@earendil-works/pi-ai 0.74.0 → 0.75.0

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)",
@@ -689,22 +553,57 @@ 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"],
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
             cost: {
-                input: 2.4,
-                output: 2.4,
-                cacheRead: 0,
-                cacheWrite: 0,
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
             },
-            contextWindow: 128000,
-            maxTokens: 4096,
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
+        "jp.anthropic.claude-sonnet-4-5-20250929-v1:0": {
+            id: "jp.anthropic.claude-sonnet-4-5-20250929-v1:0",
+            name: "Claude Sonnet 4.5 (JP)",
+            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,
+        },
+        "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: true,
+            input: ["text", "image"],
+            cost: {
+                input: 3,
+                output: 15,
+                cacheRead: 0.3,
+                cacheWrite: 3.75,
+            },
+            contextWindow: 1000000,
+            maxTokens: 64000,
         },
         "meta.llama3-1-70b-instruct-v1:0": {
             id: "meta.llama3-1-70b-instruct-v1:0",
@@ -740,128 +639,60 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 4096,
         },
-        "meta.llama3-2-11b-instruct-v1:0": {
-            id: "meta.llama3-2-11b-instruct-v1:0",
-            name: "Llama 3.2 11B Instruct",
+        "meta.llama3-3-70b-instruct-v1:0": {
+            id: "meta.llama3-3-70b-instruct-v1:0",
+            name: "Llama 3.3 70B Instruct",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
             reasoning: false,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
-                input: 0.16,
-                output: 0.16,
+                input: 0.72,
+                output: 0.72,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
             maxTokens: 4096,
         },
-        "meta.llama3-2-1b-instruct-v1:0": {
-            id: "meta.llama3-2-1b-instruct-v1:0",
-            name: "Llama 3.2 1B Instruct",
+        "meta.llama4-maverick-17b-instruct-v1:0": {
+            id: "meta.llama4-maverick-17b-instruct-v1:0",
+            name: "Llama 4 Maverick 17B Instruct",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
             reasoning: false,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
-                input: 0.1,
-                output: 0.1,
+                input: 0.24,
+                output: 0.97,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131000,
-            maxTokens: 4096,
+            contextWindow: 1000000,
+            maxTokens: 16384,
         },
-        "meta.llama3-2-3b-instruct-v1:0": {
-            id: "meta.llama3-2-3b-instruct-v1:0",
-            name: "Llama 3.2 3B Instruct",
+        "meta.llama4-scout-17b-instruct-v1:0": {
+            id: "meta.llama4-scout-17b-instruct-v1:0",
+            name: "Llama 4 Scout 17B Instruct",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
             reasoning: false,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
-                input: 0.15,
-                output: 0.15,
+                input: 0.17,
+                output: 0.66,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131000,
-            maxTokens: 4096,
+            contextWindow: 3500000,
+            maxTokens: 16384,
         },
-        "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,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 4096,
-        },
-        "meta.llama3-3-70b-instruct-v1:0": {
-            id: "meta.llama3-3-70b-instruct-v1:0",
-            name: "Llama 3.3 70B Instruct",
-            api: "bedrock-converse-stream",
-            provider: "amazon-bedrock",
-            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.72,
-                output: 0.72,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 4096,
-        },
-        "meta.llama4-maverick-17b-instruct-v1:0": {
-            id: "meta.llama4-maverick-17b-instruct-v1:0",
-            name: "Llama 4 Maverick 17B Instruct",
-            api: "bedrock-converse-stream",
-            provider: "amazon-bedrock",
-            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.24,
-                output: 0.97,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 16384,
-        },
-        "meta.llama4-scout-17b-instruct-v1:0": {
-            id: "meta.llama4-scout-17b-instruct-v1:0",
-            name: "Llama 4 Scout 17B Instruct",
-            api: "bedrock-converse-stream",
-            provider: "amazon-bedrock",
-            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.17,
-                output: 0.66,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 3500000,
-            maxTokens: 16384,
-        },
-        "minimax.minimax-m2": {
-            id: "minimax.minimax-m2",
-            name: "MiniMax M2",
+        "minimax.minimax-m2": {
+            id: "minimax.minimax-m2",
+            name: "MiniMax M2",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -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: {
@@ -3618,6 +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: {
@@ -3635,6 +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: {
@@ -3652,6 +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: {
@@ -3669,6 +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: {
@@ -3686,6 +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: {
@@ -3703,6 +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: {
@@ -3720,6 +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: {
@@ -3737,6 +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: {
@@ -3754,6 +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: {
@@ -3771,6 +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: {
@@ -3788,6 +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: {
@@ -3805,6 +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: {
@@ -3822,6 +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: {
@@ -3839,6 +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: {
@@ -3856,6 +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: {
@@ -3873,6 +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: {
@@ -3890,6 +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: {
@@ -3907,6 +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: {
