@elyracode/ai 0.9.16 → 0.9.18

package/dist/models.generated.js

@@ -4685,7 +4685,7 @@ export const MODELS = {
                 input: 1,
                 output: 6,
                 cacheRead: 0.1,
-                cacheWrite: 0,
+                cacheWrite: 1.25,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -4704,7 +4704,7 @@ export const MODELS = {
                 input: 5,
                 output: 30,
                 cacheRead: 0.5,
-                cacheWrite: 0,
+                cacheWrite: 6.25,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -4723,7 +4723,7 @@ export const MODELS = {
                 input: 2.5,
                 output: 15,
                 cacheRead: 0.25,
-                cacheWrite: 0,
+                cacheWrite: 3.125,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -4988,9 +4988,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.3,
-                output: 2.5,
-                cacheRead: 0.075,
+                input: 1.5,
+                output: 9,
+                cacheRead: 0.15,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -5005,8 +5005,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.1,
-                output: 0.4,
+                input: 0.25,
+                output: 1.5,
                 cacheRead: 0.025,
                 cacheWrite: 0,
             },
@@ -6284,9 +6284,9 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
-        "kimi-for-coding": {
-            id: "kimi-for-coding",
-            name: "Kimi For Coding",
+        "k3": {
+            id: "k3",
+            name: "Kimi K3",
             api: "anthropic-messages",
             provider: "kimi-coding",
             baseUrl: "https://api.kimi.com/coding",
@@ -6299,18 +6299,18 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 32768,
+            contextWindow: 1048576,
+            maxTokens: 131072,
         },
-        "kimi-k2-thinking": {
-            id: "kimi-k2-thinking",
-            name: "Kimi K2 Thinking",
+        "kimi-for-coding-highspeed": {
+            id: "kimi-for-coding-highspeed",
+            name: "Kimi For Coding HighSpeed",
             api: "anthropic-messages",
             provider: "kimi-coding",
             baseUrl: "https://api.kimi.com/coding",
             headers: { "User-Agent": "KimiCLI/1.5" },
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 0,
                 output: 0,
@@ -7102,6 +7102,24 @@ 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": {
@@ -7266,6 +7284,24 @@ 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": {
@@ -9191,9 +9227,9 @@ 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,
@@ -9233,6 +9269,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 131072,
         },
+        "grok-4.5": {
+            id: "grok-4.5",
+            name: "Grok 4.5",
+            api: "openai-completions",
+            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",
@@ -9267,6 +9320,23 @@ 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",
@@ -9293,9 +9363,9 @@ 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,
@@ -10122,7 +10192,7 @@ export const MODELS = {
             cost: {
                 input: 0.098,
                 output: 0.196,
-                cacheRead: 0.02,
+                cacheRead: 0.0196,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -10377,13 +10447,13 @@ 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",
@@ -10691,6 +10761,23 @@ 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",
@@ -10768,9 +10855,9 @@ 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,
@@ -10989,8 +11076,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.02,
-                output: 0.04,
+                input: 0.019000000000000003,
+                output: 0.03,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -11127,11 +11214,11 @@ 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",
@@ -11159,13 +11246,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.66,
-                output: 3.41,
-                cacheRead: 0.144,
+                input: 0.95,
+                output: 4,
+                cacheRead: 0.16,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 4096,
         },
         "moonshotai/kimi-k2.7-code": {
             id: "moonshotai/kimi-k2.7-code",
@@ -11176,14 +11263,31 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.719,
-                output: 3.49,
-                cacheRead: 0.149,
+                input: 1,
+                output: 4.4,
+                cacheRead: 0.19999999999999998,
                 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",
@@ -11218,23 +11322,6 @@ 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",
@@ -12318,6 +12405,23 @@ 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",
@@ -12497,13 +12601,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.24,
+                input: 0.22749999999999998,
+                output: 0.9099999999999999,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131702,
-            maxTokens: 40960,
+            maxTokens: 8192,
         },
         "qwen/qwen3-235b-a22b": {
             id: "qwen/qwen3-235b-a22b",
@@ -12565,13 +12669,13 @@ 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",
@@ -12701,7 +12805,7 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.12,
+                input: 0.11,
                 output: 0.7999999999999999,
                 cacheRead: 0.07,
                 cacheWrite: 0,
@@ -12973,13 +13077,13 @@ 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",
@@ -13007,9 +13111,9 @@ 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,
@@ -13177,10 +13281,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.25,
-                output: 3.75,
-                cacheRead: 0.25,
-                cacheWrite: 1.5625,
+                input: 1.475,
+                output: 4.425,
+                cacheRead: 0.295,
+                cacheWrite: 1.84375,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
@@ -13355,6 +13459,23 @@ 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",
@@ -13653,9 +13774,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.8932,
-                output: 2.8072,
-                cacheRead: 0.16588,
+                input: 0.3374,
+                output: 1.0604,
+                cacheRead: 0.06266000000000001,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -13790,13 +13911,13 @@ 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",
@@ -14169,6 +14290,25 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 131072,
         },
+        "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", "image"],
+            cost: {
+                input: 1,
+                output: 4.05,
+                cacheRead: 0.17,
+                cacheWrite: 0,
+            },
+            contextWindow: 524288,
+            maxTokens: 131072,
+        },
         "zai-org/GLM-5": {
             id: "zai-org/GLM-5",
             name: "GLM-5",
@@ -15526,40 +15666,6 @@ 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",
@@ -16104,6 +16210,23 @@ 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",
@@ -16949,6 +17072,23 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 256000,
         },
+        "thinkingmachines/inkling": {
+            id: "thinkingmachines/inkling",
+            name: "Inkling",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1,
+                output: 4.05,
+                cacheRead: 0.16999999999999998,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
         "xai/grok-4.1-fast-non-reasoning": {
             id: "xai/grok-4.1-fast-non-reasoning",
             name: "Grok 4.1 Fast Non-Reasoning",