
             maxTokens: 262000,
         },
         "qwen/qwen3-max": {
@@ -12145,7 +11978,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 262144,
             maxTokens: 32768,
         },
         "qwen/qwen3-vl-235b-a22b-instruct": {
@@ -12196,7 +12029,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 262144,
             maxTokens: 32768,
         },
         "qwen/qwen3-vl-30b-a3b-thinking": {
@@ -12230,7 +12063,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 262144,
             maxTokens: 32768,
         },
         "qwen/qwen3-vl-8b-instruct": {
@@ -12247,7 +12080,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 256000,
             maxTokens: 32768,
         },
         "qwen/qwen3-vl-8b-thinking": {
@@ -12264,7 +12097,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 256000,
             maxTokens: 32768,
         },
         "qwen/qwen3.5-122b-a10b": {
@@ -12395,8 +12228,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.39999999999999997,
-                output: 2.4,
+                input: 0.3,
+                output: 1.7999999999999998,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -12446,10 +12279,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.25,
-                output: 1.5,
+                input: 0.1875,
+                output: 1.125,
                 cacheRead: 0,
-                cacheWrite: 0.3125,
+                cacheWrite: 0.234375,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
@@ -12512,270 +12345,134 @@ export const MODELS = {
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 1,
-                output: 3,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 128000,
-        },
-        "sao10k/l3-euryale-70b": {
-            id: "sao10k/l3-euryale-70b",
-            name: "Sao10k: Llama 3 Euryale 70B v2.1",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 1.48,
-                output: 1.48,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 8192,
-            maxTokens: 8192,
-        },
-        "sao10k/l3.1-euryale-70b": {
-            id: "sao10k/l3.1-euryale-70b",
-            name: "Sao10K: Llama 3.1 Euryale 70B v2.2",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.85,
-                output: 0.85,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 16384,
-        },
-        "stepfun/step-3.5-flash": {
-            id: "stepfun/step-3.5-flash",
-            name: "StepFun: Step 3.5 Flash",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.09999999999999999,
-                output: 0.3,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 65536,
-        },
-        "tencent/hy3-preview:free": {
-            id: "tencent/hy3-preview:free",
-            name: "Tencent: Hy3 preview (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: 262144,
-        },
-        "thedrummer/rocinante-12b": {
-            id: "thedrummer/rocinante-12b",
-            name: "TheDrummer: Rocinante 12B",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.16999999999999998,
-                output: 0.43,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 32768,
-            maxTokens: 32768,
-        },
-        "thedrummer/unslopnemo-12b": {
-            id: "thedrummer/unslopnemo-12b",
-            name: "TheDrummer: UnslopNemo 12B",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.39999999999999997,
-                output: 0.39999999999999997,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 32768,
-            maxTokens: 32768,
-        },
-        "tngtech/deepseek-r1t2-chimera": {
-            id: "tngtech/deepseek-r1t2-chimera",
-            name: "TNG: DeepSeek R1T2 Chimera",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 1.1,
-                cacheRead: 0.15,
-                cacheWrite: 0,
-            },
-            contextWindow: 163840,
-            maxTokens: 163840,
-        },
-        "upstage/solar-pro-3": {
-            id: "upstage/solar-pro-3",
-            name: "Upstage: Solar Pro 3",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0.015,
+            input: ["text"],
+            cost: {
+                input: 1,
+                output: 3,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 4096,
+            contextWindow: 256000,
+            maxTokens: 128000,
         },
-        "x-ai/grok-3": {
-            id: "x-ai/grok-3",
-            name: "xAI: Grok 3",
+        "sao10k/l3-euryale-70b": {
+            id: "sao10k/l3-euryale-70b",
+            name: "Sao10k: Llama 3 Euryale 70B v2.1",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.75,
+                input: 1.48,
+                output: 1.48,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 4096,
+            contextWindow: 8192,
+            maxTokens: 8192,
         },
-        "x-ai/grok-3-beta": {
-            id: "x-ai/grok-3-beta",
-            name: "xAI: Grok 3 Beta",
+        "sao10k/l3.1-euryale-70b": {
+            id: "sao10k/l3.1-euryale-70b",
+            name: "Sao10K: Llama 3.1 Euryale 70B v2.2",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.75,
+                input: 0.85,
+                output: 0.85,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