@@ -3995,25 +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",
@@ -4089,25 +3937,6 @@ export const MODELS = {
             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",
@@ -4165,25 +3994,6 @@ export const MODELS = {
             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 },
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 128000,
-        },
         "gpt-5-mini": {
             id: "gpt-5-mini",
             name: "GPT-5-mini",
@@ -4192,7 +4002,7 @@ 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" },
             reasoning: true,
-            thinkingLevelMap: { "off": null },
+            thinkingLevelMap: { "off": null, "minimal": "low" },
             input: ["text", "image"],
             cost: {
                 input: 0,
@@ -4203,15 +4013,15 @@ export const MODELS = {
             contextWindow: 264000,
             maxTokens: 64000,
         },
-        "gpt-5.1": {
-            id: "gpt-5.1",
-            name: "GPT-5.1",
+        "gpt-5.2": {
+            id: "gpt-5.2",
+            name: "GPT-5.2",
             api: "openai-responses",
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
             headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
             reasoning: true,
-            thinkingLevelMap: { "off": null },
+            thinkingLevelMap: { "off": null, "minimal": "low", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
                 input: 0,
@@ -4222,15 +4032,15 @@ export const MODELS = {
             contextWindow: 264000,
             maxTokens: 64000,
         },
-        "gpt-5.1-codex": {
-            id: "gpt-5.1-codex",
-            name: "GPT-5.1-Codex",
+        "gpt-5.2-codex": {
+            id: "gpt-5.2-codex",
+            name: "GPT-5.2-Codex",
             api: "openai-responses",
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
             headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
             reasoning: true,
-            thinkingLevelMap: { "off": null },
+            thinkingLevelMap: { "off": null, "minimal": "low", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
                 input: 0,
@@ -4241,15 +4051,15 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
-        "gpt-5.1-codex-max": {
-            id: "gpt-5.1-codex-max",
-            name: "GPT-5.1-Codex-max",
+        "gpt-5.3-codex": {
+            id: "gpt-5.3-codex",
+            name: "GPT-5.3-Codex",
             api: "openai-responses",
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
             headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
             reasoning: true,
-            thinkingLevelMap: { "off": null },
+            thinkingLevelMap: { "off": null, "minimal": "low", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
                 input: 0,
@@ -4260,15 +4070,15 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
-        "gpt-5.1-codex-mini": {
-            id: "gpt-5.1-codex-mini",
-            name: "GPT-5.1-Codex-mini",
+        "gpt-5.4": {
+            id: "gpt-5.4",
+            name: "GPT-5.4",
             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 },
+            thinkingLevelMap: { "off": null, "minimal": "low", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
                 input: 0,
@@ -4279,15 +4089,15 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
-        "gpt-5.2": {
-            id: "gpt-5.2",
-            name: "GPT-5.2",
+        "gpt-5.4-mini": {
+            id: "gpt-5.4-mini",
+            name: "GPT-5.4 Mini",
             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, "xhigh": "xhigh" },
+            thinkingLevelMap: { "off": null, "minimal": "low", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
                 input: 0,
@@ -4295,18 +4105,18 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 264000,
-            maxTokens: 64000,
+            contextWindow: 400000,
+            maxTokens: 128000,
         },
-        "gpt-5.2-codex": {
-            id: "gpt-5.2-codex",
-            name: "GPT-5.2-Codex",
+        "gpt-5.5": {
+            id: "gpt-5.5",
+            name: "GPT-5.5",
             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, "xhigh": "xhigh" },
+            thinkingLevelMap: { "off": null, "minimal": "low", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
                 input: 0,
@@ -4317,92 +4127,16 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
-        "gpt-5.3-codex": {
-            id: "gpt-5.3-codex",
-            name: "GPT-5.3-Codex",
-            api: "openai-responses",
+        "grok-code-fast-1": {
+            id: "grok-code-fast-1",
+            name: "Grok Code Fast 1",
+            api: "openai-completions",
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
             headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
             reasoning: true,
-            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 400000,
-            maxTokens: 128000,
-        },
-        "gpt-5.4": {
-            id: "gpt-5.4",
-            name: "GPT-5.4",
-            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, "xhigh": "xhigh" },
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 400000,
-            maxTokens: 128000,
-        },
-        "gpt-5.4-mini": {
-            id: "gpt-5.4-mini",
-            name: "GPT-5.4 Mini",
-            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, "xhigh": "xhigh" },
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 400000,
-            maxTokens: 128000,
-        },
-        "gpt-5.5": {
-            id: "gpt-5.5",
-            name: "GPT-5.5",
-            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, "xhigh": "xhigh" },
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 400000,
-            maxTokens: 128000,
-        },
-        "grok-code-fast-1": {
-            id: "grok-code-fast-1",
-            name: "Grok Code Fast 1",
-            api: "openai-completions",
-            provider: "github-copilot",
-            baseUrl: "https://api.individual.githubcopilot.com",
-            headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
-            reasoning: true,
-            input: ["text"],
+            input: ["text"],
             cost: {
                 input: 0,
                 output: 0,
@@ -4527,7 +4261,7 @@ export const MODELS = {
             cost: {
                 input: 0.1,
