@avadisabelle/ava-pi-ai 0.65.0 → 0.65.3

package/dist/models.generated.js

@@ -325,6 +325,40 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "au.anthropic.claude-opus-4-6-v1": {
+            id: "au.anthropic.claude-opus-4-6-v1",
+            name: "AU Anthropic Claude Opus 4.6",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 16.5,
+                output: 82.5,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
+        "au.anthropic.claude-sonnet-4-6": {
+            id: "au.anthropic.claude-sonnet-4-6",
+            name: "AU Anthropic Claude Sonnet 4.6",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 3.3,
+                output: 16.5,
+                cacheRead: 0.33,
+                cacheWrite: 4.125,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "deepseek.r1-v1:0": {
             id: "deepseek.r1-v1:0",
             name: "DeepSeek-R1",
@@ -2488,6 +2522,40 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "gpt-5.5": {
+            id: "gpt-5.5",
+            name: "GPT-5.5",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 30,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
+        "gpt-5.5-pro": {
+            id: "gpt-5.5-pro",
+            name: "GPT-5.5 Pro",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 30,
+                output: 180,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
         "o1": {
             id: "o1",
             name: "o1",
@@ -3134,6 +3202,24 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
+        "gpt-5.5": {
+            id: "gpt-5.5",
+            name: "GPT-5.5",
+            api: "openai-responses",
+            provider: "github-copilot",
+            baseUrl: "https://api.individual.githubcopilot.com",
+            headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
         "grok-code-fast-1": {
             id: "grok-code-fast-1",
             name: "Grok Code Fast 1",
@@ -3251,7 +3337,7 @@ export const MODELS = {
             cost: {
                 input: 0.3,
                 output: 2.5,
-                cacheRead: 0.075,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -3370,7 +3456,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.31,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -3580,8 +3666,8 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 8192,
         },
-        "gemma-4-26b-it": {
-            id: "gemma-4-26b-it",
+        "gemma-4-26b-a4b-it": {
+            id: "gemma-4-26b-a4b-it",
             name: "Gemma 4 26B",
             api: "google-generative-ai",
             provider: "google",
@@ -4622,6 +4708,24 @@ export const MODELS = {
             contextWindow: 163840,
             maxTokens: 65536,
         },
+        "deepseek-ai/DeepSeek-V4-Pro": {
+            id: "deepseek-ai/DeepSeek-V4-Pro",
+            name: "DeepSeek V4 Pro",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.74,
+                output: 3.48,
+                cacheRead: 0.145,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 393216,
+        },
         "moonshotai/Kimi-K2-Instruct": {
             id: "moonshotai/Kimi-K2-Instruct",
             name: "Kimi-K2-Instruct",
@@ -4694,6 +4798,24 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 262144,
         },
+        "moonshotai/Kimi-K2.6": {
+            id: "moonshotai/Kimi-K2.6",
+            name: "Kimi-K2.6",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.95,
+                output: 4,
+                cacheRead: 0.16,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
         "zai-org/GLM-4.7": {
             id: "zai-org/GLM-4.7",
             name: "GLM-4.7",
@@ -4768,6 +4890,23 @@ export const MODELS = {
         },
     },
     "kimi-coding": {
+        "k2p6": {
+            id: "k2p6",
+            name: "Kimi K2.6",
+            api: "anthropic-messages",
+            provider: "kimi-coding",
+            baseUrl: "https://api.kimi.com/coding",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 32768,
+        },
         "kimi-for-coding": {
             id: "kimi-for-coding",
             name: "Kimi For Coding",
@@ -5148,22 +5287,39 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 262144,
         },
+        "mistral-medium-2604": {
+            id: "mistral-medium-2604",
+            name: "Mistral Medium 3.5",
+            api: "mistral-conversations",
+            provider: "mistral",
+            baseUrl: "https://api.mistral.ai",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.5,
+                output: 7.5,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
         "mistral-medium-latest": {
             id: "mistral-medium-latest",
             name: "Mistral Medium (latest)",
             api: "mistral-conversations",
