npm - @fleetagent/pi-ai - Versions diffs - 0.2.3 → 0.2.5 - Mend

@fleetagent/pi-ai 0.2.3 → 0.2.5

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (8) hide show

package/dist/image-models.generated.d.ts.map +1 -1
package/dist/image-models.generated.js +4 -4
package/dist/image-models.generated.js.map +1 -1
package/dist/models.generated.d.ts +911 -293
package/dist/models.generated.d.ts.map +1 -1
package/dist/models.generated.js +1142 -625
package/dist/models.generated.js.map +1 -1
package/package.json +1 -1

package/dist/models.generated.js CHANGED Viewed

@@ -13,11 +13,11 @@ export const MODELS = {
             cost: {
                 input: 0.33,
                 output: 2.75,
-                cacheRead: 0,
-                cacheWrite: 0,
+                cacheRead: 0.0825,
+                cacheWrite: 0.33,
             },
-            contextWindow: 128000,
-            maxTokens: 4096,
+            contextWindow: 1000000,
+            maxTokens: 65535,
         },
         "amazon.nova-lite-v1:0": {
             id: "amazon.nova-lite-v1:0",
@@ -31,10 +31,10 @@ export const MODELS = {
                 input: 0.06,
                 output: 0.24,
                 cacheRead: 0.015,
-                cacheWrite: 0,
+                cacheWrite: 0.06,
             },
             contextWindow: 300000,
-            maxTokens: 8192,
+            maxTokens: 10000,
         },
         "amazon.nova-micro-v1:0": {
             id: "amazon.nova-micro-v1:0",
@@ -48,10 +48,10 @@ export const MODELS = {
                 input: 0.035,
                 output: 0.14,
                 cacheRead: 0.00875,
-                cacheWrite: 0,
+                cacheWrite: 0.035,
             },
             contextWindow: 128000,
-            maxTokens: 8192,
+            maxTokens: 10000,
         },
         "amazon.nova-pro-v1:0": {
             id: "amazon.nova-pro-v1:0",
@@ -65,10 +65,10 @@ export const MODELS = {
                 input: 0.8,
                 output: 3.2,
                 cacheRead: 0.2,
-                cacheWrite: 0,
+                cacheWrite: 0.8,
             },
             contextWindow: 300000,
-            maxTokens: 8192,
+            maxTokens: 10000,
         },
         "anthropic.claude-fable-5": {
             id: "anthropic.claude-fable-5",
@@ -165,8 +165,8 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "max" },
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 25,
+                input: 5.5,
+                output: 27.5,
                 cacheRead: 0.5,
                 cacheWrite: 6.25,
             },
@@ -251,13 +251,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
+                input: 3.3,
+                output: 16.5,
+                cacheRead: 0.33,
+                cacheWrite: 4.125,
             },
             contextWindow: 1000000,
-            maxTokens: 64000,
+            maxTokens: 128000,
         },
         "anthropic.claude-sonnet-5": {
             id: "anthropic.claude-sonnet-5",
@@ -288,10 +288,10 @@ export const MODELS = {
                 input: 0.063,
                 output: 0.252,
                 cacheRead: 0.01575,
-                cacheWrite: 0,
+                cacheWrite: 0.063,
             },
             contextWindow: 300000,
-            maxTokens: 8192,
+            maxTokens: 10000,
         },
         "apac.amazon.nova-micro-v1:0": {
             id: "apac.amazon.nova-micro-v1:0",
@@ -305,10 +305,10 @@ export const MODELS = {
                 input: 0.037,
                 output: 0.148,
                 cacheRead: 0.00925,
-                cacheWrite: 0,
+                cacheWrite: 0.037,
             },
             contextWindow: 128000,
-            maxTokens: 8192,
+            maxTokens: 10000,
         },
         "apac.amazon.nova-pro-v1:0": {
             id: "apac.amazon.nova-pro-v1:0",
@@ -322,10 +322,27 @@ export const MODELS = {
                 input: 0.84,
                 output: 3.36,
                 cacheRead: 0.21,
-                cacheWrite: 0,
+                cacheWrite: 0.84,
             },
             contextWindow: 300000,
-            maxTokens: 8192,
+            maxTokens: 10000,
+        },
+        "apac.anthropic.claude-sonnet-4-20250514-v1:0": {
+            id: "apac.anthropic.claude-sonnet-4-20250514-v1:0",
+            name: "Claude Sonnet 4 (APAC)",
+            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-haiku-4-5-20251001-v1:0": {
             id: "au.anthropic.claude-haiku-4-5-20251001-v1:0",
@@ -336,10 +353,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 5,
-                cacheRead: 0.1,
-                cacheWrite: 1.25,
+                input: 1.1,
+                output: 5.5,
+                cacheRead: 0.11,
+                cacheWrite: 1.375,
             },
             contextWindow: 200000,
             maxTokens: 64000,
@@ -354,8 +371,8 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "max" },
             input: ["text", "image"],
             cost: {
-                input: 16.5,
-                output: 82.5,
+                input: 5.5,
+                output: 27.5,
                 cacheRead: 0.5,
                 cacheWrite: 6.25,
             },
@@ -389,10 +406,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 25,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 5.5,
+                output: 27.5,
+                cacheRead: 0.55,
+                cacheWrite: 6.875,
             },
             contextWindow: 1000000,
             maxTokens: 128000,
@@ -406,10 +423,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 25,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 5.5,
+                output: 27.5,
+                cacheRead: 0.55,
+                cacheWrite: 6.875,
             },
             contextWindow: 1000000,
             maxTokens: 128000,
@@ -423,10 +440,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
+                input: 3.3,
+                output: 16.5,
+                cacheRead: 0.33,
+                cacheWrite: 4.125,
             },
             contextWindow: 200000,
             maxTokens: 64000,
@@ -457,10 +474,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 0.2,
-                cacheWrite: 2.5,
+                input: 2.2,
+                output: 11,
+                cacheRead: 0.22,
+                cacheWrite: 2.75,
             },
             contextWindow: 1000000,
             maxTokens: 128000,
@@ -477,27 +494,10 @@ export const MODELS = {
                 input: 0.064,
                 output: 0.256,
                 cacheRead: 0.016,
-                cacheWrite: 0,
+                cacheWrite: 0.064,
             },
             contextWindow: 300000,
-            maxTokens: 8192,
-        },
-        "deepseek.r1-v1:0": {
-            id: "deepseek.r1-v1:0",
-            name: "DeepSeek-R1",
-            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,
+            maxTokens: 10000,
         },
         "deepseek.v3-v1:0": {
             id: "deepseek.v3-v1:0",
@@ -518,7 +518,7 @@ export const MODELS = {
         },
         "deepseek.v3.2": {
             id: "deepseek.v3.2",
-            name: "DeepSeek-V3.2",
+            name: "DeepSeek V3.2",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -545,10 +545,10 @@ export const MODELS = {
                 input: 0.374,
                 output: 3.157,
                 cacheRead: 0.0935,
-                cacheWrite: 0,
+                cacheWrite: 0.374,
             },
             contextWindow: 1000000,
-            maxTokens: 64000,
+            maxTokens: 65535,
         },
         "eu.amazon.nova-lite-v1:0": {
             id: "eu.amazon.nova-lite-v1:0",
@@ -562,10 +562,10 @@ export const MODELS = {
                 input: 0.069,
                 output: 0.276,
                 cacheRead: 0.01725,
-                cacheWrite: 0,
+                cacheWrite: 0.069,
             },
             contextWindow: 300000,
-            maxTokens: 8192,
+            maxTokens: 10000,
         },
         "eu.amazon.nova-micro-v1:0": {
             id: "eu.amazon.nova-micro-v1:0",
@@ -579,10 +579,10 @@ export const MODELS = {
                 input: 0.04,
                 output: 0.16,
                 cacheRead: 0.01,
-                cacheWrite: 0,
+                cacheWrite: 0.04,
             },
             contextWindow: 128000,
-            maxTokens: 8192,
+            maxTokens: 10000,
         },
         "eu.amazon.nova-pro-v1:0": {
             id: "eu.amazon.nova-pro-v1:0",
@@ -596,10 +596,10 @@ export const MODELS = {
                 input: 0.92,
                 output: 3.68,
                 cacheRead: 0.23,
-                cacheWrite: 0,
+                cacheWrite: 0.92,
             },
             contextWindow: 300000,
-            maxTokens: 8192,
+            maxTokens: 10000,
         },
         "eu.anthropic.claude-fable-5": {
             id: "eu.anthropic.claude-fable-5",
@@ -722,6 +722,23 @@ 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)",
@@ -754,7 +771,7 @@ export const MODELS = {
                 cacheWrite: 4.125,
             },
             contextWindow: 1000000,
-            maxTokens: 64000,
+            maxTokens: 128000,
         },
         "eu.anthropic.claude-sonnet-5": {
             id: "eu.anthropic.claude-sonnet-5",
