@caupulican/pi-ai 0.81.38 → 0.81.39

package/dist/models.generated.js

@@ -4806,7 +4806,7 @@ export const MODELS = {
                 input: 1,
                 output: 6,
                 cacheRead: 0.1,
-                cacheWrite: 0,
+                cacheWrite: 1.25,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -4825,7 +4825,7 @@ export const MODELS = {
                 input: 5,
                 output: 30,
                 cacheRead: 0.5,
-                cacheWrite: 0,
+                cacheWrite: 6.25,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -4844,7 +4844,7 @@ export const MODELS = {
                 input: 2.5,
                 output: 15,
                 cacheRead: 0.25,
-                cacheWrite: 0,
+                cacheWrite: 3.125,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -6405,9 +6405,9 @@ export const MODELS = {
         },
     },
     "kimi-coding": {
-        "k2p7": {
-            id: "k2p7",
-            name: "Kimi K2.7 Code",
+        "k3": {
+            id: "k3",
+            name: "Kimi K3",
             api: "anthropic-messages",
             provider: "kimi-coding",
             baseUrl: "https://api.kimi.com/coding",
@@ -6420,12 +6420,12 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 32768,
+            contextWindow: 1048576,
+            maxTokens: 131072,
         },
         "kimi-for-coding": {
             id: "kimi-for-coding",
-            name: "Kimi For Coding",
+            name: "Kimi K2.7 Code",
             api: "anthropic-messages",
             provider: "kimi-coding",
             baseUrl: "https://api.kimi.com/coding",
@@ -6459,24 +6459,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
-        "kimi-k2-thinking": {
-            id: "kimi-k2-thinking",
-            name: "Kimi K2 Thinking",
-            api: "anthropic-messages",
-            provider: "kimi-coding",
-            baseUrl: "https://api.kimi.com/coding",
-            headers: { "User-Agent": "KimiCLI/1.5" },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 32768,
-        },
     },
     "llama-cpp": {
         "local": {
@@ -7245,6 +7227,24 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 262144,
         },
+        "kimi-k3": {
+            id: "kimi-k3",
+            name: "Kimi K3",
+            api: "openai-completions",
+            provider: "moonshotai",
+            baseUrl: "https://api.moonshot.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 3,
+                output: 15,
+                cacheRead: 0.3,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
     },
     "moonshotai-cn": {
         "kimi-k2-0711-preview": {
@@ -7409,6 +7409,24 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 262144,
         },
+        "kimi-k3": {
+            id: "kimi-k3",
+            name: "Kimi K3",
+            api: "openai-completions",
+            provider: "moonshotai-cn",
+            baseUrl: "https://api.moonshot.cn/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 3,
+                output: 15,
+                cacheRead: 0.3,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
     },
     "openai": {
         "gpt-4": {
@@ -9136,7 +9154,7 @@ export const MODELS = {
         "grok-4.5": {
             id: "grok-4.5",
             name: "Grok 4.5",
-            api: "openai-completions",
+            api: "openai-responses",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
             reasoning: true,
@@ -9406,9 +9424,9 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
             cost: {
-                input: 1.74,
-                output: 3.48,
-                cacheRead: 0.0145,
+                input: 0.435,
+                output: 0.87,
+                cacheRead: 0.003625,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -9448,6 +9466,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 131072,
         },
+        "grok-4.5": {
+            id: "grok-4.5",
+            name: "Grok 4.5",
+            api: "openai-responses",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 6,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 500000,
+            maxTokens: 500000,
+        },
         "kimi-k2.6": {
             id: "kimi-k2.6",
             name: "Kimi K2.6",
@@ -9484,6 +9519,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 262144,
         },
+        "kimi-k3": {
+            id: "kimi-k3",
+            name: "Kimi K3 (2x usage)",
+            api: "openai-completions",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 3,
+                output: 15,
+                cacheRead: 0.3,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
         "mimo-v2.5": {
             id: "mimo-v2.5",
             name: "MiMo V2.5",
@@ -9510,9 +9562,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.74,
-                output: 3.48,
-                cacheRead: 0.0145,
+                input: 0.435,
+                output: 0.87,
+                cacheRead: 0.003625,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -10338,7 +10390,7 @@ export const MODELS = {
             cost: {
                 input: 0.098,
                 output: 0.196,
-                cacheRead: 0.02,
+                cacheRead: 0.0196,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -10593,13 +10645,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.08,