             provider: "mistral",
             baseUrl: "https://api.mistral.ai",
-            reasoning: false,
+            reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.4,
-                output: 2,
+                input: 1.5,
+                output: 7.5,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 16384,
+            contextWindow: 262144,
+            maxTokens: 262144,
         },
         "mistral-nemo": {
             id: "mistral-nemo",
@@ -5864,6 +6020,40 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "gpt-5.5": {
+            id: "gpt-5.5",
+            name: "GPT-5.5",
+            api: "openai-responses",
+            provider: "openai",
+            baseUrl: "https://api.openai.com/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 30,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
+        "gpt-5.5-pro": {
+            id: "gpt-5.5-pro",
+            name: "GPT-5.5 Pro",
+            api: "openai-responses",
+            provider: "openai",
+            baseUrl: "https://api.openai.com/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 30,
+                output: 180,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
         "o1": {
             id: "o1",
             name: "o1",
@@ -6174,23 +6364,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 128000,
         },
-        "claude-3-5-haiku": {
-            id: "claude-3-5-haiku",
-            name: "Claude Haiku 3.5",
-            api: "anthropic-messages",
-            provider: "opencode",
-            baseUrl: "https://opencode.ai/zen",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.8,
-                output: 4,
-                cacheRead: 0.08,
-                cacheWrite: 1,
-            },
-            contextWindow: 200000,
-            maxTokens: 8192,
-        },
         "claude-haiku-4-5": {
             id: "claude-haiku-4-5",
             name: "Claude Haiku 4.5",
@@ -6633,6 +6806,57 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "gpt-5.5": {
+            id: "gpt-5.5",
+            name: "GPT-5.5",
+            api: "openai-responses",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 30,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
+        "gpt-5.5-pro": {
+            id: "gpt-5.5-pro",
+            name: "GPT-5.5 Pro",
+            api: "openai-responses",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 30,
+                output: 180,
+                cacheRead: 30,
+                cacheWrite: 0,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
+        "hy3-preview-free": {
+            id: "hy3-preview-free",
+            name: "Hy3 preview Free",
+            api: "openai-completions",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 64000,
+        },
         "kimi-k2.5": {
             id: "kimi-k2.5",
             name: "Kimi K2.5",
@@ -6650,6 +6874,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
+        "kimi-k2.6": {
+            id: "kimi-k2.6",
+            name: "Kimi K2.6",
+            api: "openai-completions",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.95,
+                output: 4,
+                cacheRead: 0.16,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 65536,
+        },
         "minimax-m2.5": {
             id: "minimax-m2.5",
             name: "MiniMax M2.5",
@@ -6684,6 +6925,23 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131072,
         },
+        "minimax-m2.7": {
+            id: "minimax-m2.7",
+            name: "MiniMax M2.7",
+            api: "openai-completions",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
+                cacheWrite: 0,
+            },
+            contextWindow: 204800,
+            maxTokens: 131072,
+        },
         "nemotron-3-super-free": {
             id: "nemotron-3-super-free",
             name: "Nemotron 3 Super Free",
@@ -6704,9 +6962,9 @@ export const MODELS = {
         "qwen3.5-plus": {
             id: "qwen3.5-plus",
             name: "Qwen3.5 Plus",
-            api: "openai-completions",
+            api: "anthropic-messages",
             provider: "opencode",
-            baseUrl: "https://opencode.ai/zen/v1",
+            baseUrl: "https://opencode.ai/zen",
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -6721,9 +6979,9 @@ export const MODELS = {
         "qwen3.6-plus": {
             id: "qwen3.6-plus",
             name: "Qwen3.6 Plus",
-            api: "openai-completions",
+            api: "anthropic-messages",
             provider: "opencode",
-            baseUrl: "https://opencode.ai/zen/v1",
+            baseUrl: "https://opencode.ai/zen",
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -6737,7 +6995,41 @@ export const MODELS = {
         },
     },