@@ -802,10 +819,10 @@ export const MODELS = {
                 input: 0.3,
                 output: 2.5,
                 cacheRead: 0.075,
-                cacheWrite: 0,
+                cacheWrite: 0.3,
             },
             contextWindow: 1000000,
-            maxTokens: 64000,
+            maxTokens: 65535,
         },
         "global.anthropic.claude-fable-5": {
             id: "global.anthropic.claude-fable-5",
@@ -945,6 +962,23 @@ 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)",
@@ -977,7 +1011,7 @@ export const MODELS = {
                 cacheWrite: 3.75,
             },
             contextWindow: 1000000,
-            maxTokens: 64000,
+            maxTokens: 128000,
         },
         "global.anthropic.claude-sonnet-5": {
             id: "global.anthropic.claude-sonnet-5",
@@ -1085,30 +1119,47 @@ export const MODELS = {
             contextWindow: 500000,
             maxTokens: 500000,
         },
-        "google.gemma-3-27b-it": {
-            id: "google.gemma-3-27b-it",
-            name: "Google Gemma 3 27B Instruct",
+        "google.gemma-4-26b-a4b": {
+            id: "google.gemma-4-26b-a4b",
+            name: "Gemma 4 26B A4B IT",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: false,
+            reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.12,
-                output: 0.2,
+                input: 0.13,
+                output: 0.4,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 202752,
-            maxTokens: 8192,
+            contextWindow: 262144,
+            maxTokens: 32768,
         },
-        "google.gemma-3-4b-it": {
-            id: "google.gemma-3-4b-it",
-            name: "Gemma 3 4B IT",
+        "google.gemma-4-31b": {
+            id: "google.gemma-4-31b",
+            name: "Gemma 4 31B IT",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: false,
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.14,
+                output: 0.4,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 32768,
+        },
+        "google.gemma-4-e2b": {
+            id: "google.gemma-4-e2b",
+            name: "Gemma 4 E2B IT",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
             input: ["text", "image"],
             cost: {
                 input: 0.04,
@@ -1116,8 +1167,44 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 4096,
+            contextWindow: 131072,
+            maxTokens: 8192,
+        },
+        "in.openai.gpt-5.6-luna": {
+            id: "in.openai.gpt-5.6-luna",
+            name: "GPT-5.6 Luna (India)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 0.22,
+                output: 1.32,
+                cacheRead: 0.022,
+                cacheWrite: 0.275,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
+        "in.openai.gpt-5.6-terra": {
+            id: "in.openai.gpt-5.6-terra",
+            name: "GPT-5.6 Terra (India)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 2.2,
+                output: 13.2,
+                cacheRead: 0.22,
+                cacheWrite: 2.75,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
         },
         "jp.amazon.nova-2-lite-v1:0": {
             id: "jp.amazon.nova-2-lite-v1:0",
@@ -1131,10 +1218,10 @@ export const MODELS = {
                 input: 0.396,
                 output: 3.311,
                 cacheRead: 0.099,
-                cacheWrite: 0,
+                cacheWrite: 0.396,
             },
             contextWindow: 1000000,
-            maxTokens: 64000,
+            maxTokens: 65535,
         },
         "jp.anthropic.claude-haiku-4-5-20251001-v1:0": {
             id: "jp.anthropic.claude-haiku-4-5-20251001-v1:0",
@@ -1145,10 +1232,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 5,
-                cacheRead: 0.1,
-                cacheWrite: 1.25,
+                input: 1.1,
+                output: 5.5,
+                cacheRead: 0.11,
+                cacheWrite: 1.375,
             },
             contextWindow: 200000,
             maxTokens: 64000,
@@ -1163,10 +1250,10 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 25,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 5.5,
+                output: 27.5,
+                cacheRead: 0.55,
+                cacheWrite: 6.875,
             },
             contextWindow: 1000000,
             maxTokens: 128000,
@@ -1180,10 +1267,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 25,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 5.5,
+                output: 27.5,
+                cacheRead: 0.55,
+                cacheWrite: 6.875,
             },
             contextWindow: 1000000,
             maxTokens: 128000,
@@ -1197,10 +1284,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 25,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 5.5,
+                output: 27.5,
+                cacheRead: 0.55,
+                cacheWrite: 6.875,
             },
             contextWindow: 1000000,
             maxTokens: 128000,
@@ -1214,10 +1301,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
+                input: 3.3,
+                output: 16.5,
+                cacheRead: 0.33,
+                cacheWrite: 4.125,
             },
             contextWindow: 200000,
             maxTokens: 64000,
@@ -1231,13 +1318,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
+                input: 3.3,
+                output: 16.5,
+                cacheRead: 0.33,
+                cacheWrite: 4.125,
             },
             contextWindow: 1000000,
-            maxTokens: 64000,
+            maxTokens: 128000,
         },
         "jp.anthropic.claude-sonnet-5": {
             id: "jp.anthropic.claude-sonnet-5",
@@ -1248,10 +1335,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 0.2,
-                cacheWrite: 2.5,
+                input: 2.2,
+                output: 11,
+                cacheRead: 0.22,
+                cacheWrite: 2.75,
             },
             contextWindow: 1000000,
             maxTokens: 128000,
@@ -1322,7 +1409,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
-            maxTokens: 16384,
+            maxTokens: 8192,
         },
         "meta.llama4-scout-17b-instruct-v1:0": {
             id: "meta.llama4-scout-17b-instruct-v1:0",
@@ -1338,12 +1425,12 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 3500000,
-            maxTokens: 16384,
+            contextWindow: 10000000,
+            maxTokens: 8192,
         },
         "minimax.minimax-m2": {
             id: "minimax.minimax-m2",
-            name: "MiniMax M2",
+            name: "MiniMax-M2",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -1360,7 +1447,7 @@ export const MODELS = {
         },
         "minimax.minimax-m2.1": {
             id: "minimax.minimax-m2.1",
-            name: "MiniMax M2.1",
+            name: "MiniMax-M2.1",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -1377,7 +1464,7 @@ export const MODELS = {
         },
         "minimax.minimax-m2.5": {
             id: "minimax.minimax-m2.5",
-            name: "MiniMax M2.5",
+            name: "MiniMax-M2.5",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -1433,7 +1520,7 @@ export const MODELS = {
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
             reasoning: false,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 0.2,
                 output: 0.2,
@@ -1467,7 +1554,7 @@ export const MODELS = {
             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,
@@ -1525,7 +1612,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 32768,
             maxTokens: 4096,
         },
         "mistral.voxtral-small-24b-2507": {
@@ -1537,12 +1624,12 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.15,
-                output: 0.35,
+                input: 0.1,
+                output: 0.3,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 32000,
+            contextWindow: 32768,
             maxTokens: 8192,
         },
         "moonshot.kimi-k2-thinking": {
@@ -1577,7 +1664,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262143,
-            maxTokens: 16000,
+            maxTokens: 16384,
         },
         "nvidia.nemotron-nano-12b-v2": {
             id: "nvidia.nemotron-nano-12b-v2",
@@ -1594,7 +1681,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 4096,
+            maxTokens: 8192,
         },
         "nvidia.nemotron-nano-3-30b": {
             id: "nvidia.nemotron-nano-3-30b",
@@ -1610,8 +1697,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 4096,
+            contextWindow: 262144,
+            maxTokens: 8192,
         },
         "nvidia.nemotron-nano-9b-v2": {
             id: "nvidia.nemotron-nano-9b-v2",
@@ -1627,8 +1714,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 4096,
+            contextWindow: 131072,
+            maxTokens: 8192,
         },
         "nvidia.nemotron-super-3-120b": {
             id: "nvidia.nemotron-super-3-120b",
@@ -1829,7 +1916,7 @@ export const MODELS = {
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: false,
+            reasoning: true,
             input: ["text"],
             cost: {
                 input: 0.15,
@@ -1846,7 +1933,7 @@ export const MODELS = {
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: false,
+            reasoning: true,
             input: ["text"],
             cost: {
