@fleetagent/pi-ai 0.2.3 → 0.2.4

package/dist/models.generated.js

@@ -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",
@@ -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 +322,10 @@ export const MODELS = {
                 input: 0.84,
                 output: 3.36,
                 cacheRead: 0.21,
-                cacheWrite: 0,
+                cacheWrite: 0.84,
             },
             contextWindow: 300000,
-            maxTokens: 8192,
+            maxTokens: 10000,
         },
         "au.anthropic.claude-haiku-4-5-20251001-v1:0": {
             id: "au.anthropic.claude-haiku-4-5-20251001-v1:0",
@@ -477,27 +477,10 @@ 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 +501,7 @@ 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 +528,10 @@ 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 +545,10 @@ 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 +562,10 @@ 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 +579,10 @@ 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",
@@ -802,10 +785,10 @@ 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",
@@ -1085,30 +1068,47 @@ 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 +1116,44 @@ 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 +1167,10 @@ 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",
@@ -1322,7 +1358,7 @@ 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 +1374,12 @@ 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 +1396,7 @@ 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 +1413,7 @@ 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 +1469,7 @@ 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 +1503,7 @@ 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 +1561,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 32768,
             maxTokens: 4096,
         },
         "mistral.voxtral-small-24b-2507": {
@@ -1537,12 +1573,12 @@ 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 +1613,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262143,
-            maxTokens: 16000,
+            maxTokens: 16384,
         },
         "nvidia.nemotron-nano-12b-v2": {
             id: "nvidia.nemotron-nano-12b-v2",
@@ -1594,7 +1630,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 4096,
+            maxTokens: 8192,
         },
         "nvidia.nemotron-nano-3-30b": {
             id: "nvidia.nemotron-nano-3-30b",
@@ -1610,8 +1646,8 @@ 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 +1663,8 @@ 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 +1865,7 @@ 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 +1882,7 @@ 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 +1895,7 @@ 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 +1912,7 @@ 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 +1924,12 @@ 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 +1946,14 @@ 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 +1967,85 @@ 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 +2058,10 @@ 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 +2075,10 @@ 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 +2092,27 @@ 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 +2126,10 @@ 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",
@@ -2250,23 +2337,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "us.deepseek.r1-v1:0": {
-            id: "us.deepseek.r1-v1:0",
-            name: "DeepSeek-R1 (US)",
-            api: "bedrock-converse-stream",
-            provider: "amazon-bedrock",
-            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 1.35,
-                output: 5.4,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 32768,
-        },
         "us.meta.llama3-1-70b-instruct-v1:0": {
             id: "us.meta.llama3-1-70b-instruct-v1:0",
             name: "Llama 3.1 70B Instruct (US)",
@@ -2333,7 +2403,7 @@ 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 +2419,8 @@ 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 +2679,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 202752,
-            maxTokens: 101376,
+            maxTokens: 131072,
         },
     },
     "anthropic": {
@@ -4643,6 +4713,24 @@ 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",
@@ -4805,6 +4893,24 @@ export const MODELS = {
             contextWindow: 512000,
             maxTokens: 512000,
         },
+        "accounts/fireworks/models/mistral-large-3-fp8": {
+            id: "accounts/fireworks/models/mistral-large-3-fp8",
+            name: "Mistral Large 3 675B Instruct 2512",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
         "accounts/fireworks/models/muse-glimmer-30b": {
             id: "accounts/fireworks/models/muse-glimmer-30b",
             name: "Muse Glimmer 30B",
@@ -6999,6 +7105,78 @@ 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",
@@ -10522,23 +10700,6 @@ export const MODELS = {
         },
     },
     "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",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0.003,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 384000,
-        },
         "deepseek-v4-flash": {
             id: "deepseek-v4-flash",
             name: "DeepSeek V4 Flash",
@@ -10596,6 +10757,25 @@ 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",
@@ -11805,9 +11985,9 @@ 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 +12106,9 @@ 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: 0.06678,
+                output: 0.13356,
+                cacheRead: 0.013356,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -11945,9 +12125,9 @@ 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: 0.04,
+                output: 0.08,
+                cacheRead: 0.008,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
@@ -12021,9 +12201,9 @@ 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: 0.788916,
+                output: 1.577832,
+                cacheRead: 0.065743,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -12040,13 +12220,13 @@ 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: 0.57816,
+                output: 1.73448,
