@elyracode/ai 0.9.15 → 0.9.16

package/dist/models.generated.js

@@ -1318,6 +1318,57 @@ export const MODELS = {
             contextWindow: 272000,
             maxTokens: 128000,
         },
+        "openai.gpt-5.6-luna": {
+            id: "openai.gpt-5.6-luna",
+            name: "GPT-5.6 Luna",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1,
+                output: 6,
+                cacheRead: 0.1,
+                cacheWrite: 1.25,
+            },
+            contextWindow: 272000,
+            maxTokens: 128000,
+        },
+        "openai.gpt-5.6-sol": {
+            id: "openai.gpt-5.6-sol",
+            name: "GPT-5.6 Sol",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 30,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 272000,
+            maxTokens: 128000,
+        },
+        "openai.gpt-5.6-terra": {
+            id: "openai.gpt-5.6-terra",
+            name: "GPT-5.6 Terra",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2.5,
+                output: 15,
+                cacheRead: 0.25,
+                cacheWrite: 3.125,
+            },
+            contextWindow: 272000,
+            maxTokens: 128000,
+        },
         "openai.gpt-oss-120b": {
             id: "openai.gpt-oss-120b",
             name: "gpt-oss-120b",
@@ -2942,7 +2993,7 @@ export const MODELS = {
             cost: {
                 input: 2.25,
                 output: 2.75,
-                cacheRead: 0,
+                cacheRead: 2.25,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -3403,6 +3454,60 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "gpt-5.6-luna": {
+            id: "gpt-5.6-luna",
+            name: "GPT-5.6 Luna",
+            api: "openai-responses",
+            provider: "cloudflare-ai-gateway",
+            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
+            reasoning: true,
+            thinkingLevelMap: { "off": null },
+            input: ["text", "image"],
+            cost: {
+                input: 1,
+                output: 6,
+                cacheRead: 0.1,
+                cacheWrite: 0,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
+        "gpt-5.6-sol": {
+            id: "gpt-5.6-sol",
+            name: "GPT-5.6 Sol",
+            api: "openai-responses",
+            provider: "cloudflare-ai-gateway",
+            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
+            reasoning: true,
+            thinkingLevelMap: { "off": null },
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 30,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
+        "gpt-5.6-terra": {
+            id: "gpt-5.6-terra",
+            name: "GPT-5.6 Terra",
+            api: "openai-responses",
+            provider: "cloudflare-ai-gateway",
+            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
+            reasoning: true,
+            thinkingLevelMap: { "off": null },
+            input: ["text", "image"],
+            cost: {
+                input: 2.5,
+                output: 15,
+                cacheRead: 0.25,
+                cacheWrite: 0,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
         "o1": {
             id: "o1",
             name: "o1",
@@ -3560,6 +3665,24 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 131072,
         },
+        "workers-ai/@cf/zai-org/glm-5.2": {
+            id: "workers-ai/@cf/zai-org/glm-5.2",
+            name: "Glm 5.2",
+            api: "openai-completions",
+            provider: "cloudflare-ai-gateway",
+            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/compat",
+            compat: { "sendSessionAffinityHeaders": true },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.4,
+                output: 4.4,
+                cacheRead: 0.26,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
     },
     "cloudflare-workers-ai": {
         "@cf/google/gemma-4-26b-a4b-it": {
@@ -9876,13 +9999,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.24,
-                output: 0.8999999999999999,
+                input: 0.27,
+                output: 1.12,
                 cacheRead: 0.135,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 16384,
+            maxTokens: 65536,
         },
         "deepseek/deepseek-chat-v3.1": {
             id: "deepseek/deepseek-chat-v3.1",
@@ -9893,8 +10016,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.21,
-                output: 0.7899999999999999,
+                input: 0.25,
+                output: 0.95,
                 cacheRead: 0.13,
                 cacheWrite: 0,
             },
@@ -9945,11 +10068,11 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.27,
-                output: 0.95,
-                cacheRead: 0.13,
+                output: 1,
+                cacheRead: 0.135,
                 cacheWrite: 0,
             },
-            contextWindow: 163840,
+            contextWindow: 131072,
             maxTokens: 32768,
         },
         "deepseek/deepseek-v3.2": {
@@ -9961,13 +10084,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.2145,