                 input: 0.07,
@@ -1859,7 +1946,7 @@ export const MODELS = {
         },
         "qwen.qwen3-235b-a22b-2507-v1:0": {
             id: "qwen.qwen3-235b-a22b-2507-v1:0",
-            name: "Qwen3 235B A22B 2507",
+            name: "Qwen3 235B-A22B Instruct 2507",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -1876,7 +1963,7 @@ export const MODELS = {
         },
         "qwen.qwen3-32b-v1:0": {
             id: "qwen.qwen3-32b-v1:0",
-            name: "Qwen3 32B (dense)",
+            name: "Qwen3 32B",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -1888,12 +1975,12 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 16384,
+            contextWindow: 32768,
             maxTokens: 16384,
         },
         "qwen.qwen3-coder-30b-a3b-v1:0": {
             id: "qwen.qwen3-coder-30b-a3b-v1:0",
-            name: "Qwen3 Coder 30B A3B Instruct",
+            name: "Qwen3-Coder 30B-A3B Instruct",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -1910,14 +1997,14 @@ export const MODELS = {
         },
         "qwen.qwen3-coder-480b-a35b-v1:0": {
             id: "qwen.qwen3-coder-480b-a35b-v1:0",
-            name: "Qwen3 Coder 480B A35B Instruct",
+            name: "Qwen3-Coder 480B-A35B Instruct",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.22,
+                input: 0.45,
                 output: 1.8,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -1931,51 +2018,85 @@ export const MODELS = {
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: true,
+            reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.22,
-                output: 1.8,
+                input: 0.5,
+                output: 1.2,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 262144,
             maxTokens: 65536,
         },
         "qwen.qwen3-next-80b-a3b": {
             id: "qwen.qwen3-next-80b-a3b",
-            name: "Qwen/Qwen3-Next-80B-A3B-Instruct",
+            name: "Qwen3-Next 80B-A3B Instruct",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.14,
-                output: 1.4,
+                input: 0.15,
+                output: 1.2,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262000,
+            contextWindow: 262144,
             maxTokens: 262000,
         },
         "qwen.qwen3-vl-235b-a22b": {
             id: "qwen.qwen3-vl-235b-a22b",
-            name: "Qwen/Qwen3-VL-235B-A22B-Instruct",
+            name: "Qwen3 VL 235B A22B Instruct",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.3,
-                output: 1.5,
+                input: 0.53,
+                output: 2.66,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262000,
+            contextWindow: 262144,
             maxTokens: 262000,
         },
+        "us-gov.openai.gpt-oss-120b-1:0": {
+            id: "us-gov.openai.gpt-oss-120b-1:0",
+            name: "gpt-oss-120b (GovCloud)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.18,
+                output: 0.72,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
+        "us-gov.openai.gpt-oss-20b-1:0": {
+            id: "us-gov.openai.gpt-oss-20b-1:0",
+            name: "gpt-oss-20b (GovCloud)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.084,
+                output: 0.36,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
         "us.amazon.nova-2-lite-v1:0": {
             id: "us.amazon.nova-2-lite-v1:0",
             name: "Nova 2 Lite (US)",
@@ -1988,10 +2109,10 @@ export const MODELS = {
                 input: 0.33,
                 output: 2.75,
                 cacheRead: 0.0825,
-                cacheWrite: 0,
+                cacheWrite: 0.33,
             },
             contextWindow: 1000000,
-            maxTokens: 64000,
+            maxTokens: 65535,
         },
         "us.amazon.nova-lite-v1:0": {
             id: "us.amazon.nova-lite-v1:0",
@@ -2005,10 +2126,10 @@ export const MODELS = {
                 input: 0.06,
                 output: 0.24,
                 cacheRead: 0.015,
-                cacheWrite: 0,
+                cacheWrite: 0.06,
             },
             contextWindow: 300000,
-            maxTokens: 8192,
+            maxTokens: 10000,
         },
         "us.amazon.nova-micro-v1:0": {
             id: "us.amazon.nova-micro-v1:0",
@@ -2022,10 +2143,27 @@ export const MODELS = {
                 input: 0.035,
                 output: 0.14,
                 cacheRead: 0.00875,
-                cacheWrite: 0,
+                cacheWrite: 0.035,
             },
             contextWindow: 128000,
-            maxTokens: 8192,
+            maxTokens: 10000,
+        },
+        "us.amazon.nova-premier-v1:0": {
+            id: "us.amazon.nova-premier-v1:0",
+            name: "Nova Premier (US)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 2.5,
+                output: 12.5,
+                cacheRead: 0.625,
+                cacheWrite: 2.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 10000,
         },
         "us.amazon.nova-pro-v1:0": {
             id: "us.amazon.nova-pro-v1:0",
@@ -2039,10 +2177,10 @@ export const MODELS = {
                 input: 0.8,
                 output: 3.2,
                 cacheRead: 0.2,
-                cacheWrite: 0,
+                cacheWrite: 0.8,
             },
             contextWindow: 300000,
-            maxTokens: 8192,
+            maxTokens: 10000,
         },
         "us.anthropic.claude-fable-5": {
             id: "us.anthropic.claude-fable-5",
@@ -2053,10 +2191,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 10,
-                output: 50,
-                cacheRead: 1,
-                cacheWrite: 12.5,
+                input: 11,
+                output: 55,
+                cacheRead: 1.1,
+                cacheWrite: 13.75,
             },
             contextWindow: 1000000,
             maxTokens: 128000,
@@ -2087,10 +2225,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 5,
-                cacheRead: 0.1,
-                cacheWrite: 1.25,
+                input: 1.1,
+                output: 5.5,
+                cacheRead: 0.11,
+                cacheWrite: 1.375,
             },
             contextWindow: 200000,
             maxTokens: 64000,
@@ -2121,10 +2259,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 25,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 5.5,
+                output: 27.5,
+                cacheRead: 0.55,
+                cacheWrite: 6.875,
             },
             contextWindow: 200000,
             maxTokens: 64000,
@@ -2139,8 +2277,8 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "max" },
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 25,
+                input: 5.5,
+                output: 27.5,
                 cacheRead: 0.5,
                 cacheWrite: 6.25,
             },
@@ -2157,10 +2295,10 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 25,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 5.5,
+                output: 27.5,
+                cacheRead: 0.55,
+                cacheWrite: 6.875,
             },
             contextWindow: 1000000,
             maxTokens: 128000,
@@ -2173,11 +2311,11 @@ export const MODELS = {
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
             reasoning: true,
             input: ["text", "image"],
-            cost: {
-                input: 5,
-                output: 25,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+            cost: {
+                input: 5.5,
+                output: 27.5,
+                cacheRead: 0.55,
+                cacheWrite: 6.875,
             },
             contextWindow: 1000000,
             maxTokens: 128000,
@@ -2191,17 +2329,17 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 25,
-                cacheRead: 0.5,
-                cacheWrite: 6.25,
+                input: 5.5,
+                output: 27.5,
+                cacheRead: 0.55,
+                cacheWrite: 6.875,
             },
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "us.anthropic.claude-sonnet-4-5-20250929-v1:0": {
-            id: "us.anthropic.claude-sonnet-4-5-20250929-v1:0",
-            name: "Claude Sonnet 4.5 (US)",
+        "us.anthropic.claude-sonnet-4-20250514-v1:0": {
+            id: "us.anthropic.claude-sonnet-4-20250514-v1:0",
+            name: "Claude Sonnet 4 (US)",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
@@ -2216,56 +2354,56 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 64000,
         },
-        "us.anthropic.claude-sonnet-4-6": {
-            id: "us.anthropic.claude-sonnet-4-6",
-            name: "Claude Sonnet 4.6 (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",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
+                input: 3.3,
+                output: 16.5,
+                cacheRead: 0.33,
+                cacheWrite: 4.125,
             },
-            contextWindow: 1000000,
+            contextWindow: 200000,
             maxTokens: 64000,
         },
-        "us.anthropic.claude-sonnet-5": {
-            id: "us.anthropic.claude-sonnet-5",
-            name: "Claude Sonnet 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",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 0.2,
-                cacheWrite: 2.5,
+                input: 3.3,
+                output: 16.5,