                 output: 0.4,
-                cacheRead: 0.025,
+                cacheRead: 0.01,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -4705,6 +4439,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "gemini-3.1-flash-lite": {
+            id: "gemini-3.1-flash-lite",
+            name: "Gemini 3.1 Flash Lite",
+            api: "google-generative-ai",
+            provider: "google",
+            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+            reasoning: true,
+            thinkingLevelMap: { "off": null },
+            input: ["text", "image"],
+            cost: {
+                input: 0.25,
+                output: 1.5,
+                cacheRead: 0.025,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
         "gemini-3.1-flash-lite-preview": {
             id: "gemini-3.1-flash-lite-preview",
             name: "Gemini 3.1 Flash Lite Preview",
@@ -4718,7 +4470,7 @@ export const MODELS = {
                 input: 0.25,
                 output: 1.5,
                 cacheRead: 0.025,
-                cacheWrite: 1,
+                cacheWrite: 0,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
@@ -6945,7 +6697,7 @@ export const MODELS = {
             provider: "openai",
             baseUrl: "https://api.openai.com/v1",
             reasoning: true,
-            thinkingLevelMap: { "off": null },
+            thinkingLevelMap: { "off": "none" },
             input: ["text", "image"],
             cost: {
                 input: 1.25,
@@ -7035,7 +6787,7 @@ export const MODELS = {
             provider: "openai",
             baseUrl: "https://api.openai.com/v1",
             reasoning: true,
-            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
+            thinkingLevelMap: { "off": "none", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
                 input: 1.75,
@@ -7125,7 +6877,7 @@ export const MODELS = {
             provider: "openai",
             baseUrl: "https://api.openai.com/v1",
             reasoning: true,
-            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
+            thinkingLevelMap: { "off": "none", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
                 input: 1.75,
@@ -7161,7 +6913,7 @@ export const MODELS = {
             provider: "openai",
             baseUrl: "https://api.openai.com/v1",
             reasoning: true,
-            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
+            thinkingLevelMap: { "off": "none", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
                 input: 2.5,
@@ -7179,7 +6931,7 @@ export const MODELS = {
             provider: "openai",
             baseUrl: "https://api.openai.com/v1",
             reasoning: true,
-            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
+            thinkingLevelMap: { "off": "none", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
                 input: 0.75,
@@ -7197,7 +6949,7 @@ export const MODELS = {
             provider: "openai",
             baseUrl: "https://api.openai.com/v1",
             reasoning: true,
-            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
+            thinkingLevelMap: { "off": "none", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
                 input: 0.2,
@@ -7233,7 +6985,7 @@ export const MODELS = {
             provider: "openai",
             baseUrl: "https://api.openai.com/v1",
             reasoning: true,
-            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
+            thinkingLevelMap: { "off": "none", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
                 input: 5,
@@ -7400,67 +7152,51 @@ export const MODELS = {
         },
     },
     "openai-codex": {
-        "gpt-5.1": {
-            id: "gpt-5.1",
-            name: "GPT-5.1",
-            api: "openai-codex-responses",
-            provider: "openai-codex",
-            baseUrl: "https://chatgpt.com/backend-api",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1.25,
-                output: 10,
-                cacheRead: 0.125,
-                cacheWrite: 0,
-            },
-            contextWindow: 272000,
-            maxTokens: 128000,
-        },
-        "gpt-5.1-codex-max": {
-            id: "gpt-5.1-codex-max",
-            name: "GPT-5.1 Codex Max",
+        "gpt-5.2": {
+            id: "gpt-5.2",
+            name: "GPT-5.2",
             api: "openai-codex-responses",
             provider: "openai-codex",
             baseUrl: "https://chatgpt.com/backend-api",
             reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh", "minimal": "low" },
             input: ["text", "image"],
             cost: {
-                input: 1.25,
-                output: 10,
-                cacheRead: 0.125,
+                input: 1.75,
+                output: 14,
+                cacheRead: 0.175,
                 cacheWrite: 0,
             },
             contextWindow: 272000,
             maxTokens: 128000,
         },
-        "gpt-5.1-codex-mini": {
-            id: "gpt-5.1-codex-mini",
-            name: "GPT-5.1 Codex Mini",
+        "gpt-5.3-codex": {
+            id: "gpt-5.3-codex",
+            name: "GPT-5.3 Codex",
             api: "openai-codex-responses",
             provider: "openai-codex",
             baseUrl: "https://chatgpt.com/backend-api",
             reasoning: true,
-            thinkingLevelMap: { "minimal": "medium", "low": "medium", "medium": "medium", "high": "high" },
+            thinkingLevelMap: { "xhigh": "xhigh", "minimal": "low" },
             input: ["text", "image"],
             cost: {
-                input: 0.25,
-                output: 2,
-                cacheRead: 0.025,
+                input: 1.75,
+                output: 14,
+                cacheRead: 0.175,
                 cacheWrite: 0,
             },
             contextWindow: 272000,
             maxTokens: 128000,
         },
-        "gpt-5.2": {
-            id: "gpt-5.2",
-            name: "GPT-5.2",
+        "gpt-5.3-codex-spark": {
+            id: "gpt-5.3-codex-spark",
+            name: "GPT-5.3 Codex Spark",
             api: "openai-codex-responses",
             provider: "openai-codex",
             baseUrl: "https://chatgpt.com/backend-api",
             reasoning: true,
             thinkingLevelMap: { "xhigh": "xhigh", "minimal": "low" },
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