-                output: 0.32175,
-                cacheRead: 0.02145,
+                input: 0.26899999999999996,
+                output: 0.39999999999999997,
+                cacheRead: 0.13449999999999998,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 64000,
+            contextWindow: 163840,
+            maxTokens: 65536,
         },
         "deepseek/deepseek-v3.2-exp": {
             id: "deepseek/deepseek-v3.2-exp",
@@ -9997,13 +10120,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
             cost: {
-                input: 0.077,
-                output: 0.154,
-                cacheRead: 0.015399999999999999,
+                input: 0.098,
+                output: 0.196,
+                cacheRead: 0.02,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 384000,
+            maxTokens: 4096,
         },
         "deepseek/deepseek-v4-pro": {
             id: "deepseek/deepseek-v4-pro",
@@ -10255,12 +10378,12 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.08,
-                output: 0.16,
-                cacheRead: 0,
+                output: 0.44999999999999996,
+                cacheRead: 0.04,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 16384,
+            maxTokens: 131072,
         },
         "google/gemma-4-26b-a4b-it": {
             id: "google/gemma-4-26b-a4b-it",
@@ -10271,13 +10394,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.06,
-                output: 0.33,
+                input: 0.09999999999999999,
+                output: 0.3,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 256000,
         },
         "google/gemma-4-26b-a4b-it:free": {
             id: "google/gemma-4-26b-a4b-it:free",
@@ -10306,12 +10429,12 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.12,
-                output: 0.35,
-                cacheRead: 0.09,
+                output: 0.37,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 16384,
         },
         "google/gemma-4-31b-it:free": {
             id: "google/gemma-4-31b-it:free",
@@ -10328,7 +10451,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 8192,
+            maxTokens: 32768,
         },
         "ibm-granite/granite-4.1-8b": {
             id: "ibm-granite/granite-4.1-8b",
@@ -10415,6 +10538,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
+        "kwaipilot/kat-coder-air-v2.5": {
+            id: "kwaipilot/kat-coder-air-v2.5",
+            name: "Kwaipilot: KAT-Coder-Air V2.5",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0.03,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 80000,
+        },
         "kwaipilot/kat-coder-pro-v2": {
             id: "kwaipilot/kat-coder-pro-v2",
             name: "Kwaipilot: KAT-Coder-Pro V2",
@@ -10432,22 +10572,22 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 80000,
         },
-        "liquid/lfm-2.5-1.2b-thinking:free": {
-            id: "liquid/lfm-2.5-1.2b-thinking:free",
-            name: "LiquidAI: LFM2.5-1.2B-Thinking (free)",
+        "kwaipilot/kat-coder-pro-v2.5": {
+            id: "kwaipilot/kat-coder-pro-v2.5",
+            name: "Kwaipilot: KAT-Coder-Pro V2.5",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
+            reasoning: false,
             input: ["text"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 0.74,
+                output: 2.96,
+                cacheRead: 0.15,
                 cacheWrite: 0,
             },
-            contextWindow: 32768,
-            maxTokens: 4096,
+            contextWindow: 256000,
+            maxTokens: 80000,
         },
         "meta-llama/llama-3.1-70b-instruct": {
             id: "meta-llama/llama-3.1-70b-instruct",
@@ -10475,13 +10615,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.02,
-                output: 0.03,
-                cacheRead: 0,
+                input: 0.049999999999999996,
+                output: 0.08,
+                cacheRead: 0.024999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 16384,
+            maxTokens: 131072,
         },
         "meta-llama/llama-3.3-70b-instruct": {
             id: "meta-llama/llama-3.3-70b-instruct",
@@ -10492,13 +10632,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.32,
+                input: 0.13,
+                output: 0.39999999999999997,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 16384,
+            maxTokens: 128000,
         },
         "meta-llama/llama-3.3-70b-instruct:free": {
             id: "meta-llama/llama-3.3-70b-instruct:free",
@@ -10560,7 +10700,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.39999999999999997,
+                input: 0.55,
                 output: 2.2,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -10628,13 +10768,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.24,
-                output: 0.96,
-                cacheRead: 0,
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
-            maxTokens: 196608,
+            maxTokens: 131072,
         },
         "minimax/minimax-m3": {
             id: "minimax/minimax-m3",