+                cacheRead: 0.33,
+                cacheWrite: 4.125,
             },
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "us.deepseek.r1-v1:0": {
-            id: "us.deepseek.r1-v1:0",
-            name: "DeepSeek-R1 (US)",
+        "us.anthropic.claude-sonnet-5": {
+            id: "us.anthropic.claude-sonnet-5",
+            name: "Claude Sonnet 5 (US)",
             api: "bedrock-converse-stream",
             provider: "amazon-bedrock",
             baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
-                input: 1.35,
-                output: 5.4,
-                cacheRead: 0,
-                cacheWrite: 0,
+                input: 2.2,
+                output: 11,
+                cacheRead: 0.22,
+                cacheWrite: 2.75,
             },
-            contextWindow: 128000,
-            maxTokens: 32768,
+            contextWindow: 1000000,
+            maxTokens: 128000,
         },
         "us.meta.llama3-1-70b-instruct-v1:0": {
             id: "us.meta.llama3-1-70b-instruct-v1:0",
@@ -2333,7 +2471,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
-            maxTokens: 16384,
+            maxTokens: 8192,
         },
         "us.meta.llama4-scout-17b-instruct-v1:0": {
             id: "us.meta.llama4-scout-17b-instruct-v1:0",
@@ -2349,8 +2487,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 3500000,
-            maxTokens: 16384,
+            contextWindow: 10000000,
+            maxTokens: 8192,
         },
         "us.mistral.pixtral-large-2502-v1:0": {
             id: "us.mistral.pixtral-large-2502-v1:0",
@@ -2609,7 +2747,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 202752,
-            maxTokens: 101376,
+            maxTokens: 131072,
         },
     },
     "anthropic": {
@@ -4625,6 +4763,24 @@ export const MODELS = {
             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: {
+                input: 1.2,
+                output: 1.2,
+                cacheRead: 0.6,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
         "accounts/fireworks/models/deepseek-v4-pro-0813": {
             id: "accounts/fireworks/models/deepseek-v4-pro-0813",
             name: "DeepSeek V4 Pro 0813",
@@ -4643,6 +4799,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 384000,
         },
+        "accounts/fireworks/models/deepseek-v4p1-flash": {
+            id: "accounts/fireworks/models/deepseek-v4p1-flash",
+            name: "DeepSeek V4.1 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", "image"],
+            cost: {
+                input: 0.22,
+                output: 0.66,
+                cacheRead: 0.007,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
         "accounts/fireworks/models/glm-5p2": {
             id: "accounts/fireworks/models/glm-5p2",
             name: "GLM 5.2",
@@ -4787,6 +4961,24 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 131072,
         },
+        "accounts/fireworks/models/minimax-m2p7": {
+            id: "accounts/fireworks/models/minimax-m2p7",
+            name: "MiniMax-M2.7",
+            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: 1.2,
+                output: 1.2,
+                cacheRead: 0.6,
+                cacheWrite: 0,
+            },
+            contextWindow: 196608,
+            maxTokens: 131072,
+        },
         "accounts/fireworks/models/minimax-m3": {
             id: "accounts/fireworks/models/minimax-m3",
             name: "MiniMax-M3",
@@ -4795,7 +4987,7 @@ export const MODELS = {
             baseUrl: "https://api.fireworks.ai/inference",
             compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
             reasoning: true,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
                 input: 0.3,
                 output: 1.2,
@@ -4835,7 +5027,7 @@ export const MODELS = {
             cost: {
                 input: 0.6,
                 output: 2.4,
-                cacheRead: 0.119,
+                cacheRead: 0.12,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -4903,7 +5095,7 @@ export const MODELS = {
             baseUrl: "https://api.fireworks.ai/inference",
             compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 2,
                 output: 6,
@@ -4913,6 +5105,42 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 131072,
         },
+        "accounts/fireworks/routers/deepseek-flash-latest": {
+            id: "accounts/fireworks/routers/deepseek-flash-latest",
+            name: "DeepSeek Flash Latest",
+            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: {
+                input: 0.22,
+                output: 0.66,
+                cacheRead: 0.007,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
+        "accounts/fireworks/routers/deepseek-pro-latest": {
+            id: "accounts/fireworks/routers/deepseek-pro-latest",
+            name: "DeepSeek Pro Latest",
+            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: 1.32,
+                output: 3.96,
+                cacheRead: 0.044,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
         "accounts/fireworks/routers/glm-5p2-fast": {
             id: "accounts/fireworks/routers/glm-5p2-fast",
             name: "GLM 5.2 Fast",
@@ -4949,6 +5177,78 @@ export const MODELS = {
             contextWindow: 1048572,
             maxTokens: 262144,
         },
+        "accounts/fireworks/routers/glm-fast-latest": {
+            id: "accounts/fireworks/routers/glm-fast-latest",
+            name: "GLM 5.3 Fast (Latest)",
+            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: 2.1,
+                output: 6.6,
+                cacheRead: 0.39,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048572,
+            maxTokens: 262144,
+        },
+        "accounts/fireworks/routers/glm-flash-latest": {
+            id: "accounts/fireworks/routers/glm-flash-latest",
+            name: "GLM Flash Latest (GLM 5.3 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", "image"],
+            cost: {
+                input: 0.15,
+                output: 0.5,
+                cacheRead: 0.03,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048573,
+            maxTokens: 131072,
+        },
+        "accounts/fireworks/routers/glm-latest": {
+            id: "accounts/fireworks/routers/glm-latest",
+            name: "GLM Latest",
+            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: 1.4,
+                output: 4.4,
+                cacheRead: 0.26,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048573,
+            maxTokens: 262144,
+        },
+        "accounts/fireworks/routers/kimi-fast-latest": {
+            id: "accounts/fireworks/routers/kimi-fast-latest",
+            name: "Kimi Fast Latest",
+            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: {
+                input: 4.5,
+                output: 22.5,
+                cacheRead: 0.45,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
         "accounts/fireworks/routers/kimi-k2p6-turbo": {
             id: "accounts/fireworks/routers/kimi-k2p6-turbo",
             name: "Kimi K2.6 Turbo",
@@ -4967,9 +5267,63 @@ export const MODELS = {
             contextWindow: 262000,
             maxTokens: 262000,
         },
-        "accounts/fireworks/routers/kimi-k3-fast": {
-            id: "accounts/fireworks/routers/kimi-k3-fast",
-            name: "Kimi K3 Fast",
+        "accounts/fireworks/routers/kimi-k3-fast": {
+            id: "accounts/fireworks/routers/kimi-k3-fast",
+            name: "Kimi K3 Fast",
+            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: {
+                input: 4.5,
+                output: 22.5,
+                cacheRead: 0.45,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
+        "accounts/fireworks/routers/kimi-latest": {
+            id: "accounts/fireworks/routers/kimi-latest",
+            name: "Kimi Latest",
+            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: {
+                input: 3,
+                output: 15,
+                cacheRead: 0.3,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
+        "accounts/fireworks/routers/minimax-latest": {
+            id: "accounts/fireworks/routers/minimax-latest",
+            name: "MiniMax Latest",
+            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: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
+                cacheWrite: 0,
+            },
+            contextWindow: 512000,
+            maxTokens: 512000,
+        },
+        "accounts/fireworks/routers/qwen-max-latest": {
+            id: "accounts/fireworks/routers/qwen-max-latest",
+            name: "Qwen Max Latest (Qwen3.8 Max)",
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
@@ -4977,12 +5331,12 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 4.5,
-                output: 22.5,
-                cacheRead: 0.45,
+                input: 2,
+                output: 6,
+                cacheRead: 0.25,
                 cacheWrite: 0,
             },
-            contextWindow: 1048576,
+            contextWindow: 262144,
             maxTokens: 131072,
         },
     },
@@ -6999,6 +7353,78 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 384000,
         },
+        "deepseek-ai/DeepSeek-V4.1-Flash": {