                 input: 1.75,
                 output: 14,
@@ -7470,9 +7206,9 @@ export const MODELS = {
             contextWindow: 272000,
             maxTokens: 128000,
         },
-        "gpt-5.2-codex": {
-            id: "gpt-5.2-codex",
-            name: "GPT-5.2 Codex",
+        "gpt-5.4": {
+            id: "gpt-5.4",
+            name: "GPT-5.4",
             api: "openai-codex-responses",
             provider: "openai-codex",
             baseUrl: "https://chatgpt.com/backend-api",
@@ -7480,17 +7216,17 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh", "minimal": "low" },
             input: ["text", "image"],
             cost: {
-                input: 1.75,
-                output: 14,
-                cacheRead: 0.175,
+                input: 2.5,
+                output: 15,
+                cacheRead: 0.25,
                 cacheWrite: 0,
             },
             contextWindow: 272000,
             maxTokens: 128000,
         },
-        "gpt-5.3-codex": {
-            id: "gpt-5.3-codex",
-            name: "GPT-5.3 Codex",
+        "gpt-5.4-fast": {
+            id: "gpt-5.4-fast",
+            name: "GPT-5.4 Fast",
             api: "openai-codex-responses",
             provider: "openai-codex",
             baseUrl: "https://chatgpt.com/backend-api",
@@ -7498,35 +7234,35 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh", "minimal": "low" },
             input: ["text", "image"],
             cost: {
-                input: 1.75,
-                output: 14,
-                cacheRead: 0.175,
+                input: 5,
+                output: 30,
+                cacheRead: 0.5,
                 cacheWrite: 0,
             },
             contextWindow: 272000,
             maxTokens: 128000,
         },
-        "gpt-5.3-codex-spark": {
-            id: "gpt-5.3-codex-spark",
-            name: "GPT-5.3 Codex Spark",
+        "gpt-5.4-mini": {
+            id: "gpt-5.4-mini",
+            name: "GPT-5.4 mini",
             api: "openai-codex-responses",
             provider: "openai-codex",
             baseUrl: "https://chatgpt.com/backend-api",
             reasoning: true,
             thinkingLevelMap: { "xhigh": "xhigh", "minimal": "low" },
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 0.75,
+                output: 4.5,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 272000,
             maxTokens: 128000,
         },
-        "gpt-5.4": {
-            id: "gpt-5.4",
-            name: "GPT-5.4",
+        "gpt-5.4-mini-fast": {
+            id: "gpt-5.4-mini-fast",
+            name: "GPT-5.4 mini Fast",
             api: "openai-codex-responses",
             provider: "openai-codex",
             baseUrl: "https://chatgpt.com/backend-api",
@@ -7534,17 +7270,17 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh", "minimal": "low" },
             input: ["text", "image"],
             cost: {
-                input: 2.5,
-                output: 15,
-                cacheRead: 0.25,
+                input: 1.5,
+                output: 9,
+                cacheRead: 0.15,
                 cacheWrite: 0,
             },
             contextWindow: 272000,
             maxTokens: 128000,
         },
-        "gpt-5.4-mini": {
-            id: "gpt-5.4-mini",
-            name: "GPT-5.4 Mini",
+        "gpt-5.5": {
+            id: "gpt-5.5",
+            name: "GPT-5.5",
             api: "openai-codex-responses",
             provider: "openai-codex",
             baseUrl: "https://chatgpt.com/backend-api",
@@ -7552,17 +7288,17 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh", "minimal": "low" },
             input: ["text", "image"],
             cost: {
-                input: 0.75,
-                output: 4.5,
-                cacheRead: 0.075,
+                input: 5,
+                output: 30,
+                cacheRead: 0.5,
                 cacheWrite: 0,
             },
             contextWindow: 272000,
             maxTokens: 128000,
         },
-        "gpt-5.5": {
-            id: "gpt-5.5",
-            name: "GPT-5.5",
+        "gpt-5.5-fast": {
+            id: "gpt-5.5-fast",
+            name: "GPT-5.5 Fast",
             api: "openai-codex-responses",
             provider: "openai-codex",
             baseUrl: "https://chatgpt.com/backend-api",
@@ -7570,9 +7306,9 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh", "minimal": "low" },
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 30,
-                cacheRead: 0.5,
+                input: 12.5,
+                output: 75,
+                cacheRead: 1.25,
                 cacheWrite: 0,
             },
             contextWindow: 272000,
@@ -7735,6 +7471,25 @@ 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",
@@ -8093,23 +7848,6 @@ 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",
@@ -8246,17 +7984,34 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
-    },
-    "opencode-go": {
-        "deepseek-v4-flash": {
-            id: "deepseek-v4-flash",
-            name: "DeepSeek V4 Flash",
-            api: "openai-completions",
-            provider: "opencode-go",
-            baseUrl: "https://opencode.ai/zen/go/v1",
-            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
-            reasoning: true,
-            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
+        "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": {
+            id: "deepseek-v4-flash",
+            name: "DeepSeek V4 Flash",
+            api: "openai-completions",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
             cost: {
                 input: 0.14,
@@ -8391,9 +8146,9 @@ 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: {
@@ -8613,40 +8368,6 @@ 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",
@@ -8769,6 +8490,24 @@ 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",
@@ -8854,6 +8593,23 @@ 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",
@@ -8936,7 +8692,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 120000,
+            contextWindow: 131072,
             maxTokens: 8000,
         },
         "baidu/ernie-4.5-vl-28b-a3b": {
@@ -8953,7 +8709,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 30000,
+            contextWindow: 131072,
             maxTokens: 8000,
         },
         "bytedance-seed/seed-1.6": {
@@ -9101,13 +8857,13 @@ 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",