-                output: 0.44999999999999996,
-                cacheRead: 0.04,
+                input: 0.09999999999999999,
+                output: 0.3,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 131072,
+            maxTokens: 4096,
         },
         "google/gemma-4-26b-a4b-it": {
             id: "google/gemma-4-26b-a4b-it",
@@ -10610,13 +10662,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.3,
+                input: 0.07,
+                output: 0.33999999999999997,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 256000,
+            maxTokens: 16384,
         },
         "google/gemma-4-26b-a4b-it:free": {
             id: "google/gemma-4-26b-a4b-it:free",
@@ -10644,13 +10696,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.22,
-                output: 0.55,
-                cacheRead: 0.12,
+                input: 0.12,
+                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",
@@ -10806,6 +10858,23 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 80000,
         },
+        "meituan/longcat-2.0": {
+            id: "meituan/longcat-2.0",
+            name: "Meituan: LongCat 2.0",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.006,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048756,
+            maxTokens: 262144,
+        },
         "meta-llama/llama-3.1-70b-instruct": {
             id: "meta-llama/llama-3.1-70b-instruct",
             name: "Meta: Llama 3.1 70B Instruct",
@@ -10857,23 +10926,6 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 128000,
         },
-        "meta-llama/llama-3.3-70b-instruct:free": {
-            id: "meta-llama/llama-3.3-70b-instruct:free",
-            name: "Meta: Llama 3.3 70B Instruct (free)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 4096,
-        },
         "meta-llama/llama-4-maverick": {
             id: "meta-llama/llama-4-maverick",
             name: "Meta: Llama 4 Maverick",
@@ -10908,6 +10960,23 @@ export const MODELS = {
             contextWindow: 10000000,
             maxTokens: 16384,
         },
+        "meta/muse-spark-1.1": {
+            id: "meta/muse-spark-1.1",
+            name: "Meta: Muse Spark 1.1",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.25,
+                output: 4.25,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 4096,
+        },
         "minimax/minimax-m1": {
             id: "minimax/minimax-m1",
             name: "MiniMax: MiniMax M1",
@@ -10985,9 +11054,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.3,
-                output: 1.2,
-                cacheRead: 0.06,
+                input: 0.25,
+                output: 1,
+                cacheRead: 0.049999999999999996,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
@@ -11206,8 +11275,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.02,
-                output: 0.04,
+                input: 0.019000000000000003,
+                output: 0.03,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -11344,11 +11413,11 @@ export const MODELS = {
             cost: {
                 input: 0.6,
                 output: 2.5,
-                cacheRead: 0,
+                cacheRead: 0.15,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 100352,
         },
         "moonshotai/kimi-k2.5": {
             id: "moonshotai/kimi-k2.5",
@@ -11377,13 +11446,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.95,
-                output: 4,
-                cacheRead: 0.16,
+                input: 0.684,
+                output: 3.42,
+                cacheRead: 0.144,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 262144,
         },
         "moonshotai/kimi-k2.7-code": {
             id: "moonshotai/kimi-k2.7-code",
@@ -11394,14 +11463,31 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.719,
-                output: 3.49,
-                cacheRead: 0.149,
+                input: 0.82,
+                output: 3.75,
+                cacheRead: 0.16,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
             maxTokens: 262144,
         },
+        "moonshotai/kimi-k3": {
+            id: "moonshotai/kimi-k3",
+            name: "MoonshotAI: Kimi K3",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 3,
+                output: 15,
+                cacheRead: 0.3,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 4096,
+        },
         "nex-agi/nex-n2-mini": {
             id: "nex-agi/nex-n2-mini",
             name: "Nex AGI: Nex-N2-Mini",
@@ -11436,23 +11522,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 262144,
         },
-        "nvidia/llama-3.3-nemotron-super-49b-v1.5": {
-            id: "nvidia/llama-3.3-nemotron-super-49b-v1.5",
-            name: "NVIDIA: Llama 3.3 Nemotron Super 49B V1.5",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.39999999999999997,
-                output: 0.39999999999999997,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 16384,
-        },
         "nvidia/nemotron-3-nano-30b-a3b": {
             id: "nvidia/nemotron-3-nano-30b-a3b",
             name: "NVIDIA: Nemotron 3 Nano 30B A3B",
@@ -11513,13 +11582,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.21,
-                output: 0.45499999999999996,
-                cacheRead: 0.06,