@@ -10651,7 +10791,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 131072,
+            maxTokens: 512000,
         },
         "mistralai/codestral-2508": {
             id: "mistralai/codestral-2508",
@@ -10850,12 +10990,12 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.02,
-                output: 0.03,
+                output: 0.04,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "mistralai/mistral-saba": {
             id: "mistralai/mistral-saba",
@@ -10900,13 +11040,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.075,
-                output: 0.19999999999999998,
-                cacheRead: 0,
+                input: 0.09999999999999999,
+                output: 0.3,
+                cacheRead: 0.01,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 16384,
+            contextWindow: 131072,
+            maxTokens: 4096,
         },
         "mistralai/mixtral-8x22b-instruct": {
             id: "mistralai/mixtral-8x22b-instruct",
@@ -10987,11 +11127,11 @@ export const MODELS = {
             cost: {
                 input: 0.6,
                 output: 2.5,
-                cacheRead: 0.15,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 100352,
+            maxTokens: 262144,
         },
         "moonshotai/kimi-k2.5": {
             id: "moonshotai/kimi-k2.5",
@@ -11021,7 +11161,7 @@ export const MODELS = {
             cost: {
                 input: 0.66,
                 output: 3.41,
-                cacheRead: 0.15,
+                cacheRead: 0.144,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -11036,9 +11176,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.72,
-                output: 3.5,
-                cacheRead: 0.15,
+                input: 0.719,
+                output: 3.49,
+                cacheRead: 0.149,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -11155,9 +11295,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.08,
-                output: 0.44999999999999996,
-                cacheRead: 0,
+                input: 0.21,
+                output: 0.45499999999999996,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -11189,13 +11329,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.5,
-                output: 2.2,
-                cacheRead: 0.09999999999999999,
+                input: 0.6,
+                output: 3.5999999999999996,
+                cacheRead: 0.19999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
-            maxTokens: 16384,
+            maxTokens: 4096,
         },
         "nvidia/nemotron-3-ultra-550b-a55b:free": {
             id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -11331,7 +11471,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1047576,
-            maxTokens: 4096,
+            maxTokens: 32768,
         },
         "openai/gpt-4.1-mini": {
             id: "openai/gpt-4.1-mini",
@@ -11378,7 +11518,7 @@ export const MODELS = {
             cost: {
                 input: 2.5,
                 output: 10,
-                cacheRead: 0,
+                cacheRead: 1.25,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -11463,11 +11603,11 @@ export const MODELS = {
             cost: {
                 input: 0.049999999999999996,
                 output: 0.39999999999999997,
-                cacheRead: 0.01,
+                cacheRead: 0.005,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
-            maxTokens: 4096,
+            maxTokens: 128000,
         },
         "openai/gpt-5-pro": {
             id: "openai/gpt-5-pro",
@@ -11497,7 +11637,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.13,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -11514,11 +11654,11 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.13,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 32000,
+            maxTokens: 16384,
         },
         "openai/gpt-5.1-codex": {
             id: "openai/gpt-5.1-codex",
@@ -11531,7 +11671,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.13,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -11949,25 +12089,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.036,
-                output: 0.18,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 4096,
-        },
-        "openai/gpt-oss-120b:free": {
-            id: "openai/gpt-oss-120b:free",
-            name: "OpenAI: gpt-oss-120b (free)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
+                input: 0.037,
+                output: 0.16999999999999998,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -11983,13 +12106,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.029,
-                output: 0.14,
-                cacheRead: 0,
+                input: 0.03,
+                output: 0.13,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 4096,
+            maxTokens: 131072,
         },
         "openai/gpt-oss-20b:free": {
             id: "openai/gpt-oss-20b:free",
@@ -12459,13 +12582,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.04815,