@@ -9123,7 +8879,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 64000,
+            contextWindow: 163840,
             maxTokens: 16000,
         },
         "deepseek/deepseek-r1-0528": {
@@ -9205,9 +8961,28 @@ 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,
@@ -9402,6 +9177,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
+        "google/gemini-3.1-flash-lite": {
+            id: "google/gemini-3.1-flash-lite",
+            name: "Google: Gemini 3.1 Flash Lite",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.25,
+                output: 1.5,
+                cacheRead: 0.024999999999999998,
+                cacheWrite: 0.08333333333333334,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
         "google/gemini-3.1-flash-lite-preview": {
             id: "google/gemini-3.1-flash-lite-preview",
             name: "Google: Gemini 3.1 Flash Lite Preview",
@@ -9450,7 +9242,7 @@ export const MODELS = {
                 cacheRead: 0.19999999999999998,
                 cacheWrite: 0.375,
             },
-            contextWindow: 1048576,
+            contextWindow: 1048756,
             maxTokens: 65536,
         },
         "google/gemma-3-12b-it": {
@@ -9530,8 +9322,8 @@ 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,
             },
@@ -9579,6 +9371,7 @@ export const MODELS = {
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
+            thinkingLevelMap: { "off": null },
             input: ["text"],
             cost: {
                 input: 0.25,
@@ -9615,14 +9408,31 @@ 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: 65536,
+        },
         "kwaipilot/kat-coder-pro-v2": {
             id: "kwaipilot/kat-coder-pro-v2",
             name: "Kwaipilot: KAT-Coder-Pro V2",
@@ -9671,7 +9481,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 16384,
+            contextWindow: 131072,
             maxTokens: 16384,
         },
         "meta-llama/llama-3.3-70b-instruct": {
@@ -9705,7 +9515,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 65536,
+            contextWindow: 131072,
             maxTokens: 4096,
         },
         "meta-llama/llama-4-scout": {
@@ -9722,7 +9532,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 327680,
+            contextWindow: 10000000,
             maxTokens: 16384,
         },
         "minimax/minimax-m1": {
@@ -9756,7 +9566,7 @@ export const MODELS = {
                 cacheRead: 0.03,
                 cacheWrite: 0,
             },
-            contextWindow: 196608,
+            contextWindow: 204800,
             maxTokens: 196608,
         },
         "minimax/minimax-m2.1": {
@@ -9773,7 +9583,7 @@ export const MODELS = {
                 cacheRead: 0.03,
                 cacheWrite: 0,
             },
-            contextWindow: 196608,
+            contextWindow: 204800,
             maxTokens: 196608,
         },
         "minimax/minimax-m2.5": {
@@ -9787,11 +9597,11 @@ 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",
@@ -9807,7 +9617,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 196608,
+            contextWindow: 204800,
             maxTokens: 8192,
         },
         "minimax/minimax-m2.7": {
@@ -9819,13 +9629,13 @@ 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",
@@ -10150,23 +9960,6 @@ export const MODELS = {
             contextWindow: 65536,
             maxTokens: 4096,
         },
-        "mistralai/mixtral-8x7b-instruct": {
-            id: "mistralai/mixtral-8x7b-instruct",
-            name: "Mistral: Mixtral 8x7B Instruct",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.54,
-                output: 0.54,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 32768,
-            maxTokens: 16384,
-        },
         "mistralai/pixtral-large-2411": {
             id: "mistralai/pixtral-large-2411",
             name: "Mistral: Pixtral Large 2411",
@@ -10227,8 +10020,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.39999999999999997,
-                output: 2,
+                input: 0.6,
+                output: 2.5,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -10246,7 +10039,7 @@ export const MODELS = {
             cost: {
                 input: 0.6,
                 output: 2.5,
-                cacheRead: 0.15,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -10278,13 +10071,13 @@ 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",
@@ -10303,23 +10096,6 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 163840,
         },
-        "nvidia/llama-3.1-nemotron-70b-instruct": {
-            id: "nvidia/llama-3.1-nemotron-70b-instruct",
-            name: "NVIDIA: Llama 3.1 Nemotron 70B Instruct",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 1.2,
-                output: 1.2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 16384,
-        },
         "nvidia/llama-3.3-nemotron-super-49b-v1.5": {
             id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
             name: "NVIDIA: Llama 3.3 Nemotron Super 49B V1.5",
@@ -10402,7 +10178,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
+            contextWindow: 1000000,
             maxTokens: 4096,
         },
         "nvidia/nemotron-3-super-120b-a12b:free": {
@@ -10419,7 +10195,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
+            contextWindow: 1000000,
             maxTokens: 262144,
         },
         "nvidia/nemotron-nano-12b-v2-vl:free": {
@@ -11570,7 +11346,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 32768,
+            contextWindow: 131072,
             maxTokens: 16384,
         },
         "qwen/qwen-2.5-7b-instruct": {
@@ -11587,26 +11363,9 @@ 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",
@@ -11658,40 +11417,6 @@ 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",
@@ -11701,12 +11426,12 @@ 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": {
@@ -11757,7 +11482,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 262144,
             maxTokens: 4096,
         },
         "qwen/qwen3-30b-a3b": {
@@ -11774,7 +11499,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 40960,
+            contextWindow: 131072,
             maxTokens: 20000,
         },
         "qwen/qwen3-30b-a3b-instruct-2507": {
@@ -11821,12 +11546,12 @@ 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",
@@ -11842,7 +11567,7 @@ export const MODELS = {
                 cacheRead: 0.049999999999999996,