+                input: 0.08499999999999999,
+                output: 0.39999999999999997,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "nvidia/nemotron-3-super-120b-a12b:free": {
             id: "nvidia/nemotron-3-super-120b-a12b:free",
@@ -12644,6 +12713,23 @@ export const MODELS = {
             contextWindow: 2000000,
             maxTokens: 4096,
         },
+        "openrouter/auto-beta": {
+            id: "openrouter/auto-beta",
+            name: "Auto Router (Beta)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: -1000000,
+                output: -1000000,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 2000000,
+            maxTokens: 4096,
+        },
         "openrouter/free": {
             id: "openrouter/free",
             name: "Free Models Router",
@@ -12840,13 +12926,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
+                input: 0.12,
                 output: 0.24,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131702,
-            maxTokens: 40960,
+            maxTokens: 16384,
         },
         "qwen/qwen3-235b-a22b": {
             id: "qwen/qwen3-235b-a22b",
@@ -12891,13 +12977,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.14950000000000002,
-                output: 1.495,
+                input: 0.3,
+                output: 3,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 32768,
         },
         "qwen/qwen3-30b-a3b": {
             id: "qwen/qwen3-30b-a3b",
@@ -12908,13 +12994,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.12,
-                output: 0.5,
+                input: 0.13,
+                output: 0.52,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 16384,
+            maxTokens: 8192,
         },
         "qwen/qwen3-30b-a3b-instruct-2507": {
             id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -13069,23 +13155,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 65536,
         },
-        "qwen/qwen3-coder:free": {
-            id: "qwen/qwen3-coder:free",
-            name: "Qwen: Qwen3 Coder 480B A35B (free)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 262000,
-        },
         "qwen/qwen3-max": {
             id: "qwen/qwen3-max",
             name: "Qwen: Qwen3 Max",
@@ -13137,23 +13206,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 262144,
         },
-        "qwen/qwen3-next-80b-a3b-instruct:free": {
-            id: "qwen/qwen3-next-80b-a3b-instruct:free",
-            name: "Qwen: Qwen3 Next 80B A3B Instruct (free)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 4096,
-        },
         "qwen/qwen3-next-80b-a3b-thinking": {
             id: "qwen/qwen3-next-80b-a3b-thinking",
             name: "Qwen: Qwen3 Next 80B A3B Thinking",
@@ -13316,13 +13368,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.195,
-                output: 1.56,
+                input: 0.26,
+                output: 2.6,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 65536,
+            maxTokens: 81920,
         },
         "qwen/qwen3.5-35b-a3b": {
             id: "qwen/qwen3.5-35b-a3b",
@@ -13350,9 +13402,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.44999999999999996,
-                output: 3,
-                cacheRead: 0.22499999999999998,
+                input: 0.39,
+                output: 2.34,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -13715,6 +13767,23 @@ export const MODELS = {
             contextWindow: 32768,
             maxTokens: 32768,
         },
+        "thinkingmachines/inkling": {
+            id: "thinkingmachines/inkling",
+            name: "Thinking Machines: Inkling",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1,
+                output: 4.05,
+                cacheRead: 0.16999999999999998,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 4096,
+        },
         "upstage/solar-pro-3": {
             id: "upstage/solar-pro-3",
             name: "Upstage: Solar Pro 3",
@@ -13777,7 +13846,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0.5,
+                cacheRead: 0.3,
                 cacheWrite: 0,
             },
             contextWindow: 500000,
@@ -13945,13 +14014,13 @@ 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",
@@ -13967,8 +14036,8 @@ export const MODELS = {
                 cacheRead: 0.119,
                 cacheWrite: 0,
             },
-            contextWindow: 202752,
-            maxTokens: 202752,
+            contextWindow: 204800,
+            maxTokens: 131072,
         },
         "z-ai/glm-5-turbo": {
             id: "z-ai/glm-5-turbo",
@@ -14013,9 +14082,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.9478,
-                output: 2.9788,
-                cacheRead: 0.17602,
+                input: 0.9786,
+                output: 3.0755999999999997,
+                cacheRead: 0.18174,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -14149,13 +14218,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.66,
-                output: 3.41,
-                cacheRead: 0.15,
+                input: 3,
+                output: 15,
+                cacheRead: 0.3,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 262144,
+            contextWindow: 1048576,
+            maxTokens: 4096,
         },
         "~openai/gpt-latest": {
             id: "~openai/gpt-latest",