     "opencode-go": {
-        "glm-5": {
+        "deepseek-v4-flash": {
+            id: "deepseek-v4-flash",
+            name: "DeepSeek V4 Flash",
+            api: "openai-completions",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.0028,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
+        "deepseek-v4-pro": {
+            id: "deepseek-v4-pro",
+            name: "DeepSeek V4 Pro",
+            api: "openai-completions",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.74,
+                output: 3.48,
+                cacheRead: 0.0145,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
+        "glm-5": {
             id: "glm-5",
             name: "GLM-5",
             api: "openai-completions",
@@ -6751,8 +7043,8 @@ export const MODELS = {
                 cacheRead: 0.2,
                 cacheWrite: 0,
             },
-            contextWindow: 204800,
-            maxTokens: 131072,
+            contextWindow: 202752,
+            maxTokens: 32768,
         },
         "glm-5.1": {
             id: "glm-5.1",
@@ -6768,8 +7060,8 @@ export const MODELS = {
                 cacheRead: 0.26,
                 cacheWrite: 0,
             },
-            contextWindow: 204800,
-            maxTokens: 131072,
+            contextWindow: 202752,
+            maxTokens: 32768,
         },
         "kimi-k2.5": {
             id: "kimi-k2.5",
@@ -6788,6 +7080,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
+        "kimi-k2.6": {
+            id: "kimi-k2.6",
+            name: "Kimi K2.6 (3x limits)",
+            api: "openai-completions",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.32,
+                output: 1.34,
+                cacheRead: 0.054,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 65536,
+        },
         "mimo-v2-omni": {
             id: "mimo-v2-omni",
             name: "MiMo V2 Omni",
@@ -6803,7 +7112,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 64000,
+            maxTokens: 128000,
         },
         "mimo-v2-pro": {
             id: "mimo-v2-pro",
@@ -6820,7 +7129,41 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 64000,
+            maxTokens: 128000,
+        },
+        "mimo-v2.5": {
+            id: "mimo-v2.5",
+            name: "MiMo V2.5",
+            api: "openai-completions",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.4,
+                output: 2,
+                cacheRead: 0.08,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
+        "mimo-v2.5-pro": {
+            id: "mimo-v2.5-pro",
+            name: "MiMo V2.5 Pro",
+            api: "openai-completions",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1,
+                output: 3,
+                cacheRead: 0.2,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 128000,
         },
         "minimax-m2.5": {
             id: "minimax-m2.5",
@@ -6859,9 +7202,9 @@ export const MODELS = {
         "qwen3.5-plus": {
             id: "qwen3.5-plus",
             name: "Qwen3.5 Plus",
-            api: "openai-completions",
+            api: "anthropic-messages",
             provider: "opencode-go",
-            baseUrl: "https://opencode.ai/zen/go/v1",
+            baseUrl: "https://opencode.ai/zen/go",
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -6876,9 +7219,9 @@ export const MODELS = {
         "qwen3.6-plus": {
             id: "qwen3.6-plus",
             name: "Qwen3.6 Plus",
-            api: "openai-completions",
+            api: "anthropic-messages",
             provider: "opencode-go",
-            baseUrl: "https://opencode.ai/zen/go/v1",
+            baseUrl: "https://opencode.ai/zen/go",
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -6941,7 +7284,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 65536,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "amazon/nova-2-lite-v1": {
             id: "amazon/nova-2-lite-v1",
@@ -7266,17 +7609,17 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "arcee-ai/trinity-large-preview:free": {
-            id: "arcee-ai/trinity-large-preview:free",
-            name: "Arcee AI: Trinity Large Preview (free)",
+        "arcee-ai/trinity-large-preview": {
+            id: "arcee-ai/trinity-large-preview",
+            name: "Arcee AI: Trinity Large Preview",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0,
-                output: 0,
+                input: 0.15,
+                output: 0.44999999999999996,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -7502,7 +7845,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 163840,
+            maxTokens: 16384,
         },
         "deepseek/deepseek-chat-v3-0324": {
             id: "deepseek/deepseek-chat-v3-0324",