                 cacheWrite: 0,
             },
-            contextWindow: 40960,
+            contextWindow: 131072,
             maxTokens: 8192,
         },
         "qwen/qwen3-coder": {
@@ -11859,7 +11584,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
+            contextWindow: 1048576,
             maxTokens: 65536,
         },
         "qwen/qwen3-coder-30b-a3b-instruct": {
@@ -11944,7 +11669,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262000,
+            contextWindow: 1048576,
             maxTokens: 262000,
         },
         "qwen/qwen3-max": {
@@ -12029,7 +11754,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 262144,
             maxTokens: 32768,
         },
         "qwen/qwen3-vl-235b-a22b-instruct": {
@@ -12080,7 +11805,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 262144,
             maxTokens: 32768,
         },
         "qwen/qwen3-vl-30b-a3b-thinking": {
@@ -12114,7 +11839,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 262144,
             maxTokens: 32768,
         },
         "qwen/qwen3-vl-8b-instruct": {
@@ -12131,7 +11856,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 256000,
             maxTokens: 32768,
         },
         "qwen/qwen3-vl-8b-thinking": {
@@ -12148,7 +11873,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 256000,
             maxTokens: 32768,
         },
         "qwen/qwen3.5-122b-a10b": {
@@ -12279,8 +12004,8 @@ 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,
             },
@@ -12330,10 +12055,10 @@ 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,
@@ -12457,18 +12182,18 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
-        "tencent/hy3-preview:free": {
-            id: "tencent/hy3-preview:free",
-            name: "Tencent: Hy3 preview (free)",
+        "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,
-                output: 0,
-                cacheRead: 0,
+                input: 0.06599999999999999,
+                output: 0.26,
+                cacheRead: 0.029,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -12508,23 +12233,6 @@ export const MODELS = {
             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",
@@ -12542,125 +12250,6 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 4096,
         },
-        "x-ai/grok-3": {
-            id: "x-ai/grok-3",
-            name: "xAI: Grok 3",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.75,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 4096,
-        },
-        "x-ai/grok-3-beta": {
-            id: "x-ai/grok-3-beta",
-            name: "xAI: Grok 3 Beta",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.75,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 4096,
-        },
-        "x-ai/grok-3-mini": {
-            id: "x-ai/grok-3-mini",
-            name: "xAI: Grok 3 Mini",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 0.5,
-                cacheRead: 0.075,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 4096,
-        },
-        "x-ai/grok-3-mini-beta": {
-            id: "x-ai/grok-3-mini-beta",
-            name: "xAI: Grok 3 Mini Beta",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 0.5,
-                cacheRead: 0.075,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 4096,
-        },
-        "x-ai/grok-4": {
-            id: "x-ai/grok-4",
-            name: "xAI: Grok 4",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.75,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 4096,
-        },
-        "x-ai/grok-4-fast": {
-            id: "x-ai/grok-4-fast",
-            name: "xAI: Grok 4 Fast",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.19999999999999998,
-                output: 0.5,
-                cacheRead: 0.049999999999999996,
-                cacheWrite: 0,
-            },
-            contextWindow: 2000000,
-            maxTokens: 30000,
-        },
-        "x-ai/grok-4.1-fast": {
-            id: "x-ai/grok-4.1-fast",
-            name: "xAI: Grok 4.1 Fast",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.19999999999999998,
-                output: 0.5,
-                cacheRead: 0.049999999999999996,
-                cacheWrite: 0,
-            },
-            contextWindow: 2000000,
-            maxTokens: 30000,
-        },
         "x-ai/grok-4.20": {
             id: "x-ai/grok-4.20",
             name: "xAI: Grok 4.20",
@@ -12695,23 +12284,6 @@ 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",
@@ -12721,9 +12293,9 @@ 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,
@@ -12795,7 +12367,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 131072,
+            maxTokens: 16384,
         },
         "z-ai/glm-4-32b": {
             id: "z-ai/glm-4-32b",
@@ -12891,13 +12463,13 @@ 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",
@@ -12925,13 +12497,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.38,
-                output: 1.74,
-                cacheRead: 0,
+                input: 0.39999999999999997,
+                output: 1.75,
+                cacheRead: 0.08,
                 cacheWrite: 0,
             },
             contextWindow: 202752,
-            maxTokens: 4096,
+            maxTokens: 131072,
         },
         "z-ai/glm-4.7-flash": {
             id: "z-ai/glm-4.7-flash",
@@ -12993,13 +12565,13 @@ 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",
@@ -13056,103 +12628,425 @@ export const MODELS = {
             id: "~anthropic/claude-sonnet-latest",
             name: "Anthropic Claude Sonnet Latest",
             api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
+            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: 1000000,
+            maxTokens: 128000,
+        },
+        "~google/gemini-flash-latest": {
+            id: "~google/gemini-flash-latest",
+            name: "Google Gemini Flash Latest",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.5,
+                output: 3,
+                cacheRead: 0.049999999999999996,
+                cacheWrite: 0.08333333333333334,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
+        "~google/gemini-pro-latest": {
+            id: "~google/gemini-pro-latest",
+            name: "Google Gemini Pro Latest",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 12,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 0.375,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
