@earendil-works/pi-ai 0.74.0 → 0.74.2

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",
@@ -1077,8 +908,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 256000,
+            contextWindow: 262143,
+            maxTokens: 16000,
         },
         "moonshotai.kimi-k2.5": {
             id: "moonshotai.kimi-k2.5",
@@ -1094,8 +925,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 256000,
+            contextWindow: 262143,
+            maxTokens: 16000,
         },
         "nvidia.nemotron-nano-12b-v2": {
             id: "nvidia.nemotron-nano-12b-v2",
@@ -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",
@@ -3427,6 +3275,42 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 16384,
         },
+        "@cf/ibm-granite/granite-4.0-h-micro": {
+            id: "@cf/ibm-granite/granite-4.0-h-micro",
+            name: "Granite 4.0 H Micro",
+            api: "openai-completions",
+            provider: "cloudflare-workers-ai",
+            baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+            compat: { "sendSessionAffinityHeaders": true },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.017,
+                output: 0.112,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131000,
+            maxTokens: 131000,
+        },
+        "@cf/meta/llama-3.3-70b-instruct-fp8-fast": {
+            id: "@cf/meta/llama-3.3-70b-instruct-fp8-fast",
+            name: "Llama 3.3 70B Instruct fp8 Fast",
+            api: "openai-completions",
+            provider: "cloudflare-workers-ai",
+            baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+            compat: { "sendSessionAffinityHeaders": true },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.293,
+                output: 2.253,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 24000,
+            maxTokens: 24000,
+        },
         "@cf/meta/llama-4-scout-17b-16e-instruct": {
             id: "@cf/meta/llama-4-scout-17b-16e-instruct",
             name: "Llama 4 Scout 17B 16E Instruct",
@@ -3442,9 +3326,27 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 131000,
             maxTokens: 16384,
         },
+        "@cf/mistralai/mistral-small-3.1-24b-instruct": {
+            id: "@cf/mistralai/mistral-small-3.1-24b-instruct",
+            name: "Mistral Small 3.1 24B Instruct",
+            api: "openai-completions",
+            provider: "cloudflare-workers-ai",
+            baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+            compat: { "sendSessionAffinityHeaders": true },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.351,
+                output: 0.555,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 128000,
+        },
         "@cf/moonshotai/kimi-k2.5": {
             id: "@cf/moonshotai/kimi-k2.5",
             name: "Kimi K2.5",
@@ -3478,7 +3380,7 @@ export const MODELS = {
                 cacheRead: 0.16,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
+            contextWindow: 262144,
             maxTokens: 256000,
         },
         "@cf/nvidia/nemotron-3-120b-a12b": {
@@ -3535,6 +3437,24 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 16384,
         },
+        "@cf/qwen/qwen3-30b-a3b-fp8": {
+            id: "@cf/qwen/qwen3-30b-a3b-fp8",
+            name: "Qwen3 30B A3b fp8",
+            api: "openai-completions",
+            provider: "cloudflare-workers-ai",
+            baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+            compat: { "sendSessionAffinityHeaders": true },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.0509,
+                output: 0.335,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 32768,
+            maxTokens: 32768,
+        },
         "@cf/zai-org/glm-4.7-flash": {
             id: "@cf/zai-org/glm-4.7-flash",
             name: "GLM-4.7-Flash",
@@ -3545,7 +3465,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.06,
+                input: 0.0605,
                 output: 0.4,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -3601,6 +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: {
@@ -3618,6 +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: {
@@ -3629,12 +3551,31 @@ export const MODELS = {
             contextWindow: 160000,
             maxTokens: 160000,
         },
+        "accounts/fireworks/models/deepseek-v4-flash": {
+            id: "accounts/fireworks/models/deepseek-v4-flash",
+            name: "DeepSeek V4 Flash",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.03,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
         "accounts/fireworks/models/deepseek-v4-pro": {
             id: "accounts/fireworks/models/deepseek-v4-pro",
             name: "DeepSeek V4 Pro",
             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 +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: {
@@ -3669,6 +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: {
@@ -3686,6 +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: true,
             input: ["text"],
             cost: {
@@ -3703,6 +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: {
@@ -3720,6 +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"],
             cost: {
@@ -3737,6 +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"],
             cost: {
@@ -3754,6 +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: {
@@ -3771,6 +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: false,
             input: ["text"],
             cost: {
@@ -3788,6 +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: {
@@ -3805,6 +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: {
@@ -3822,6 +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: {
@@ -3839,6 +3791,7 @@ 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 +3809,7 @@ 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 +3827,7 @@ 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 +3845,7 @@ 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 +3863,7 @@ 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 +3952,6 @@ 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 +4027,6 @@ 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 +4084,6 @@ 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",