+            id: "deepseek-ai/DeepSeek-V4.1-Flash",
+            name: "DeepSeek V4.1 Flash",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 384000,
+        },
+        "google/gemma-3-12b-it": {
+            id: "google/gemma-3-12b-it",
+            name: "Gemma 3 12B IT",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.05,
+                output: 0.15,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
+        "google/gemma-3-27b-it": {
+            id: "google/gemma-3-27b-it",
+            name: "Gemma 3 27B IT",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.08,
+                output: 0.16,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
+        "google/gemma-3-4b-it": {
+            id: "google/gemma-3-4b-it",
+            name: "Gemma 3 4B IT",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.05,
+                output: 0.1,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
         "google/gemma-4-26B-A4B-it": {
             id: "google/gemma-4-26B-A4B-it",
             name: "Gemma 4 26B A4B IT",
@@ -7579,7 +8005,7 @@ export const MODELS = {
         },
         "kimi-for-coding": {
             id: "kimi-for-coding",
-            name: "Kimi K2.7 Code",
+            name: "kimi-for-coding",
             api: "anthropic-messages",
             provider: "kimi-coding",
             baseUrl: "https://api.kimi.com/coding",
@@ -7592,7 +8018,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
+            contextWindow: 1048576,
             maxTokens: 32768,
         },
         "kimi-for-coding-highspeed": {
@@ -10520,25 +10946,25 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
-    },
-    "opencode-go": {
-        "deepseek-flash": {
-            id: "deepseek-flash",
-            name: "DeepSeek V4.1 Flash",
-            api: "openai-completions",
-            provider: "opencode-go",
-            baseUrl: "https://opencode.ai/zen/go/v1",
+        "union-alpha": {
+            id: "union-alpha",
+            name: "Union Alpha Free",
+            api: "anthropic-messages",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0.003,
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 384000,
+            contextWindow: 262144,
+            maxTokens: 131072,
         },
+    },
+    "opencode-go": {
         "deepseek-v4-flash": {
             id: "deepseek-v4-flash",
             name: "DeepSeek V4 Flash",
@@ -10596,6 +11022,25 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 384000,
         },
+        "deepseek-v4.1-flash": {
+            id: "deepseek-v4.1-flash",
+            name: "DeepSeek V4.1 Flash",
+            api: "openai-completions",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0.003,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
         "glm-5.1": {
             id: "glm-5.1",
             name: "GLM-5.1",
@@ -10991,6 +11436,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 131072,
         },
+        "union-alpha": {
+            id: "union-alpha",
+            name: "Union Alpha Free",
+            api: "anthropic-messages",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 131072,
+        },
     },
     "openrouter": {
         "aion-labs/aion-2.0": {
@@ -11441,7 +11903,7 @@ export const MODELS = {
         },
         "anthropic/claude-opus-5": {
             id: "anthropic/claude-opus-5",
-            name: "Claude Opus 5",
+            name: "Anthropic: Claude Opus 5",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
@@ -11458,7 +11920,7 @@ export const MODELS = {
         },
         "anthropic/claude-opus-5:batch": {
             id: "anthropic/claude-opus-5:batch",
-            name: "Claude Opus 5 (batch)",
+            name: "Anthropic: Claude Opus 5 (batch)",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
@@ -11805,9 +12267,9 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.29,
-                output: 1.1400000000000001,
-                cacheRead: 0.11,
+                input: 0.25,
+                output: 1,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
@@ -11926,9 +12388,9 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 0.088606,
-                output: 0.177212,
-                cacheRead: 0.017721200000000003,
+                input: 0.07,
+                output: 0.14,
+                cacheRead: 0.014,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -11945,9 +12407,9 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 0.065,
-                output: 0.18,
-                cacheRead: 0.016,
+                input: 0.06,
+                output: 0.12,
+                cacheRead: 0.012,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
@@ -12021,13 +12483,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 0.9552599999999999,
-                output: 1.9105199999999998,
-                cacheRead: 0.07960500000000001,
+                input: 1.5999999999999999,
+                output: 3.1999999999999997,
+                cacheRead: 0.135,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 384000,
+            maxTokens: 393216,
         },
         "deepseek/deepseek-v4-pro-0813": {
             id: "deepseek/deepseek-v4-pro-0813",
@@ -12040,13 +12502,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 1.0494,
-                output: 3.1482,
-                cacheRead: 0.03498,
+                input: 0.57948,
+                output: 1.73844,
+                cacheRead: 0.018438,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 384000,
+            maxTokens: 393216,
         },
         "deepseek/deepseek-v4-pro-0813:batch": {
             id: "deepseek/deepseek-v4-pro-0813:batch",
@@ -12067,6 +12529,25 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 943718,
         },
+        "deepseek/deepseek-v4.1-flash": {
+            id: "deepseek/deepseek-v4.1-flash",
+            name: "DeepSeek: DeepSeek V4.1 Flash",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            compat: { "requiresReasoningContentOnAssistantMessages": true },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0.003,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 384000,
+        },
         "dots-studio/dots-3-note-preview:free": {
             id: "dots-studio/dots-3-note-preview:free",
             name: "Dots Studio: Dots3-Note Preview (free)",
@@ -12186,23 +12667,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "google/gemini-2.5-pro-preview-05-06": {
-            id: "google/gemini-2.5-pro-preview-05-06",
-            name: "Google: Gemini 2.5 Pro Preview 05-06",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1.25,
-                output: 10,
-                cacheRead: 0.125,
-                cacheWrite: 0.375,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65535,
-        },
         "google/gemini-2.5-pro:batch": {
             id: "google/gemini-2.5-pro:batch",
             name: "Google: Gemini 2.5 Pro (batch)",
@@ -12586,13 +13050,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.07,
-                output: 0.33999999999999997,
-                cacheRead: 0,
+                input: 0.09,
+                output: 0.3,
+                cacheRead: 0.049999999999999996,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 235929,
         },
         "google/gemma-4-26b-a4b-it:free": {
             id: "google/gemma-4-26b-a4b-it:free",
@@ -12628,23 +13092,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 16384,
         },
-        "google/gemma-4-31b-it:batch": {
-            id: "google/gemma-4-31b-it:batch",
-            name: "Google: Gemma 4 31B (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.39,
-                output: 0.9700000000000001,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 235929,
-        },
         "google/gemma-4-31b-it:free": {
             id: "google/gemma-4-31b-it:free",
             name: "Google: Gemma 4 31B (free)",
@@ -12783,6 +13230,40 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
+        "inclusionai/ling-3.0-flash-vl": {
+            id: "inclusionai/ling-3.0-flash-vl",
+            name: "inclusionAI: Ling 3.0 Flash VL",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.06,
+                output: 0.18,
+                cacheRead: 0.012,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 32768,
+        },
+        "inclusionai/ling-3.0-flash-vl:free": {
+            id: "inclusionai/ling-3.0-flash-vl:free",
+            name: "inclusionAI: Ling 3.0 Flash VL (free)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 32768,
+        },
         "kwaipilot/kat-coder-pro-v2": {
             id: "kwaipilot/kat-coder-pro-v2",
             name: "Kwaipilot: KAT-Coder-Pro V2",
@@ -12911,13 +13392,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.19999999999999998,
-                output: 0.696,
+                input: 0.1875,
+                output: 0.6525,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 115200,
+            maxTokens: 16384,
         },
         "meta-llama/llama-4-scout": {
             id: "meta-llama/llama-4-scout",
@@ -13064,7 +13545,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.55,
+                input: 0.39999999999999997,
                 output: 2.2,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -13115,13 +13596,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.3,