-                output: 0.19305,
+                input: 0.09999999999999999,
+                output: 0.3,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 32000,
+            contextWindow: 262144,
+            maxTokens: 4096,
         },
         "qwen/qwen3-30b-a3b-thinking-2507": {
             id: "qwen/qwen3-30b-a3b-thinking-2507",
@@ -12527,9 +12650,9 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.22,
-                output: 1.7999999999999998,
-                cacheRead: 0,
+                input: 0.3,
+                output: 1,
+                cacheRead: 0.09999999999999999,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -12578,7 +12701,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.11,
+                input: 0.12,
                 output: 0.7999999999999999,
                 cacheRead: 0.07,
                 cacheWrite: 0,
@@ -12663,13 +12786,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09,
+                input: 0.09999999999999999,
                 output: 1.1,
-                cacheRead: 0,
+                cacheRead: 0.07,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 262144,
         },
         "qwen/qwen3-next-80b-a3b-instruct:free": {
             id: "qwen/qwen3-next-80b-a3b-instruct:free",
@@ -12714,13 +12837,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.19999999999999998,
-                output: 0.88,
-                cacheRead: 0.11,
+                input: 0.21,
+                output: 1.9,
+                cacheRead: 0.09999999999999999,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 16384,
+            contextWindow: 131072,
+            maxTokens: 32768,
         },
         "qwen/qwen3-vl-235b-a22b-thinking": {
             id: "qwen/qwen3-vl-235b-a22b-thinking",
@@ -12839,7 +12962,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 65536,
         },
         "qwen/qwen3.5-27b": {
             id: "qwen/qwen3.5-27b",
@@ -12869,11 +12992,11 @@ export const MODELS = {
             cost: {
                 input: 0.14,
                 output: 1,
-                cacheRead: 0.049999999999999996,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 81920,
+            maxTokens: 262144,
         },
         "qwen/qwen3.5-397b-a17b": {
             id: "qwen/qwen3.5-397b-a17b",
@@ -12884,13 +13007,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.385,
-                output: 2.4499999999999997,
-                cacheRead: 0.111,
+                input: 0.44999999999999996,
+                output: 3,
+                cacheRead: 0.22499999999999998,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 4096,
+            contextWindow: 262144,
+            maxTokens: 65536,
         },
         "qwen/qwen3.5-9b": {
             id: "qwen/qwen3.5-9b",
@@ -12969,13 +13092,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.28500000000000003,
-                output: 2.4,
-                cacheRead: 0.15,
+                input: 0.44999999999999996,
+                output: 2.7,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262140,
+            maxTokens: 65536,
         },
         "qwen/qwen3.6-35b-a3b": {
             id: "qwen/qwen3.6-35b-a3b",
@@ -13190,13 +13313,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.14,
-                output: 0.58,
-                cacheRead: 0.035,
+                input: 0.19999999999999998,
+                output: 0.7999999999999999,
+                cacheRead: 0.049999999999999996,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 131072,
         },
         "tencent/hy3:free": {
             id: "tencent/hy3:free",
@@ -13326,13 +13449,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.105,
+                input: 0.14,
                 output: 0.28,
-                cacheRead: 0.028,
+                cacheRead: 0.0028,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 4096,
+            maxTokens: 131072,
         },
         "xiaomi/mimo-v2.5-pro": {
             id: "xiaomi/mimo-v2.5-pro",
@@ -13411,13 +13534,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.43,
-                output: 1.75,
-                cacheRead: 0.08,
+                input: 0.5,
+                output: 2,
+                cacheRead: 0.09999999999999999,
                 cacheWrite: 0,
             },
-            contextWindow: 200000,
-            maxTokens: 16384,
+            contextWindow: 202752,
+            maxTokens: 131072,
         },
         "z-ai/glm-4.6v": {
             id: "z-ai/glm-4.6v",
@@ -13462,13 +13585,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.06,
+                input: 0.060500000000000005,
                 output: 0.39999999999999997,
-                cacheRead: 0.01,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 202752,
-            maxTokens: 16384,
+            contextWindow: 200000,
+            maxTokens: 131072,
         },
         "z-ai/glm-5": {
             id: "z-ai/glm-5",
@@ -13485,7 +13608,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 202752,
-            maxTokens: 4096,