@@ -4203,82 +4103,6 @@ export const MODELS = {
             contextWindow: 264000,
             maxTokens: 64000,
         },
-        "gpt-5.1": {
-            id: "gpt-5.1",
-            name: "GPT-5.1",
-            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: 264000,
-            maxTokens: 64000,
-        },
-        "gpt-5.1-codex": {
-            id: "gpt-5.1-codex",
-            name: "GPT-5.1-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 },
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 400000,
-            maxTokens: 128000,
-        },
-        "gpt-5.1-codex-max": {
-            id: "gpt-5.1-codex-max",
-            name: "GPT-5.1-Codex-max",
-            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: 400000,
-            maxTokens: 128000,
-        },
-        "gpt-5.1-codex-mini": {
-            id: "gpt-5.1-codex-mini",
-            name: "GPT-5.1-Codex-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 },
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 400000,
-            maxTokens: 128000,
-        },
         "gpt-5.2": {
             id: "gpt-5.2",
             name: "GPT-5.2",
@@ -4414,57 +4238,6 @@ export const MODELS = {
         },
     },
     "google": {
-        "gemini-1.5-flash": {
-            id: "gemini-1.5-flash",
-            name: "Gemini 1.5 Flash",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.075,
-                output: 0.3,
-                cacheRead: 0.01875,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 8192,
-        },
-        "gemini-1.5-flash-8b": {
-            id: "gemini-1.5-flash-8b",
-            name: "Gemini 1.5 Flash-8B",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.0375,
-                output: 0.15,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 8192,
-        },
-        "gemini-1.5-pro": {
-            id: "gemini-1.5-pro",
-            name: "Gemini 1.5 Pro",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 1.25,
-                output: 5,
-                cacheRead: 0.3125,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 8192,
-        },
         "gemini-2.0-flash": {
             id: "gemini-2.0-flash",
             name: "Gemini 2.0 Flash",
@@ -4484,7 +4257,7 @@ export const MODELS = {
         },
         "gemini-2.0-flash-lite": {
             id: "gemini-2.0-flash-lite",
-            name: "Gemini 2.0 Flash Lite",
+            name: "Gemini 2.0 Flash-Lite",
             api: "google-generative-ai",
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
@@ -4518,7 +4291,7 @@ export const MODELS = {
         },
         "gemini-2.5-flash-lite": {
             id: "gemini-2.5-flash-lite",
-            name: "Gemini 2.5 Flash Lite",
+            name: "Gemini 2.5 Flash-Lite",
             api: "google-generative-ai",
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
@@ -4527,331 +4300,197 @@ export const MODELS = {
             cost: {
                 input: 0.1,
                 output: 0.4,
-                cacheRead: 0.025,
+                cacheRead: 0.01,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "gemini-2.5-flash-lite-preview-06-17": {
-            id: "gemini-2.5-flash-lite-preview-06-17",
-            name: "Gemini 2.5 Flash Lite Preview 06-17",
+        "gemini-2.5-pro": {
+            id: "gemini-2.5-pro",
+            name: "Gemini 2.5 Pro",
             api: "google-generative-ai",
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.1,
-                output: 0.4,
-                cacheRead: 0.025,
+                input: 1.25,
+                output: 10,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "gemini-2.5-flash-lite-preview-09-2025": {
-            id: "gemini-2.5-flash-lite-preview-09-2025",
-            name: "Gemini 2.5 Flash Lite Preview 09-25",
+        "gemini-3-flash-preview": {
+            id: "gemini-3-flash-preview",
+            name: "Gemini 3 Flash Preview",
             api: "google-generative-ai",
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
             reasoning: true,
+            thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 0.1,
-                output: 0.4,
-                cacheRead: 0.025,
+                input: 0.5,
+                output: 3,
+                cacheRead: 0.05,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "gemini-2.5-flash-preview-04-17": {
-            id: "gemini-2.5-flash-preview-04-17",
-            name: "Gemini 2.5 Flash Preview 04-17",
+        "gemini-3-pro-preview": {
+            id: "gemini-3-pro-preview",
+            name: "Gemini 3 Pro Preview",
             api: "google-generative-ai",
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
             reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": null, "high": "HIGH" },
             input: ["text", "image"],
             cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0.0375,
+                input: 2,
+                output: 12,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "gemini-2.5-flash-preview-05-20": {
-            id: "gemini-2.5-flash-preview-05-20",
-            name: "Gemini 2.5 Flash Preview 05-20",
+        "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: 0.15,
-                output: 0.6,
-                cacheRead: 0.0375,
+                input: 0.25,
+                output: 1.5,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "gemini-2.5-flash-preview-09-2025": {
-            id: "gemini-2.5-flash-preview-09-2025",
-            name: "Gemini 2.5 Flash Preview 09-25",
+        "gemini-3.1-flash-lite-preview": {
+            id: "gemini-3.1-flash-lite-preview",
+            name: "Gemini 3.1 Flash Lite Preview",
             api: "google-generative-ai",
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
             reasoning: true,
+            thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 0.3,