-                output: 1.2,
-                cacheRead: 0.03,
+                input: 0.27,
+                output: 1.08,
+                cacheRead: 0.027,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
-            maxTokens: 131072,
+            maxTokens: 128000,
         },
         "minimax/minimax-m2.7": {
             id: "minimax/minimax-m2.7",
@@ -13523,12 +14004,12 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.075,
-                output: 0.19999999999999998,
+                input: 0.09375,
+                output: 0.25,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 256000,
             maxTokens: 16384,
         },
         "mistralai/mixtral-8x22b-instruct": {
@@ -13580,7 +14061,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 100352,
+            maxTokens: 98304,
         },
         "moonshotai/kimi-k2-0905": {
             id: "moonshotai/kimi-k2-0905",
@@ -13597,7 +14078,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 100352,
+            maxTokens: 98304,
         },
         "moonshotai/kimi-k2-thinking": {
             id: "moonshotai/kimi-k2-thinking",
@@ -13614,7 +14095,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 100352,
+            maxTokens: 98304,
         },
         "moonshotai/kimi-k2.5": {
             id: "moonshotai/kimi-k2.5",
@@ -13660,9 +14141,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.71,
-                output: 3.5,
-                cacheRead: 0.15,
+                input: 0.7062,
+                output: 3.21,
+                cacheRead: 0.18,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -13745,9 +14226,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.049999999999999996,
-                output: 0.19999999999999998,
-                cacheRead: 0.03,
+                input: 0.06,
+                output: 0.24,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -13779,13 +14260,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.08499999999999999,
-                output: 0.39999999999999997,
+                input: 0.08,
+                output: 0.44999999999999996,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 235929,
         },
         "nvidia/nemotron-3-super-120b-a12b:free": {
             id: "nvidia/nemotron-3-super-120b-a12b:free",
@@ -13974,23 +14455,6 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 4096,
         },
-        "openai/gpt-4-turbo-preview": {
-            id: "openai/gpt-4-turbo-preview",
-            name: "OpenAI: GPT-4 Turbo Preview",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 10,
-                output: 30,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 4096,
-        },
         "openai/gpt-4-turbo:batch": {
             id: "openai/gpt-4-turbo:batch",
             name: "OpenAI: GPT-4 Turbo (batch)",
@@ -15582,13 +16046,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.22749999999999998,
-                output: 0.9099999999999999,
+                input: 0.12,
+                output: 0.24,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 8192,
+            maxTokens: 16384,
         },
         "qwen/qwen3-235b-a22b": {
             id: "qwen/qwen3-235b-a22b",
@@ -15616,13 +16080,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.22,
-                output: 0.88,
-                cacheRead: 0,
+                input: 0.0875,
+                output: 0.35,
+                cacheRead: 0.0175,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 235929,
         },
         "qwen/qwen3-235b-a22b-thinking-2507": {
             id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -15667,13 +16131,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09,
-                output: 0.3,
+                input: 0.04815,
+                output: 0.19305,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 235929,
+            maxTokens: 32000,
         },
         "qwen/qwen3-30b-a3b-thinking-2507": {
             id: "qwen/qwen3-30b-a3b-thinking-2507",
@@ -15877,7 +16341,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 235929,
+            maxTokens: 32768,
         },
         "qwen/qwen3-vl-235b-a22b-instruct": {
             id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -15922,13 +16386,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.15,
-                output: 0.6,
+                input: 0.13,
+                output: 0.52,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 32768,
         },
         "qwen/qwen3-vl-30b-a3b-thinking": {
             id: "qwen/qwen3-vl-30b-a3b-thinking",
@@ -16041,13 +16505,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.3125,
-                output: 1.25,
-                cacheRead: 0.15625,
+                input: 0.1625,
+                output: 1.3,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 65536,
         },
         "qwen/qwen3.5-397b-a17b": {
             id: "qwen/qwen3.5-397b-a17b",
@@ -16330,9 +16794,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.42,
-                output: 3,
-                cacheRead: 0.08499999999999999,
+                input: 0.21400000000000002,
+                output: 2.5500000000000003,
+                cacheRead: 0.15,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -16406,6 +16870,23 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 128000,
         },
+        "sakana/fugu-max": {
+            id: "sakana/fugu-max",
+            name: "Sakana: Fugu Max",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 6,
+                cacheRead: 0.25,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "sakana/fugu-ultra": {
             id: "sakana/fugu-ultra",
             name: "Sakana: Fugu Ultra",
@@ -16423,6 +16904,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "sakana/fugu-ultra-v2": {
+            id: "sakana/fugu-ultra-v2",
+            name: "Sakana: Fugu Ultra v2",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 30,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "sakana/sakana-namazu": {
             id: "sakana/sakana-namazu",
             name: "Sakana: Sakana Namazu",
@@ -16457,6 +16955,23 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 16384,
         },
+        "stealth/union-alpha": {
+            id: "stealth/union-alpha",
+            name: "Union Alpha",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 131072,
+        },
         "stepfun/step-3.5-flash": {
             id: "stepfun/step-3.5-flash",
             name: "StepFun: Step 3.5 Flash",
@@ -16542,23 +17057,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 64000,
         },
-        "thedrummer/unslopnemo-12b": {
-            id: "thedrummer/unslopnemo-12b",
-            name: "TheDrummer: UnslopNemo 12B",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.39999999999999997,
-                output: 0.39999999999999997,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1024000,
-            maxTokens: 819200,
-        },
         "thinkingmachines/inkling": {
             id: "thinkingmachines/inkling",
             name: "Thinking Machines: Inkling",
@@ -16574,7 +17072,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 32768,
+            maxTokens: 471859,
         },
         "thinkingmachines/inkling-small": {
             id: "thinkingmachines/inkling-small",
@@ -16593,23 +17091,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 262144,
         },
-        "thinkingmachines/inkling-small:batch": {
-            id: "thinkingmachines/inkling-small:batch",
-            name: "Thinking Machines: Inkling Small (batch)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.5,
-                output: 1.2,
-                cacheRead: 0.09999999999999999,
-                cacheWrite: 0,
-            },
-            contextWindow: 524288,
-            maxTokens: 471859,
-        },
         "thinkingmachines/inkling-small:free": {
             id: "thinkingmachines/inkling-small:free",
             name: "Thinking Machines: Inkling Small (free)",
@@ -16687,9 +17168,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.03,
-                output: 0.12,
-                cacheRead: 0.006,
+                input: 0.09,
+                output: 0.36,
+                cacheRead: 0.018,
                 cacheWrite: 0,
             },
             contextWindow: 524288,
@@ -16947,7 +17428,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 202752,
+            contextWindow: 200000,
             maxTokens: 117964,
         },
         "z-ai/glm-5": {
@@ -17010,9 +17491,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.966,
-                output: 3.036,
-                cacheRead: 0.1932,
+                input: 1.4,
+                output: 4.4,
+                cacheRead: 0.14,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -17050,7 +17531,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
-            maxTokens: 943718,
+            maxTokens: 943717,
         },
         "z-ai/glm-5.3-flash": {
             id: "z-ai/glm-5.3-flash",
@@ -17061,9 +17542,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.075,
-                output: 0.25,
-                cacheRead: 0.015,
+                input: 0.09,
+                output: 0.3,
+                cacheRead: 0.018,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
@@ -17139,7 +17620,7 @@ export const MODELS = {