+        "~moonshotai/kimi-latest": {
+            id: "~moonshotai/kimi-latest",
+            name: "MoonshotAI Kimi Latest",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.73,
+                output: 3.49,
+                cacheRead: 0.25,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262142,
+        },
+        "~openai/gpt-latest": {
+            id: "~openai/gpt-latest",
+            name: "OpenAI GPT Latest",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 30,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
+        "~openai/gpt-mini-latest": {
+            id: "~openai/gpt-mini-latest",
+            name: "OpenAI GPT Mini Latest",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.75,
+                output: 4.5,
+                cacheRead: 0.075,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
+    },
+    "together": {
+        "MiniMaxAI/MiniMax-M2.5": {
+            id: "MiniMaxAI/MiniMax-M2.5",
+            name: "MiniMax-M2.5",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": null },
+            input: ["text"],
+            cost: {
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
+                cacheWrite: 0,
+            },
+            contextWindow: 204800,
+            maxTokens: 131072,
+        },
+        "MiniMaxAI/MiniMax-M2.7": {
+            id: "MiniMaxAI/MiniMax-M2.7",
+            name: "MiniMax-M2.7",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": null, "low": null, "medium": null },
+            input: ["text"],
+            cost: {
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
+                cacheWrite: 0,
+            },
+            contextWindow: 202752,
+            maxTokens: 131072,
+        },
+        "Qwen/Qwen3-235B-A22B-Instruct-2507-tput": {
+            id: "Qwen/Qwen3-235B-A22B-Instruct-2507-tput",
+            name: "Qwen3 235B A22B Instruct 2507 FP8",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
+            input: ["text"],
+            cost: {
+                input: 0.2,
+                output: 0.6,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": {
+            id: "Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8",
+            name: "Qwen3 Coder 480B A35B Instruct",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 2,
+                output: 2,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "Qwen/Qwen3-Coder-Next-FP8": {
+            id: "Qwen/Qwen3-Coder-Next-FP8",
+            name: "Qwen3 Coder Next FP8",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
+            input: ["text"],
+            cost: {
+                input: 0.5,
+                output: 1.2,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "Qwen/Qwen3.5-397B-A17B": {
+            id: "Qwen/Qwen3.5-397B-A17B",
+            name: "Qwen3.5 397B A17B",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
+            input: ["text", "image"],
+            cost: {
+                input: 0.6,
+                output: 3.6,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 130000,
+        },
+        "Qwen/Qwen3.6-Plus": {
+            id: "Qwen/Qwen3.6-Plus",
+            name: "Qwen3.6 Plus",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
+            input: ["text"],
+            cost: {
+                input: 0.5,
+                output: 3,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 500000,
+        },
+        "deepseek-ai/DeepSeek-V3": {
+            id: "deepseek-ai/DeepSeek-V3",
+            name: "DeepSeek V3",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
+            input: ["text"],
+            cost: {
+                input: 1.25,
+                output: 1.25,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
+        "deepseek-ai/DeepSeek-V3-1": {
+            id: "deepseek-ai/DeepSeek-V3-1",
+            name: "DeepSeek V3.1",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
+            input: ["text"],
+            cost: {
+                input: 0.6,
+                output: 1.7,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
+        "deepseek-ai/DeepSeek-V4-Pro": {
+            id: "deepseek-ai/DeepSeek-V4-Pro",
+            name: "DeepSeek V4 Pro",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": null },
+            input: ["text"],
+            cost: {
+                input: 2.1,
+                output: 4.4,
+                cacheRead: 0.2,
+                cacheWrite: 0,
+            },
+            contextWindow: 512000,
+            maxTokens: 384000,
+        },
+        "essentialai/Rnj-1-Instruct": {
+            id: "essentialai/Rnj-1-Instruct",
+            name: "Rnj-1 Instruct",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.15,
+                output: 0.15,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 32768,
+            maxTokens: 32768,
+        },
+        "google/gemma-4-31B-it": {
+            id: "google/gemma-4-31B-it",
+            name: "Gemma 4 31B Instruct",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
             reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
             input: ["text", "image"],
             cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
+                input: 0.2,
+                output: 0.5,
+                cacheRead: 0,
+                cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 128000,
+            contextWindow: 262144,
+            maxTokens: 131072,
         },
-        "~google/gemini-flash-latest": {
-            id: "~google/gemini-flash-latest",
-            name: "Google Gemini Flash Latest",
+        "meta-llama/Llama-3.3-70B-Instruct-Turbo": {
+            id: "meta-llama/Llama-3.3-70B-Instruct-Turbo",
+            name: "Llama 3.3 70B",
             api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
+            reasoning: false,
+            input: ["text"],
             cost: {
-                input: 0.5,
-                output: 3,
-                cacheRead: 0.049999999999999996,
-                cacheWrite: 0.08333333333333334,
+                input: 0.88,
+                output: 0.88,
+                cacheRead: 0,
+                cacheWrite: 0,
             },
-            contextWindow: 1048576,
-            maxTokens: 65536,
+            contextWindow: 131072,
+            maxTokens: 131072,
         },
-        "~google/gemini-pro-latest": {
-            id: "~google/gemini-pro-latest",