-        "x-ai/grok-3-mini": {
-            id: "x-ai/grok-3-mini",
-            name: "xAI: Grok 3 Mini",
+        "stepfun/step-3.5-flash": {
+            id: "stepfun/step-3.5-flash",
+            name: "StepFun: Step 3.5 Flash",
             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,
+                input: 0.09999999999999999,
+                output: 0.3,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 4096,
+            contextWindow: 262144,
+            maxTokens: 65536,
         },
-        "x-ai/grok-3-mini-beta": {
-            id: "x-ai/grok-3-mini-beta",
-            name: "xAI: Grok 3 Mini Beta",
+        "tencent/hy3-preview": {
+            id: "tencent/hy3-preview",
+            name: "Tencent: Hy3 preview",
             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,
+                input: 0.06599999999999999,
+                output: 0.26,
+                cacheRead: 0.029,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 4096,
+            contextWindow: 262144,
+            maxTokens: 262144,
         },
-        "x-ai/grok-4": {
-            id: "x-ai/grok-4",
-            name: "xAI: Grok 4",
+        "thedrummer/rocinante-12b": {
+            id: "thedrummer/rocinante-12b",
+            name: "TheDrummer: Rocinante 12B",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
+            reasoning: false,
+            input: ["text"],
             cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.75,
+                input: 0.16999999999999998,
+                output: 0.43,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 4096,
+            contextWindow: 32768,
+            maxTokens: 32768,
         },
-        "x-ai/grok-4-fast": {
-            id: "x-ai/grok-4-fast",
-            name: "xAI: Grok 4 Fast",
+        "thedrummer/unslopnemo-12b": {
+            id: "thedrummer/unslopnemo-12b",
+            name: "TheDrummer: UnslopNemo 12B",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
+            reasoning: false,
+            input: ["text"],
             cost: {
-                input: 0.19999999999999998,
-                output: 0.5,
-                cacheRead: 0.049999999999999996,
+                input: 0.39999999999999997,
+                output: 0.39999999999999997,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 2000000,
-            maxTokens: 30000,
+            contextWindow: 32768,
+            maxTokens: 32768,
         },
-        "x-ai/grok-4.1-fast": {
-            id: "x-ai/grok-4.1-fast",
-            name: "xAI: Grok 4.1 Fast",
+        "upstage/solar-pro-3": {
+            id: "upstage/solar-pro-3",
+            name: "Upstage: Solar Pro 3",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
-                input: 0.19999999999999998,
-                output: 0.5,
-                cacheRead: 0.049999999999999996,
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0.015,
                 cacheWrite: 0,
             },
-            contextWindow: 2000000,
-            maxTokens: 30000,
+            contextWindow: 128000,
+            maxTokens: 4096,
         },
         "x-ai/grok-4.20": {
             id: "x-ai/grok-4.20",
@@ -12811,23 +12508,6 @@ 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",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.19999999999999998,
-                output: 1.5,
-                cacheRead: 0.02,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 10000,
-        },
         "xiaomi/mimo-v2-flash": {
             id: "xiaomi/mimo-v2-flash",
             name: "Xiaomi: MiMo-V2-Flash",
@@ -12837,9 +12517,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09,
-                output: 0.29,
-                cacheRead: 0.045,
+                input: 0.09999999999999999,
+                output: 0.3,
+                cacheRead: 0.01,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -12911,7 +12591,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 131072,
+            maxTokens: 16384,
         },
         "z-ai/glm-4-32b": {
             id: "z-ai/glm-4-32b",
@@ -13007,13 +12687,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.39,
-                output: 1.9,
-                cacheRead: 0,
+                input: 0.43,
+                output: 1.74,
+                cacheRead: 0.08,
                 cacheWrite: 0,
             },
-            contextWindow: 204800,
-            maxTokens: 204800,
+            contextWindow: 202752,
+            maxTokens: 131072,
         },
         "z-ai/glm-4.6v": {
             id: "z-ai/glm-4.6v",
@@ -13109,13 +12789,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.0499999999999998,
-                output: 3.5,
-                cacheRead: 0.5249999999999999,
+                input: 0.98,
+                output: 3.08,
+                cacheRead: 0.182,
                 cacheWrite: 0,
             },
             contextWindow: 202752,
-            maxTokens: 65535,
+            maxTokens: 4096,
         },
         "z-ai/glm-5v-turbo": {
             id: "z-ai/glm-5v-turbo",
@@ -13228,13 +12908,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.75,
-                output: 3.5,
-                cacheRead: 0.15,