         },
         "~anthropic/claude-haiku-latest": {
             id: "~anthropic/claude-haiku-latest",
-            name: "Anthropic Claude Haiku Latest",
+            name: "Anthropic: Claude Haiku Latest",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
@@ -17173,7 +17654,7 @@ export const MODELS = {
         },
         "~anthropic/claude-sonnet-latest": {
             id: "~anthropic/claude-sonnet-latest",
-            name: "Anthropic Claude Sonnet Latest",
+            name: "Anthropic: Claude Sonnet Latest",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
@@ -17188,9 +17669,43 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "~deepseek/deepseek-flash-latest": {
+            id: "~deepseek/deepseek-flash-latest",
+            name: "DeepSeek: DeepSeek Flash Latest",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0.015,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 393216,
+        },
+        "~deepseek/deepseek-pro-latest": {
+            id: "~deepseek/deepseek-pro-latest",
+            name: "DeepSeek: DeepSeek Pro Latest",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.57948,
+                output: 1.73844,
+                cacheRead: 0.018438,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 393216,
+        },
         "~deepseek/deepseek-v4-flash-latest": {
             id: "~deepseek/deepseek-v4-flash-latest",
-            name: "DeepSeek V4 Flash Latest",
+            name: "DeepSeek: DeepSeek V4 Flash Latest",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
@@ -17199,9 +17714,9 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 0.049999999999999996,
-                output: 0.16,
-                cacheRead: 0.013000000000000001,
+                input: 0.03,
+                output: 0.13,
+                cacheRead: 0.01,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
@@ -17209,7 +17724,7 @@ export const MODELS = {
         },
         "~google/gemini-flash-latest": {
             id: "~google/gemini-flash-latest",
-            name: "Google Gemini Flash Latest",
+            name: "Google: Gemini Flash Latest",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
@@ -17226,7 +17741,7 @@ export const MODELS = {
         },
         "~google/gemini-pro-latest": {
             id: "~google/gemini-pro-latest",
-            name: "Google Gemini Pro Latest",
+            name: "Google: Gemini Pro Latest",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
@@ -17243,41 +17758,58 @@ export const MODELS = {
         },
         "~moonshotai/kimi-latest": {
             id: "~moonshotai/kimi-latest",
-            name: "MoonshotAI Kimi Latest",
+            name: "MoonshotAI: Kimi Latest",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2.4,
-                output: 12,
-                cacheRead: 0.24,
+                input: 2.0999999999999996,
+                output: 10.950000000000001,
+                cacheRead: 0.22999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
             maxTokens: 943718,
         },
-        "~openai/gpt-latest": {
-            id: "~openai/gpt-latest",
-            name: "OpenAI GPT Latest",
+        "~openai/gpt-astra-latest": {
+            id: "~openai/gpt-astra-latest",
+            name: "OpenAI: GPT Astra Latest",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 0.19999999999999998,
-                cacheWrite: 2.5,
+                input: 10,
+                output: 50,
+                cacheRead: 1,
+                cacheWrite: 12.5,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
+        "~openai/gpt-luna-latest": {
+            id: "~openai/gpt-luna-latest",
+            name: "OpenAI: GPT Luna Latest",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.19999999999999998,
+                output: 1.2,
+                cacheRead: 0.02,
+                cacheWrite: 0.25,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
         },
         "~openai/gpt-mini-latest": {
             id: "~openai/gpt-mini-latest",
-            name: "OpenAI GPT Mini Latest",
+            name: "OpenAI: GPT Mini Latest",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
@@ -17292,6 +17824,40 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
+        "~openai/gpt-sol-latest": {
+            id: "~openai/gpt-sol-latest",
+            name: "OpenAI: GPT Sol Latest",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 10,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 2.5,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
+        "~openai/gpt-terra-latest": {
+            id: "~openai/gpt-terra-latest",
+            name: "OpenAI: GPT Terra Latest",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 12,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 2.5,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
         "~x-ai/grok-latest": {
             id: "~x-ai/grok-latest",
             name: "xAI: Grok Latest",
@@ -17335,13 +17901,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.092,
-                output: 3.432,
-                cacheRead: 0.20279999999999998,
+                input: 0.8775,
+                output: 2.9699999999999998,
+                cacheRead: 0.1755,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
-            maxTokens: 131072,
+            maxTokens: 235929,
         },
     },
     "together": {
@@ -17514,6 +18080,25 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 384000,
         },
+        "deepseek-ai/DeepSeek-V4.1-Flash": {
+            id: "deepseek-ai/DeepSeek-V4.1-Flash",
+            name: "DeepSeek V4.1 Flash",
+            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: 0.3,
+                output: 1.2,
+                cacheRead: 0.006,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 384000,
+        },
         "google/gemma-4-31B-it": {
             id: "google/gemma-4-31B-it",
             name: "Gemma 4 31B Instruct",
@@ -17822,7 +18407,7 @@ export const MODELS = {
             cost: {
                 input: 1.3,
                 output: 7.8,
-                cacheRead: 0.26,
+                cacheRead: 0.13,
                 cacheWrite: 1.625,
             },
             contextWindow: 240000,
@@ -17978,8 +18563,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 32768,
+            contextWindow: 262114,
+            maxTokens: 262114,
         },
         "alibaba/qwen3-next-80b-a3b-thinking": {
             id: "alibaba/qwen3-next-80b-a3b-thinking",
@@ -17994,9 +18579,9 @@ export const MODELS = {
                 output: 1.2,
                 cacheRead: 0,
                 cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 32768,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
         },
         "alibaba/qwen3-vl-235b-a22b-instruct": {
             id: "alibaba/qwen3-vl-235b-a22b-instruct",
@@ -18060,7 +18645,7 @@ export const MODELS = {
             cost: {
                 input: 0.09999999999999999,
                 output: 0.39999999999999997,
-                cacheRead: 0.001,
+                cacheRead: 0.01,
                 cacheWrite: 0.125,
             },
             contextWindow: 1000000,
@@ -18076,7 +18661,7 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.39999999999999997,
-                output: 2.4,
+                output: 2.5,
                 cacheRead: 0.04,
                 cacheWrite: 0.5,
             },
@@ -18111,7 +18696,7 @@ export const MODELS = {
             cost: {
                 input: 0.5,
                 output: 3,
-                cacheRead: 0.09999999999999999,
+                cacheRead: 0.049999999999999996,
                 cacheWrite: 0.625,
             },
             contextWindow: 1000000,
@@ -18211,7 +18796,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.16,
+                input: 0.15,
                 output: 0.47,
                 cacheRead: 0.016,
                 cacheWrite: 0.19999999999999998,
@@ -18219,23 +18804,6 @@ export const MODELS = {
             contextWindow: 991000,
             maxTokens: 128000,
         },
-        "alibaba/qwen3.8-flash-next": {
-            id: "alibaba/qwen3.8-flash-next",
-            name: "Qwen 3.8 Flash Next",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.12,
-                output: 0.39999999999999997,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 1048576,
-        },
         "alibaba/qwen3.8-max": {
             id: "alibaba/qwen3.8-max",
             name: "Qwen 3.8 Max",
@@ -18248,9 +18816,9 @@ export const MODELS = {
                 input: 2,
                 output: 6,
                 cacheRead: 0.25,
-                cacheWrite: 2.5,
+                cacheWrite: 0,
             },
-            contextWindow: 1000000,
+            contextWindow: 262144,
             maxTokens: 128000,
         },
         "alibaba/qwen3.8-max-0902": {
@@ -18668,6 +19236,23 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 64000,
         },
+        "bytedance/seed-2.1-turbo": {
+            id: "bytedance/seed-2.1-turbo",
+            name: "Seed 2.1 Turbo",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.5,
+                output: 2.5,
+                cacheRead: 0.09999999999999999,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
         "cohere/command-a": {
             id: "cohere/command-a",