-                output: 2.5,
-                cacheRead: 0.075,
+                input: 0.25,
+                output: 1.5,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "gemini-2.5-pro": {
-            id: "gemini-2.5-pro",
-            name: "Gemini 2.5 Pro",
+        "gemini-3.1-pro-preview": {
+            id: "gemini-3.1-pro-preview",
+            name: "Gemini 3.1 Pro Preview",
             api: "google-generative-ai",
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
             reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": null, "high": "HIGH" },
             input: ["text", "image"],
             cost: {
-                input: 1.25,
-                output: 10,
-                cacheRead: 0.125,
+                input: 2,
+                output: 12,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "gemini-2.5-pro-preview-05-06": {
-            id: "gemini-2.5-pro-preview-05-06",
-            name: "Gemini 2.5 Pro Preview 05-06",
+        "gemini-3.1-pro-preview-customtools": {
+            id: "gemini-3.1-pro-preview-customtools",
+            name: "Gemini 3.1 Pro Preview Custom Tools",
             api: "google-generative-ai",
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
             reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": null, "high": "HIGH" },
             input: ["text", "image"],
             cost: {
-                input: 1.25,
-                output: 10,
-                cacheRead: 0.31,
+                input: 2,
+                output: 12,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "gemini-2.5-pro-preview-06-05": {
-            id: "gemini-2.5-pro-preview-06-05",
-            name: "Gemini 2.5 Pro Preview 06-05",
+        "gemini-3.5-flash": {
+            id: "gemini-3.5-flash",
+            name: "Gemini 3.5 Flash",
             api: "google-generative-ai",
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
             reasoning: true,
+            thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 1.25,
-                output: 10,
-                cacheRead: 0.31,
+                input: 1.5,
+                output: 9,
+                cacheRead: 0.15,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "gemini-3-flash-preview": {
-            id: "gemini-3-flash-preview",
-            name: "Gemini 3 Flash Preview",
+        "gemini-flash-latest": {
+            id: "gemini-flash-latest",
+            name: "Gemini Flash Latest",
             api: "google-generative-ai",
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
             reasoning: true,
-            thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 0.5,
-                output: 3,
-                cacheRead: 0.05,
+                input: 0.3,
+                output: 2.5,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "gemini-3-pro-preview": {
-            id: "gemini-3-pro-preview",
-            name: "Gemini 3 Pro Preview",
+        "gemini-flash-lite-latest": {
+            id: "gemini-flash-lite-latest",
+            name: "Gemini Flash-Lite Latest",
             api: "google-generative-ai",
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
             reasoning: true,
-            thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": null, "high": "HIGH" },
             input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 12,
-                cacheRead: 0.2,
+                input: 0.1,
+                output: 0.4,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 64000,
+            contextWindow: 1048576,
+            maxTokens: 65536,
         },
-        "gemini-3.1-flash-lite-preview": {
-            id: "gemini-3.1-flash-lite-preview",
-            name: "Gemini 3.1 Flash Lite Preview",
+        "gemma-4-26b-a4b-it": {
+            id: "gemma-4-26b-a4b-it",
+            name: "Gemma 4 26B A4B IT",
             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: 1,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
-        "gemini-3.1-pro-preview": {
-            id: "gemini-3.1-pro-preview",
-            name: "Gemini 3.1 Pro Preview",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": null, "high": "HIGH" },
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 12,
-                cacheRead: 0.2,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
-        "gemini-3.1-pro-preview-customtools": {
-            id: "gemini-3.1-pro-preview-customtools",
-            name: "Gemini 3.1 Pro Preview Custom Tools",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": null, "high": "HIGH" },
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 12,
-                cacheRead: 0.2,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
-        "gemini-flash-latest": {
-            id: "gemini-flash-latest",
-            name: "Gemini Flash Latest",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.3,
-                output: 2.5,
-                cacheRead: 0.075,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
-        "gemini-flash-lite-latest": {
-            id: "gemini-flash-lite-latest",
-            name: "Gemini Flash-Lite Latest",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.1,
-                output: 0.4,
-                cacheRead: 0.025,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
-        "gemini-live-2.5-flash": {
-            id: "gemini-live-2.5-flash",
-            name: "Gemini Live 2.5 Flash",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.5,
-                output: 2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 8000,
-        },
-        "gemini-live-2.5-flash-preview-native-audio": {
-            id: "gemini-live-2.5-flash-preview-native-audio",
-            name: "Gemini Live 2.5 Flash Preview Native Audio",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.5,
-                output: 2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 65536,
-        },
-        "gemma-3-27b-it": {
-            id: "gemma-3-27b-it",