@@ -14202,7 +14271,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0.5,
+                cacheRead: 0.3,
                 cacheWrite: 0,
             },
             contextWindow: 500000,
@@ -14266,43 +14335,6 @@ export const MODELS = {
             contextWindow: 32768,
             maxTokens: 32768,
         },
-        "Qwen/Qwen3-235B-A22B-Instruct-2507-tput": {
-            id: "Qwen/Qwen3-235B-A22B-Instruct-2507-tput",
-            name: "Qwen3 235B A22B Instruct 2507 FP8",
-            api: "openai-completions",
-            provider: "together",
-            baseUrl: "https://api.together.ai/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.2,
-                output: 0.6,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 262144,
-        },
-        "Qwen/Qwen3.5-397B-A17B": {
-            id: "Qwen/Qwen3.5-397B-A17B",
-            name: "Qwen3.5 397B A17B",
-            api: "openai-completions",
-            provider: "together",
-            baseUrl: "https://api.together.ai/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
-            reasoning: true,
-            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
-            input: ["text", "image"],
-            cost: {
-                input: 0.6,
-                output: 3.6,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 130000,
-        },
         "Qwen/Qwen3.5-9B": {
             id: "Qwen/Qwen3.5-9B",
             name: "Qwen3.5 9B",
@@ -14378,24 +14410,6 @@ export const MODELS = {
             contextWindow: 512000,
             maxTokens: 384000,
         },
-        "essentialai/Rnj-1-Instruct": {
-            id: "essentialai/Rnj-1-Instruct",
-            name: "Rnj-1 Instruct",
-            api: "openai-completions",
-            provider: "together",
-            baseUrl: "https://api.together.ai/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false },
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.15,
-                output: 0.15,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 32768,
-            maxTokens: 32768,
-        },
         "google/gemma-4-31B-it": {
             id: "google/gemma-4-31B-it",
             name: "Gemma 4 31B Instruct",
@@ -14528,42 +14542,23 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 131072,
         },
-        "zai-org/GLM-5": {
-            id: "zai-org/GLM-5",
-            name: "GLM-5",
+        "thinkingmachines/Inkling": {
+            id: "thinkingmachines/Inkling",
+            name: "Inkling",
             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"],
+            input: ["text", "image"],
             cost: {
                 input: 1,
-                output: 3.2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 202752,
-            maxTokens: 131072,
-        },
-        "zai-org/GLM-5.1": {
-            id: "zai-org/GLM-5.1",
-            name: "GLM-5.1",
-            api: "openai-completions",
-            provider: "together",
-            baseUrl: "https://api.together.ai/v1",
-            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
-            reasoning: true,
-            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
-            input: ["text"],
-            cost: {
-                input: 1.4,
-                output: 4.4,
-                cacheRead: 0,
+                output: 4.05,
+                cacheRead: 0.17,
                 cacheWrite: 0,
             },
-            contextWindow: 202752,
+            contextWindow: 524288,
             maxTokens: 131072,
         },
         "zai-org/GLM-5.2": {
@@ -15890,40 +15885,6 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 8192,
         },
-        "meta/llama-3.2-11b": {
-            id: "meta/llama-3.2-11b",
-            name: "Llama 3.2 11B Vision Instruct",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.16,
-                output: 0.16,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 8192,
-        },
-        "meta/llama-3.2-90b": {
-            id: "meta/llama-3.2-90b",
-            name: "Llama 3.2 90B Vision Instruct",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.72,
-                output: 0.72,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 8192,
-        },
         "meta/llama-3.3-70b": {
             id: "meta/llama-3.3-70b",
             name: "Llama 3.3 70B Instruct",
@@ -16468,6 +16429,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
+        "moonshotai/kimi-k3": {
+            id: "moonshotai/kimi-k3",
+            name: "Kimi K3",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 3,
+                output: 15,
+                cacheRead: 0.3,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
         "nvidia/nemotron-3-nano-30b-a3b": {
             id: "nvidia/nemotron-3-nano-30b-a3b",
             name: "Nemotron 3 Nano 30B A3B",
@@ -17514,7 +17492,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0.5,
+                cacheRead: 0.3,
                 cacheWrite: 0,
             },
             contextWindow: 500000,
@@ -17924,7 +17902,7 @@ export const MODELS = {
             cost: {
                 input: 2,
                 output: 6,
-                cacheRead: 0.5,
+                cacheRead: 0.3,
                 cacheWrite: 0,
             },
             contextWindow: 500000,