+                cacheRead: 0.018396000000000003,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 384000,
+            maxTokens: 393216,
         },
         "deepseek/deepseek-v4-pro-0813:batch": {
             id: "deepseek/deepseek-v4-pro-0813:batch",
@@ -12057,15 +12237,34 @@ export const MODELS = {
             compat: { "requiresReasoningContentOnAssistantMessages": true },
             reasoning: true,
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
-            input: ["text"],
+            input: ["text"],
+            cost: {
+                input: 0.66,
+                output: 1.9800000000000002,
+                cacheRead: 0.022,
+                cacheWrite: 0,
+            },
+            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: 0.66,
-                output: 1.9800000000000002,
-                cacheRead: 0.022,
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0.003,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 943718,
+            maxTokens: 384000,
         },
         "dots-studio/dots-3-note-preview:free": {
             id: "dots-studio/dots-3-note-preview:free",
@@ -12586,13 +12785,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.07,
-                output: 0.33999999999999997,
+                input: 0.041999999999999996,
+                output: 0.22,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 32768,
         },
         "google/gemma-4-26b-a4b-it:free": {
             id: "google/gemma-4-26b-a4b-it:free",
@@ -12783,6 +12982,40 @@ 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",
@@ -12860,13 +13093,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.39999999999999997,
-                output: 0.39999999999999997,
+                input: 0.72,
+                output: 0.72,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 16384,
+            maxTokens: 8192,
         },
         "meta-llama/llama-3.1-8b-instruct": {
             id: "meta-llama/llama-3.1-8b-instruct",
@@ -13115,13 +13348,13 @@ 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",
@@ -13528,7 +13761,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
+            contextWindow: 256000,
             maxTokens: 16384,
         },
         "mistralai/mixtral-8x22b-instruct": {
@@ -13610,11 +13843,11 @@ export const MODELS = {
             cost: {
                 input: 0.6,
                 output: 2.5,
-                cacheRead: 0.15,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 100352,
+            maxTokens: 235929,
         },
         "moonshotai/kimi-k2.5": {
             id: "moonshotai/kimi-k2.5",
@@ -13677,9 +13910,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
+                input: 2.30272875,
+                output: 11.550195,
+                cacheRead: 0.26316900000000004,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -15616,13 +15849,13 @@ 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",
@@ -16330,9 +16563,9 @@ 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 +16639,23 @@ 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 +16673,23 @@ 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",
@@ -16574,7 +16841,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 32768,
+            maxTokens: 471859,
         },
         "thinkingmachines/inkling-small": {
             id: "thinkingmachines/inkling-small",
@@ -16687,9 +16954,9 @@ 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 +17214,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 202752,
+            contextWindow: 200000,
             maxTokens: 117964,
         },
         "z-ai/glm-5": {
@@ -17010,13 +17277,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.966,
-                output: 3.036,
-                cacheRead: 0.1932,
+                input: 0.6,
+                output: 2,
+                cacheRead: 0.15,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 131072,
+            maxTokens: 182476,
         },
         "z-ai/glm-5.2:batch": {
             id: "z-ai/glm-5.2:batch",
@@ -17139,7 +17406,7 @@ 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 +17440,7 @@ 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",
@@ -17190,7 +17457,7 @@ export const MODELS = {
         },
         "~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 +17466,9 @@ 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: 0.07,
+                cacheRead: 0.003,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
@@ -17209,7 +17476,7 @@ 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 +17493,7 @@ 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 +17510,58 @@ 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: 2.125,
+                output: 11.9,
+                cacheRead: 0.2465,
                 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 +17576,40 @@ 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 +17653,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.092,
-                output: 3.432,
-                cacheRead: 0.20279999999999998,
+                input: 0.8727,
+                output: 3.36,
+                cacheRead: 0.16390000000000002,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
-            maxTokens: 131072,
+            maxTokens: 943718,
         },
     },
     "together": {
@@ -18219,23 +18537,6 @@ 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",
@@ -18864,13 +19165,13 @@ 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",
@@ -19229,6 +19530,40 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 32000,
         },
+        "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: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 32000,
+        },
+        "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,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 32000,
+        },
         "interfaze/interfaze-beta": {
             id: "interfaze/interfaze-beta",
             name: "Interfaze Beta",
@@ -21122,6 +21457,23 @@ 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 +21491,23 @@ 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",