-            name: "Gemma 3 27B",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "gemma-4-26b-a4b-it": {
-            id: "gemma-4-26b-a4b-it",
-            name: "Gemma 4 26B",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": null, "medium": null, "high": "HIGH" },
+            thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": null, "medium": null, "high": "HIGH" },
             input: ["text", "image"],
             cost: {
                 input: 0,
@@ -4859,12 +4498,12 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 8192,
+            contextWindow: 262144,
+            maxTokens: 32768,
         },
         "gemma-4-31b-it": {
             id: "gemma-4-31b-it",
-            name: "Gemma 4 31B",
+            name: "Gemma 4 31B IT",
             api: "google-generative-ai",
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
@@ -4877,8 +4516,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 8192,
+            contextWindow: 262144,
+            maxTokens: 32768,
         },
     },
     "google-vertex": {
@@ -6945,7 +6584,7 @@ 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 +6674,7 @@ 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 +6764,7 @@ 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 +6800,7 @@ 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 +6818,7 @@ 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 +6836,7 @@ 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 +6872,7 @@ 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,
@@ -7735,6 +7374,25 @@ 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",
@@ -7771,6 +7429,24 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
+        "gemini-3.5-flash": {
+            id: "gemini-3.5-flash",
+            name: "Gemini 3.5 Flash",
+            api: "google-generative-ai",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            thinkingLevelMap: { "off": null },
+            input: ["text", "image"],
+            cost: {
+                input: 1.5,
+                output: 9,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
         "glm-5": {
             id: "glm-5",
             name: "GLM-5",
@@ -8093,22 +7769,22 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
-        "hy3-preview-free": {
-            id: "hy3-preview-free",
-            name: "Hy3 preview Free",
+        "grok-build-0.1": {
+            id: "grok-build-0.1",
+            name: "Grok Build 0.1",
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 1,
+                output: 2,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
-            maxTokens: 64000,
+            maxTokens: 256000,
         },
         "kimi-k2.5": {
             id: "kimi-k2.5",
@@ -8161,23 +7837,6 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131072,
         },
-        "minimax-m2.5-free": {
-            id: "minimax-m2.5-free",
-            name: "MiniMax M2.5 Free",
-            api: "anthropic-messages",
-            provider: "opencode",
-            baseUrl: "https://opencode.ai/zen",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
         "minimax-m2.7": {
             id: "minimax-m2.7",
             name: "MiniMax M2.7",
@@ -8246,6 +7905,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
+        "qwen3.6-plus-free": {
+            id: "qwen3.6-plus-free",
+            name: "Qwen3.6 Plus Free",
+            api: "anthropic-messages",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 65536,
+        },
     },
     "opencode-go": {
         "deepseek-v4-flash": {
@@ -8391,9 +8067,9 @@ 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 +8289,6 @@ 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",
@@ -8769,19 +8411,37 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "anthropic/claude-sonnet-4": {
-            id: "anthropic/claude-sonnet-4",
-            name: "Anthropic: Claude Sonnet 4",
+        "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: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
+                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",
+            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: 1000000,
             maxTokens: 64000,
@@ -8820,39 +8480,39 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "arcee-ai/trinity-large-preview": {
-            id: "arcee-ai/trinity-large-preview",
-            name: "Arcee AI: Trinity Large Preview",
+        "arcee-ai/trinity-large-thinking": {
+            id: "arcee-ai/trinity-large-thinking",
+            name: "Arcee AI: Trinity Large Thinking",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
+            reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.15,
-                output: 0.44999999999999996,
-                cacheRead: 0,
+                input: 0.22,
+                output: 0.85,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
-            contextWindow: 131000,
-            maxTokens: 4096,
+            contextWindow: 262144,
+            maxTokens: 262144,
         },
-        "arcee-ai/trinity-large-thinking": {
-            id: "arcee-ai/trinity-large-thinking",
-            name: "Arcee AI: Trinity Large Thinking",
+        "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: 0.22,
-                output: 0.85,
-                cacheRead: 0.06,
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 80000,
         },
         "arcee-ai/trinity-mini": {
             id: "arcee-ai/trinity-mini",
@@ -8936,7 +8596,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 120000,
+            contextWindow: 131072,
             maxTokens: 8000,
         },
         "baidu/ernie-4.5-vl-28b-a3b": {
@@ -8953,7 +8613,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 30000,
+            contextWindow: 131072,
             maxTokens: 8000,
         },
         "bytedance-seed/seed-1.6": {
@@ -9101,13 +8761,13 @@ 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 +8783,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 64000,
+            contextWindow: 163840,
             maxTokens: 16000,