-            name: "Google Gemini Pro Latest",
+        "moonshotai/Kimi-K2.5": {
+            id: "moonshotai/Kimi-K2.5",
+            name: "Kimi K2.5",
             api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
             reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
             input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 12,
-                cacheRead: 0.19999999999999998,
-                cacheWrite: 0.375,
+                input: 0.5,
+                output: 2.8,
+                cacheRead: 0,
+                cacheWrite: 0,
             },
-            contextWindow: 1048576,
-            maxTokens: 65536,
+            contextWindow: 262144,
+            maxTokens: 262144,
         },
-        "~moonshotai/kimi-latest": {
-            id: "~moonshotai/kimi-latest",
-            name: "MoonshotAI Kimi Latest",
+        "moonshotai/Kimi-K2.6": {
+            id: "moonshotai/Kimi-K2.6",
+            name: "Kimi K2.6",
             api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
             reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
             input: ["text", "image"],
             cost: {
-                input: 0.75,
-                output: 3.5,
-                cacheRead: 0.15,
+                input: 1.2,
+                output: 4.5,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 131000,
         },
-        "~openai/gpt-latest": {
-            id: "~openai/gpt-latest",
-            name: "OpenAI GPT Latest",
+        "openai/gpt-oss-120b": {
+            id: "openai/gpt-oss-120b",
+            name: "GPT OSS 120B",
             api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": true, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "openai" },
             reasoning: true,
-            input: ["text", "image"],
+            thinkingLevelMap: { "off": null, "minimal": null },
+            input: ["text"],
             cost: {
-                input: 5,
-                output: 30,
-                cacheRead: 0.5,
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 1050000,
-            maxTokens: 128000,
+            contextWindow: 131072,
+            maxTokens: 131072,
         },
-        "~openai/gpt-mini-latest": {
-            id: "~openai/gpt-mini-latest",
-            name: "OpenAI GPT Mini Latest",
+        "zai-org/GLM-5.1": {
+            id: "zai-org/GLM-5.1",
+            name: "GLM-5.1",
             api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
             reasoning: true,
-            input: ["text", "image"],
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
+            input: ["text"],
             cost: {
-                input: 0.75,
-                output: 4.5,
-                cacheRead: 0.075,
+                input: 1.4,
+                output: 4.4,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 400000,
-            maxTokens: 128000,
+            contextWindow: 202752,
+            maxTokens: 131072,
         },
     },
     "vercel-ai-gateway": {
@@ -13496,23 +13390,6 @@ 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",
@@ -13991,6 +13868,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "google/gemini-3.1-flash-lite": {
+            id: "google/gemini-3.1-flash-lite",
+            name: "Gemini 3.1 Flash Lite",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.25,
+                output: 1.5,
+                cacheRead: 0.03,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 65000,
+        },
         "google/gemini-3.1-flash-lite-preview": {
             id: "google/gemini-3.1-flash-lite-preview",
             name: "Gemini 3.1 Flash Lite Preview",
@@ -15178,7 +15072,7 @@ 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",
@@ -15257,213 +15151,94 @@ export const MODELS = {
                 output: 40,
                 cacheRead: 2.5,
                 cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 100000,
-        },
-        "openai/o3-mini": {
-            id: "openai/o3-mini",
-            name: "o3-mini",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 1.1,
-                output: 4.4,
-                cacheRead: 0.55,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 100000,
-        },
-        "openai/o3-pro": {
-            id: "openai/o3-pro",
-            name: "o3 Pro",
-            api: "anthropic-messages",
-            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,
+            },
+            contextWindow: 200000,
+            maxTokens: 100000,
         },
-        "xai/grok-3-mini": {
-            id: "xai/grok-3-mini",
-            name: "Grok 3 Mini Beta",
+        "openai/o3-mini": {
+            id: "openai/o3-mini",
+            name: "o3-mini",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
+            reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.3,
-                output: 0.5,
-                cacheRead: 0.075,
+                input: 1.1,
+                output: 4.4,
+                cacheRead: 0.55,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 131072,
+            contextWindow: 200000,
+            maxTokens: 100000,
         },
-        "xai/grok-3-mini-fast": {
-            id: "xai/grok-3-mini-fast",
-            name: "Grok 3 Mini Fast Beta",
+        "openai/o3-pro": {
+            id: "openai/o3-pro",
+            name: "o3 Pro",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text"],
+            reasoning: true,
+            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",
@@ -15479,8 +15254,8 @@ 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",
@@ -15496,8 +15271,8 @@ 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",
@@ -15618,23 +15393,6 @@ 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",
@@ -16062,193 +15820,6 @@ export const MODELS = {
             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)",
@@ -16323,7 +15894,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "xai",
             baseUrl: "https://api.x.ai/v1",
-            reasoning: true,
+            reasoning: false,
             input: ["text"],
             cost: {
                 input: 0.2,
@@ -16331,8 +15902,8 @@ export const MODELS = {
                 cacheRead: 0.02,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 10000,
+            contextWindow: 32768,
+            maxTokens: 8192,
         },
         "grok-vision-beta": {
             id: "grok-vision-beta",