+            maxTokens: 202752,
         },
         "z-ai/glm-5-turbo": {
             id: "z-ai/glm-5-turbo",
@@ -13501,7 +13624,7 @@ export const MODELS = {
                 cacheRead: 0.24,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
+            contextWindow: 202752,
             maxTokens: 131072,
         },
         "z-ai/glm-5.1": {
@@ -13530,9 +13653,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.42,
-                output: 1.32,
-                cacheRead: 0.078,
+                input: 0.8932,
+                output: 2.8072,
+                cacheRead: 0.16588,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -14648,7 +14771,7 @@ export const MODELS = {
                 cacheWrite: 18.75,
             },
             contextWindow: 200000,
-            maxTokens: 32000,
+            maxTokens: 8192,
         },
         "anthropic/claude-opus-4.1": {
             id: "anthropic/claude-opus-4.1",
@@ -14720,6 +14843,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "anthropic/claude-opus-4.7-fast": {
+            id: "anthropic/claude-opus-4.7-fast",
+            name: "Claude Opus 4.7 (Fast)",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 30,
+                output: 150,
+                cacheRead: 3,
+                cacheWrite: 37.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "anthropic/claude-opus-4.8": {
             id: "anthropic/claude-opus-4.8",
             name: "Claude Opus 4.8",
@@ -14738,6 +14879,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "anthropic/claude-opus-4.8-fast": {
+            id: "anthropic/claude-opus-4.8-fast",
+            name: "Claude Opus 4.8 (Fast)",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            thinkingLevelMap: { "minimal": "low", "low": "medium", "medium": "high", "high": "max", "xhigh": "ultracode" },
+            input: ["text", "image"],
+            cost: {
+                input: 10,
+                output: 50,
+                cacheRead: 1,
+                cacheWrite: 12.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "anthropic/claude-sonnet-4": {
             id: "anthropic/claude-sonnet-4",
             name: "Claude Sonnet 4",
@@ -14753,7 +14912,7 @@ export const MODELS = {
                 cacheWrite: 3.75,
             },
             contextWindow: 1000000,
-            maxTokens: 64000,
+            maxTokens: 8192,
         },
         "anthropic/claude-sonnet-4.5": {
             id: "anthropic/claude-sonnet-4.5",
@@ -14806,23 +14965,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "arcee-ai/trinity-large-preview": {
-            id: "arcee-ai/trinity-large-preview",
-            name: "Trinity Large Preview",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.25,
-                output: 1,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131000,
-            maxTokens: 131000,
-        },
         "arcee-ai/trinity-large-thinking": {
             id: "arcee-ai/trinity-large-thinking",
             name: "Trinity Large Thinking",
@@ -14951,12 +15093,12 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.6,
-                output: 1.7,
-                cacheRead: 0,
+                input: 0.25,
+                output: 0.95,
+                cacheRead: 0.13,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 163840,
             maxTokens: 128000,
         },
         "deepseek/deepseek-v3.1-terminus": {
@@ -15350,40 +15492,6 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 80000,
         },
-        "meituan/longcat-flash-chat": {
-            id: "meituan/longcat-flash-chat",
-            name: "LongCat Flash Chat",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 100000,
-        },
-        "meituan/longcat-flash-thinking-2601": {
-            id: "meituan/longcat-flash-thinking-2601",
-            name: "LongCat Flash Thinking 2601",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 32768,
-            maxTokens: 32768,
-        },
         "meta/llama-3.1-70b": {
             id: "meta/llama-3.1-70b",
             name: "Llama 3.1 70B Instruct",
@@ -15690,23 +15798,6 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 256000,
         },
-        "mistral/devstral-small": {
-            id: "mistral/devstral-small",
-            name: "Devstral Small 1.1",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.09999999999999999,
-                output: 0.3,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 64000,
-        },
         "mistral/devstral-small-2": {
             id: "mistral/devstral-small-2",
             name: "Devstral Small 2",
@@ -15911,23 +16002,6 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 4000,
         },
-        "mistral/pixtral-large": {
-            id: "mistral/pixtral-large",
-            name: "Pixtral Large",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 6,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 4000,
-        },
         "moonshotai/kimi-k2": {
             id: "moonshotai/kimi-k2",
             name: "Kimi K2 Instruct",