         },
         "deepseek/deepseek-r1-0528": {
@@ -9205,9 +8865,28 @@ 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,
@@ -9263,7 +8942,7 @@ export const MODELS = {
                 cacheRead: 0.024999999999999998,
                 cacheWrite: 0.08333333333333334,
             },
-            contextWindow: 1048576,
+            contextWindow: 1000000,
             maxTokens: 8192,
         },
         "google/gemini-2.0-flash-lite-001": {
@@ -9402,6 +9081,23 @@ 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",
@@ -9450,6 +9146,23 @@ export const MODELS = {
                 cacheRead: 0.19999999999999998,
                 cacheWrite: 0.375,
             },
+            contextWindow: 1048756,
+            maxTokens: 65536,
+        },
+        "google/gemini-3.5-flash": {
+            id: "google/gemini-3.5-flash",
+            name: "Google: Gemini 3.5 Flash",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.5,
+                output: 9,
+                cacheRead: 0.15,
+                cacheWrite: 0.08333333333333334,
+            },
             contextWindow: 1048576,
             maxTokens: 65536,
         },
@@ -9530,8 +9243,8 @@ 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 +9292,7 @@ export const MODELS = {
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
+            thinkingLevelMap: { "off": null },
             input: ["text"],
             cost: {
                 input: 0.25,
@@ -9598,9 +9312,9 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.3,
-                output: 2.5,
-                cacheRead: 0.06,
+                input: 0.075,
+                output: 0.625,
+                cacheRead: 0.015,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -9615,14 +9329,31 @@ 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 +9402,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 16384,
+            contextWindow: 131072,
             maxTokens: 16384,
         },
         "meta-llama/llama-3.3-70b-instruct": {
@@ -9705,7 +9436,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 65536,
+            contextWindow: 131072,
             maxTokens: 4096,
         },
         "meta-llama/llama-4-scout": {
@@ -9722,7 +9453,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 327680,
+            contextWindow: 10000000,
             maxTokens: 16384,
         },
         "minimax/minimax-m1": {
@@ -9756,7 +9487,7 @@ export const MODELS = {
                 cacheRead: 0.03,
                 cacheWrite: 0,
             },
-            contextWindow: 196608,
+            contextWindow: 204800,
             maxTokens: 196608,
         },
         "minimax/minimax-m2.1": {
@@ -9773,7 +9504,7 @@ export const MODELS = {
                 cacheRead: 0.03,
                 cacheWrite: 0,
             },
-            contextWindow: 196608,
+            contextWindow: 204800,
             maxTokens: 196608,
         },
         "minimax/minimax-m2.5": {
@@ -9787,11 +9518,11 @@ 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 +9538,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 196608,
+            contextWindow: 204800,
             maxTokens: 8192,
         },
         "minimax/minimax-m2.7": {
@@ -9819,13 +9550,13 @@ 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 +9881,6 @@ 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 +9941,8 @@ 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 +9960,7 @@ export const MODELS = {
             cost: {
                 input: 0.6,
                 output: 2.5,
-                cacheRead: 0.15,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -10278,13 +9992,13 @@ 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 +10017,6 @@ 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 +10099,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
+            contextWindow: 1000000,
             maxTokens: 4096,
         },
         "nvidia/nemotron-3-super-120b-a12b:free": {
@@ -10419,7 +10116,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
+            contextWindow: 1000000,
             maxTokens: 262144,
         },
         "nvidia/nemotron-nano-12b-v2-vl:free": {
@@ -11570,7 +11267,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 32768,
+            contextWindow: 131072,
             maxTokens: 16384,
         },
         "qwen/qwen-2.5-7b-instruct": {
@@ -11587,26 +11284,9 @@ 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 +11338,6 @@ 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 +11347,12 @@ 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 +11403,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 262144,
             maxTokens: 4096,
         },
         "qwen/qwen3-30b-a3b": {
@@ -11774,7 +11420,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 40960,
+            contextWindow: 131072,
             maxTokens: 20000,
         },
         "qwen/qwen3-30b-a3b-instruct-2507": {
@@ -11821,12 +11467,12 @@ 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 +11488,7 @@ export const MODELS = {
                 cacheRead: 0.049999999999999996,
                 cacheWrite: 0,
             },
-            contextWindow: 40960,
+            contextWindow: 131072,
             maxTokens: 8192,
         },
         "qwen/qwen3-coder": {
@@ -11859,7 +11505,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
+            contextWindow: 1048576,
             maxTokens: 65536,
         },
         "qwen/qwen3-coder-30b-a3b-instruct": {
@@ -11944,7 +11590,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262000,
+            contextWindow: 1048576,
             maxTokens: 262000,
         },
         "qwen/qwen3-max": {
@@ -12029,7 +11675,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 262144,
             maxTokens: 32768,
         },
         "qwen/qwen3-vl-235b-a22b-instruct": {
@@ -12080,7 +11726,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 262144,
             maxTokens: 32768,
         },
         "qwen/qwen3-vl-30b-a3b-thinking": {