             name: "Command A",
@@ -18864,13 +19449,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0.003,
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 384000,
+            contextWindow: 1048576,
+            maxTokens: 32768,
         },
         "google/gemini-2.5-flash": {
             id: "google/gemini-2.5-flash",
@@ -19153,9 +19738,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.06,
-                output: 0.18,
-                cacheRead: 0.012,
+                input: 0.020999999999999998,
+                output: 0.063,
+                cacheRead: 0.004200000000000001,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
@@ -19229,90 +19814,56 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 32000,
         },
-        "interfaze/interfaze-beta": {
-            id: "interfaze/interfaze-beta",
-            name: "Interfaze Beta",
+        "inclusionai/ling-3.0-flash-vl": {
+            id: "inclusionai/ling-3.0-flash-vl",
+            name: "Ling 3.0 Flash VL",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1.5,
-                output: 3.5,
+                input: 0,
+                output: 0,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
+            contextWindow: 256000,
             maxTokens: 32000,
         },
-        "kwaipilot/kat-coder-air-v2.5": {
-            id: "kwaipilot/kat-coder-air-v2.5",
-            name: "Kat Coder Air V2.5",
+        "inclusionai/ling-3.0-flash-vl-free": {
+            id: "inclusionai/ling-3.0-flash-vl-free",
+            name: "Ling 3.0 Flash VL (Free)",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0.03,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 80000,
-        },
-        "kwaipilot/kat-coder-pro-v1": {
-            id: "kwaipilot/kat-coder-pro-v1",
-            name: "KAT-Coder-Pro V1",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 1.2,
-                cacheRead: 0.06,
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
             maxTokens: 32000,
         },
-        "kwaipilot/kat-coder-pro-v2": {
-            id: "kwaipilot/kat-coder-pro-v2",
-            name: "Kat Coder Pro V2",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 1.2,
-                cacheRead: 0.06,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 256000,
-        },
-        "kwaipilot/kat-coder-pro-v2.5": {
-            id: "kwaipilot/kat-coder-pro-v2.5",
-            name: "Kat Coder Pro V2.5",
+        "interfaze/interfaze-beta": {
+            id: "interfaze/interfaze-beta",
+            name: "Interfaze Beta",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.74,
-                output: 2.96,
-                cacheRead: 0.15,
+                input: 1.5,
+                output: 3.5,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 80000,
+            contextWindow: 1000000,
+            maxTokens: 32000,
         },
         "meta/llama-3.1-70b": {
             id: "meta/llama-3.1-70b",
@@ -19648,46 +20199,12 @@ export const MODELS = {
             cost: {
                 input: 0.3,
                 output: 0.8999999999999999,
-                cacheRead: 0,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
             maxTokens: 4000,
         },
-        "mistral/devstral-2": {
-            id: "mistral/devstral-2",
-            name: "Devstral 2",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.39999999999999997,
-                output: 2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 256000,
-        },
-        "mistral/devstral-small-2": {
-            id: "mistral/devstral-small-2",
-            name: "Devstral Small 2",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.09999999999999999,
-                output: 0.3,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 256000,
-        },
         "mistral/ministral-14b": {
             id: "mistral/ministral-14b",
             name: "Ministral 14B",
@@ -19699,10 +20216,10 @@ export const MODELS = {
             cost: {
                 input: 0.19999999999999998,
                 output: 0.19999999999999998,
-                cacheRead: 0,
+                cacheRead: 0.02,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
+            contextWindow: 262144,
             maxTokens: 256000,
         },
         "mistral/ministral-3b": {
@@ -19716,10 +20233,10 @@ export const MODELS = {
             cost: {
                 input: 0.09999999999999999,
                 output: 0.09999999999999999,
-                cacheRead: 0,
+                cacheRead: 0.01,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 131072,
             maxTokens: 4000,
         },
         "mistral/ministral-8b": {
@@ -19733,10 +20250,10 @@ export const MODELS = {
             cost: {
                 input: 0.15,
                 output: 0.15,
-                cacheRead: 0,
+                cacheRead: 0.015,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 262144,
             maxTokens: 4000,
         },
         "mistral/mistral-large-3": {
@@ -19750,29 +20267,12 @@ export const MODELS = {
             cost: {
                 input: 0.5,
                 output: 1.5,
-                cacheRead: 0,
+                cacheRead: 0.049999999999999996,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
+            contextWindow: 262144,
             maxTokens: 256000,
         },
-        "mistral/mistral-medium": {
-            id: "mistral/mistral-medium",
-            name: "Mistral Medium 3.1",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.39999999999999997,
-                output: 2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 64000,
-        },
         "mistral/mistral-medium-3.5": {
             id: "mistral/mistral-medium-3.5",
             name: "Mistral Medium Latest",
@@ -19784,10 +20284,10 @@ export const MODELS = {
             cost: {
                 input: 1.5,
                 output: 7.5,
-                cacheRead: 0,
+                cacheRead: 0.15,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
+            contextWindow: 262144,
             maxTokens: 256000,
         },
         "mistral/mistral-nemo": {
@@ -19797,15 +20297,15 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: false,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
-                input: 0.15,
-                output: 0.15,
+                input: 0.04,
+                output: 0.16999999999999998,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 128000,
+            contextWindow: 60288,
+            maxTokens: 16000,
         },
         "mistral/mistral-small": {
             id: "mistral/mistral-small",
@@ -19815,30 +20315,13 @@ export const MODELS = {
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: false,
             input: ["text", "image"],
-            cost: {
-                input: 0.09999999999999999,
-                output: 0.3,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 32000,
-            maxTokens: 4000,
-        },
-        "mistral/pixtral-12b": {
-            id: "mistral/pixtral-12b",
-            name: "Pixtral 12B 2409",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text", "image"],
             cost: {
                 input: 0.15,
-                output: 0.15,
-                cacheRead: 0,
+                output: 0.6,
+                cacheRead: 0.015,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 262144,
             maxTokens: 4000,
         },
         "moonshotai/kimi-k2": {
@@ -19886,11 +20369,11 @@ export const MODELS = {
             cost: {
                 input: 0.6,
                 output: 3,
-                cacheRead: 0.09999999999999999,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262114,
-            maxTokens: 262114,
+            contextWindow: 256000,
+            maxTokens: 256000,
         },
         "moonshotai/kimi-k2.6": {
             id: "moonshotai/kimi-k2.6",
@@ -19987,8 +20470,8 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.049999999999999996,
-                output: 0.24,
-                cacheRead: 0,
+                output: 0.19999999999999998,
+                cacheRead: 0.024999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -20927,8 +21410,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.049999999999999996,
-                output: 0.19999999999999998,
+                input: 0.03,
+                output: 0.14,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -21122,6 +21605,23 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 32768,
         },
+        "sakana/fugu-max": {
+            id: "sakana/fugu-max",
+            name: "Fugu Max",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 6,
+                cacheRead: 0.25,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 1000000,
+        },
         "sakana/fugu-ultra": {
             id: "sakana/fugu-ultra",
             name: "Fugu Ultra",
@@ -21139,6 +21639,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 1000000,
         },
+        "sakana/fugu-ultra-v2": {
+            id: "sakana/fugu-ultra-v2",
+            name: "Fugu Ultra v2",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 30,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 1000000,
+        },
         "sakana/namazu": {
             id: "sakana/namazu",
             name: "Sakana Namazu",