+                input: 0.73,
+                output: 3.49,
+                cacheRead: 0.25,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 262142,
         },
         "~openai/gpt-latest": {
             id: "~openai/gpt-latest",
@@ -13934,23 +13614,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 8192,
         },
-        "anthropic/claude-3.7-sonnet": {
-            id: "anthropic/claude-3.7-sonnet",
-            name: "Claude 3.7 Sonnet",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 8192,
-        },
         "anthropic/claude-haiku-4.5": {
             id: "anthropic/claude-haiku-4.5",
             name: "Claude Haiku 4.5",
@@ -15633,7 +15296,7 @@ export const MODELS = {
         },
         "openai/gpt-oss-20b": {
             id: "openai/gpt-oss-20b",
-            name: "GPT OSS 120B",
+            name: "GPT OSS 20B",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
@@ -15740,185 +15403,66 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 20,
-                output: 80,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 100000,
-        },
-        "openai/o4-mini": {
-            id: "openai/o4-mini",
-            name: "o4-mini",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1.1,
-                output: 4.4,
-                cacheRead: 0.275,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 100000,
-        },
-        "perplexity/sonar": {
-            id: "perplexity/sonar",
-            name: "Sonar",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 127000,
-            maxTokens: 8000,
-        },
-        "perplexity/sonar-pro": {
-            id: "perplexity/sonar-pro",
-            name: "Sonar Pro",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            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"],
+            input: ["text", "image"],
             cost: {
-                input: 0.6,
-                output: 4,
+                input: 20,
+                output: 80,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 131072,
+            contextWindow: 200000,
+            maxTokens: 100000,
         },
-        "xai/grok-4": {
-            id: "xai/grok-4",
-            name: "Grok 4",
+        "openai/o4-mini": {
+            id: "openai/o4-mini",
+            name: "o4-mini",
             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,
+                input: 1.1,
+                output: 4.4,
+                cacheRead: 0.275,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 256000,
+            contextWindow: 200000,
+            maxTokens: 100000,
         },
-        "xai/grok-4-fast-non-reasoning": {
-            id: "xai/grok-4-fast-non-reasoning",
-            name: "Grok 4 Fast Non-Reasoning",
+        "perplexity/sonar": {
+            id: "perplexity/sonar",
+            name: "Sonar",
             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,
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 2000000,
-            maxTokens: 256000,
+            contextWindow: 127000,
+            maxTokens: 8000,
         },
-        "xai/grok-4-fast-reasoning": {
-            id: "xai/grok-4-fast-reasoning",
-            name: "Grok 4 Fast Reasoning",
+        "perplexity/sonar-pro": {
+            id: "perplexity/sonar-pro",
+            name: "Sonar Pro",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
+            reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.19999999999999998,
-                output: 0.5,
-                cacheRead: 0.049999999999999996,
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 2000000,
-            maxTokens: 256000,
+            contextWindow: 200000,
+            maxTokens: 8000,
         },
         "xai/grok-4.1-fast-non-reasoning": {
             id: "xai/grok-4.1-fast-non-reasoning",
@@ -15934,8 +15478,8 @@ 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",
@@ -15951,8 +15495,8 @@ 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",
@@ -16073,23 +15617,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 1000000,
         },
-        "xai/grok-code-fast-1": {
-            id: "xai/grok-code-fast-1",
-            name: "Grok Code Fast 1",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.19999999999999998,
-                output: 1.5,
-                cacheRead: 0.02,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 256000,
-        },
         "xiaomi/mimo-v2-flash": {
             id: "xiaomi/mimo-v2-flash",
             name: "MiMo V2 Flash",
@@ -16483,227 +16010,6 @@ export const MODELS = {
             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)",
@@ -16778,7 +16084,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "xai",
             baseUrl: "https://api.x.ai/v1",
-            reasoning: true,
+            reasoning: false,
             input: ["text"],
             cost: {
                 input: 0.2,
@@ -16786,8 +16092,8 @@ export const MODELS = {
                 cacheRead: 0.02,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 10000,
+            contextWindow: 32768,
+            maxTokens: 8192,
         },
         "grok-vision-beta": {
             id: "grok-vision-beta",