@@ -12114,7 +11760,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 262144,
             maxTokens: 32768,
         },
         "qwen/qwen3-vl-8b-instruct": {
@@ -12131,7 +11777,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 256000,
             maxTokens: 32768,
         },
         "qwen/qwen3-vl-8b-thinking": {
@@ -12148,7 +11794,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 256000,
             maxTokens: 32768,
         },
         "qwen/qwen3.5-122b-a10b": {
@@ -12194,13 +11840,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.14,
+                input: 0.13899999999999998,
                 output: 1,
-                cacheRead: 0.049999999999999996,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 81920,
+            maxTokens: 4096,
         },
         "qwen/qwen3.5-397b-a17b": {
             id: "qwen/qwen3.5-397b-a17b",
@@ -12213,7 +11859,7 @@ export const MODELS = {
             cost: {
                 input: 0.39,
                 output: 2.34,
-                cacheRead: 0.195,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -12279,8 +11925,8 @@ 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,
             },
@@ -12296,13 +11942,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.32,
+                input: 0.317,
                 output: 3.1999999999999997,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 81920,
+            maxTokens: 262140,
         },
         "qwen/qwen3.6-35b-a3b": {
             id: "qwen/qwen3.6-35b-a3b",
@@ -12330,10 +11976,10 @@ 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,
@@ -12372,6 +12018,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 65536,
         },
+        "qwen/qwen3.7-max": {
+            id: "qwen/qwen3.7-max",
+            name: "Qwen: Qwen3.7 Max",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 2.5,
+                output: 7.5,
+                cacheRead: 0,
+                cacheWrite: 3.125,
+            },
+            contextWindow: 1000000,
+            maxTokens: 65536,
+        },
         "rekaai/reka-edge": {
             id: "rekaai/reka-edge",
             name: "Reka Edge",
@@ -12449,26 +12112,26 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
+                input: 0.09,
                 output: 0.3,
-                cacheRead: 0,
+                cacheRead: 0.02,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 65536,
+            maxTokens: 16384,
         },
-        "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 +12171,6 @@ 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 +12188,6 @@ 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",
@@ -12695,22 +12222,22 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 4096,
         },
-        "x-ai/grok-code-fast-1": {
-            id: "x-ai/grok-code-fast-1",
-            name: "xAI: Grok Code Fast 1",
+        "x-ai/grok-build-0.1": {
+            id: "x-ai/grok-build-0.1",
+            name: "xAI: Grok Build 0.1",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
-                input: 0.19999999999999998,
-                output: 1.5,
-                cacheRead: 0.02,
+                input: 1,
+                output: 2,
+                cacheRead: 0.19999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
-            maxTokens: 10000,
+            maxTokens: 4096,
         },
         "xiaomi/mimo-v2-flash": {
             id: "xiaomi/mimo-v2-flash",
@@ -12721,9 +12248,9 @@ 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 +12322,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 131072,
+            maxTokens: 16384,
         },
         "z-ai/glm-4-32b": {
             id: "z-ai/glm-4-32b",
@@ -12891,13 +12418,13 @@ 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 +12452,13 @@ 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 +12520,13 @@ 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",
@@ -13078,9 +12605,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.5,
-                output: 3,
-                cacheRead: 0.049999999999999996,
+                input: 1.5,
+                output: 9,
+                cacheRead: 0.15,
                 cacheWrite: 0.08333333333333334,
             },
             contextWindow: 1048576,
@@ -13112,13 +12639,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.75,
-                output: 3.5,
-                cacheRead: 0.15,
+                input: 0.73,
+                output: 3.49,
+                cacheRead: 0.25,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 262142,
         },
         "~openai/gpt-latest": {
             id: "~openai/gpt-latest",
@@ -13155,62 +12682,384 @@ export const MODELS = {
             maxTokens: 128000,
         },
     },
-    "vercel-ai-gateway": {
-        "alibaba/qwen-3-14b": {
-            id: "alibaba/qwen-3-14b",
-            name: "Qwen3-14B",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
+    "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: 0.12,
-                output: 0.24,
-                cacheRead: 0,
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
-            contextWindow: 40960,
-            maxTokens: 16384,
+            contextWindow: 204800,
+            maxTokens: 131072,
         },
-        "alibaba/qwen-3-235b": {
-            id: "alibaba/qwen-3-235b",
-            name: "Qwen3 235B A22b Instruct 2507",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
+        "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: 0.6,
+                input: 0.3,
                 output: 1.2,
-                cacheRead: 0.6,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
-            contextWindow: 131000,
-            maxTokens: 40000,
+            contextWindow: 202752,
+            maxTokens: 131072,
         },
-        "alibaba/qwen-3-30b": {
-            id: "alibaba/qwen-3-30b",
-            name: "Qwen3-30B-A3B",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
+        "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: 0.08,
-                output: 0.29,
+                input: 0.2,
+                output: 0.6,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 40960,
-            maxTokens: 16384,
+            contextWindow: 262144,
+            maxTokens: 262144,
         },
-        "alibaba/qwen-3-32b": {
-            id: "alibaba/qwen-3-32b",
-            name: "Qwen 3 32B",
-            api: "anthropic-messages",
+        "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: 0.2,
+                output: 0.5,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 131072,
+        },
+        "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: "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: 0.88,
+                output: 0.88,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
+        "moonshotai/Kimi-K2.5": {
+            id: "moonshotai/Kimi-K2.5",
+            name: "Kimi K2.5",
+            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, "thinkingFormat": "together" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
+            input: ["text", "image"],
+            cost: {
+                input: 0.5,
+                output: 2.8,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "moonshotai/Kimi-K2.6": {
+            id: "moonshotai/Kimi-K2.6",
+            name: "Kimi K2.6",
+            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: 1.2,
+                output: 4.5,
+                cacheRead: 0.2,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 131000,
+        },
+        "openai/gpt-oss-120b": {
+            id: "openai/gpt-oss-120b",
+            name: "GPT OSS 120B",
+            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": "openai" },
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": null },
+            input: ["text"],
+            cost: {
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
+        "zai-org/GLM-5.1": {
+            id: "zai-org/GLM-5.1",
+            name: "GLM-5.1",
+            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: 1.4,
+                output: 4.4,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 202752,
+            maxTokens: 131072,
+        },
+    },
+    "vercel-ai-gateway": {
+        "alibaba/qwen-3-14b": {
+            id: "alibaba/qwen-3-14b",
+            name: "Qwen3-14B",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.12,
+                output: 0.24,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 40960,
+            maxTokens: 16384,
+        },
+        "alibaba/qwen-3-235b": {
+            id: "alibaba/qwen-3-235b",
+            name: "Qwen3 235B A22b Instruct 2507",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.6,
+                output: 1.2,
+                cacheRead: 0.6,
+                cacheWrite: 0,
+            },
+            contextWindow: 131000,
+            maxTokens: 40000,
+        },
+        "alibaba/qwen-3-30b": {
+            id: "alibaba/qwen-3-30b",
+            name: "Qwen3-30B-A3B",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.08,
+                output: 0.29,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 40960,
+            maxTokens: 16384,
+        },
+        "alibaba/qwen-3-32b": {
+            id: "alibaba/qwen-3-32b",
+            name: "Qwen 3 32B",
+            api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
@@ -13462,6 +13311,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "alibaba/qwen3.7-max": {
+            id: "alibaba/qwen3.7-max",
+            name: "Qwen 3.7 Max",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2.5,
+                output: 7.5,
+                cacheRead: 0.5,
+                cacheWrite: 3.125,
+            },
+            contextWindow: 991000,
+            maxTokens: 64000,
+        },
         "anthropic/claude-3-haiku": {
             id: "anthropic/claude-3-haiku",
             name: "Claude 3 Haiku",
@@ -13496,26 +13362,9 @@ 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",
+        "anthropic/claude-haiku-4.5": {
+            id: "anthropic/claude-haiku-4.5",
+            name: "Claude Haiku 4.5",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
@@ -13991,6 +13840,23 @@ 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",
@@ -14025,6 +13891,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "google/gemini-3.5-flash": {
+            id: "google/gemini-3.5-flash",
+            name: "Gemini 3.5 Flash",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.5,
+                output: 9,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 64000,
+        },
         "google/gemma-4-26b-a4b-it": {
             id: "google/gemma-4-26b-a4b-it",
             name: "Gemma 4 26B A4B IT",
@@ -14484,6 +14367,23 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 64000,
         },
+        "mistral/mistral-medium-3.5": {
+            id: "mistral/mistral-medium-3.5",
+            name: "Mistral Medium Latest",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.5,
+                output: 7.5,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
         "mistral/mistral-small": {
             id: "mistral/mistral-small",
             name: "Mistral Small",
@@ -15178,7 +15078,7 @@ 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",
@@ -15346,125 +15246,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 8000,
         },
-        "xai/grok-3": {
-            id: "xai/grok-3",
-            name: "Grok 3 Beta",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.75,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
-        "xai/grok-3-fast": {
-            id: "xai/grok-3-fast",
-            name: "Grok 3 Fast Beta",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 5,
-                output: 25,
-                cacheRead: 1.25,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
-        "xai/grok-3-mini": {
-            id: "xai/grok-3-mini",
-            name: "Grok 3 Mini Beta",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 0.5,
-                cacheRead: 0.075,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
-        "xai/grok-3-mini-fast": {
-            id: "xai/grok-3-mini-fast",
-            name: "Grok 3 Mini Fast Beta",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.6,
-                output: 4,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
-        "xai/grok-4": {
-            id: "xai/grok-4",
-            name: "Grok 4",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.75,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 256000,
-        },
-        "xai/grok-4-fast-non-reasoning": {
-            id: "xai/grok-4-fast-non-reasoning",
-            name: "Grok 4 Fast Non-Reasoning",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.19999999999999998,
-                output: 0.5,
-                cacheRead: 0.049999999999999996,
-                cacheWrite: 0,
-            },
-            contextWindow: 2000000,
-            maxTokens: 256000,
-        },
-        "xai/grok-4-fast-reasoning": {
-            id: "xai/grok-4-fast-reasoning",
-            name: "Grok 4 Fast Reasoning",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.19999999999999998,
-                output: 0.5,
-                cacheRead: 0.049999999999999996,
-                cacheWrite: 0,
-            },
-            contextWindow: 2000000,
-            maxTokens: 256000,
-        },
         "xai/grok-4.1-fast-non-reasoning": {
             id: "xai/grok-4.1-fast-non-reasoning",
             name: "Grok 4.1 Fast Non-Reasoning",
@@ -15479,8 +15260,8 @@ 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 +15277,8 @@ 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",
@@ -15618,18 +15399,18 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 1000000,
         },
-        "xai/grok-code-fast-1": {
-            id: "xai/grok-code-fast-1",
-            name: "Grok Code Fast 1",
+        "xai/grok-build-0.1": {
+            id: "xai/grok-build-0.1",
+            name: "Grok Build 0.1",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
-                input: 0.19999999999999998,
-                output: 1.5,
-                cacheRead: 0.02,
+                input: 1,
+                output: 2,
+                cacheRead: 0.19999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
@@ -15926,108 +15707,6 @@ export const MODELS = {
         },
     },
     "xai": {
-        "grok-2": {
-            id: "grok-2",
-            name: "Grok 2",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 2,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "grok-2-1212": {
-            id: "grok-2-1212",
-            name: "Grok 2 (1212)",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 2,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "grok-2-latest": {
-            id: "grok-2-latest",
-            name: "Grok 2 Latest",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 2,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "grok-2-vision": {
-            id: "grok-2-vision",
-            name: "Grok 2 Vision",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 2,
-                cacheWrite: 0,
-            },
-            contextWindow: 8192,
-            maxTokens: 4096,
-        },
-        "grok-2-vision-1212": {
-            id: "grok-2-vision-1212",
-            name: "Grok 2 Vision (1212)",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 2,
-                cacheWrite: 0,
-            },
-            contextWindow: 8192,
-            maxTokens: 4096,
-        },
-        "grok-2-vision-latest": {
-            id: "grok-2-vision-latest",
-            name: "Grok 2 Vision Latest",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 2,
-                cacheWrite: 0,
-            },
-            contextWindow: 8192,
-            maxTokens: 4096,
-        },
         "grok-3": {
             id: "grok-3",
             name: "Grok 3",
@@ -16062,193 +15741,6 @@ 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)",
@@ -16258,8 +15750,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 6,
+                input: 1.25,
+                output: 2.5,
                 cacheRead: 0.2,
                 cacheWrite: 0,
             },
@@ -16275,8 +15767,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 6,
+                input: 1.25,
+                output: 2.5,
                 cacheRead: 0.2,
                 cacheWrite: 0,
             },
@@ -16300,22 +15792,22 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 30000,
         },
-        "grok-beta": {
-            id: "grok-beta",
-            name: "Grok Beta",
+        "grok-build-0.1": {
+            id: "grok-build-0.1",
+            name: "Grok Build 0.1",
             api: "openai-completions",
             provider: "xai",
             baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text"],
+            reasoning: true,
+            input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 15,
-                cacheRead: 5,
+                input: 1,
+                output: 2,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 4096,
+            contextWindow: 256000,
+            maxTokens: 256000,
         },
         "grok-code-fast-1": {
             id: "grok-code-fast-1",
@@ -16323,7 +15815,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "xai",
             baseUrl: "https://api.x.ai/v1",
-            reasoning: true,
+            reasoning: false,
             input: ["text"],
             cost: {
                 input: 0.2,
@@ -16331,25 +15823,8 @@ export const MODELS = {
                 cacheRead: 0.02,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 10000,
-        },
-        "grok-vision-beta": {
-            id: "grok-vision-beta",
-            name: "Grok Vision Beta",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 5,
-                output: 15,
-                cacheRead: 5,
-                cacheWrite: 0,
-            },
-            contextWindow: 8192,
-            maxTokens: 4096,
+            contextWindow: 32768,
+            maxTokens: 8192,
         },
     },
     "xiaomi": {