@@ -7519,7 +7862,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "deepseek/deepseek-chat-v3.1": {
             id: "deepseek/deepseek-chat-v3.1",
@@ -7570,7 +7913,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 4096,
+            maxTokens: 32768,
         },
         "deepseek/deepseek-v3.1-terminus": {
             id: "deepseek/deepseek-v3.1-terminus",
@@ -7581,13 +7924,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.21,
-                output: 0.7899999999999999,
-                cacheRead: 0.1300000002,
+                input: 0.27,
+                output: 0.95,
+                cacheRead: 0.13,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 4096,
+            maxTokens: 32768,
         },
         "deepseek/deepseek-v3.2": {
             id: "deepseek/deepseek-v3.2",
@@ -7598,13 +7941,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.25899999999999995,
-                output: 0.42,
-                cacheRead: 0.135,
+                input: 0.252,
+                output: 0.378,
+                cacheRead: 0.0252,
                 cacheWrite: 0,
             },
-            contextWindow: 163840,
-            maxTokens: 163840,
+            contextWindow: 131072,
+            maxTokens: 65536,
         },
         "deepseek/deepseek-v3.2-exp": {
             id: "deepseek/deepseek-v3.2-exp",
@@ -7623,6 +7966,40 @@ export const MODELS = {
             contextWindow: 163840,
             maxTokens: 65536,
         },
+        "deepseek/deepseek-v4-flash": {
+            id: "deepseek/deepseek-v4-flash",
+            name: "DeepSeek: DeepSeek V4 Flash",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.0028,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 384000,
+        },
+        "deepseek/deepseek-v4-pro": {
+            id: "deepseek/deepseek-v4-pro",
+            name: "DeepSeek: DeepSeek V4 Pro",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.435,
+                output: 0.87,
+                cacheRead: 0.003625,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 384000,
+        },
         "essentialai/rnj-1-instruct": {
             id: "essentialai/rnj-1-instruct",
             name: "EssentialAI: Rnj 1 Instruct",
@@ -7844,6 +8221,40 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
+        "google/gemma-3-12b-it": {
+            id: "google/gemma-3-12b-it",
+            name: "Google: Gemma 3 12B",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.04,
+                output: 0.13,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 16384,
+        },
+        "google/gemma-3-27b-it": {
+            id: "google/gemma-3-27b-it",
+            name: "Google: Gemma 3 27B",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.08,
+                output: 0.16,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 16384,
+        },
         "google/gemma-4-26b-a4b-it": {
             id: "google/gemma-4-26b-a4b-it",
             name: "Google: Gemma 4 26B A4B ",
@@ -7853,9 +8264,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.08,
-                output: 0.35,
-                cacheRead: 0.01,
+                input: 0.06,
+                output: 0.33,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -7889,11 +8300,11 @@ export const MODELS = {
             cost: {
                 input: 0.13,
                 output: 0.38,
-                cacheRead: 0.019999999499999997,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "google/gemma-4-31b-it:free": {
             id: "google/gemma-4-31b-it:free",
@@ -7912,6 +8323,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
+        "ibm-granite/granite-4.1-8b": {
+            id: "ibm-granite/granite-4.1-8b",
+            name: "IBM: Granite 4.1 8B",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.049999999999999996,
+                output: 0.09999999999999999,
+                cacheRead: 0.049999999999999996,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 131072,
+        },
         "inception/mercury-2": {
             id: "inception/mercury-2",
             name: "Inception: Mercury 2",
@@ -7929,6 +8357,40 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 50000,
         },
+        "inclusionai/ling-2.6-1t:free": {
+            id: "inclusionai/ling-2.6-1t:free",
+            name: "inclusionAI: Ling-2.6-1T (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: 32768,
+        },
+        "inclusionai/ling-2.6-flash": {
+            id: "inclusionai/ling-2.6-flash",
+            name: "inclusionAI: Ling-2.6-flash",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.08,
+                output: 0.24,
+                cacheRead: 0.016,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 32768,
+        },
         "kwaipilot/kat-coder-pro-v2": {
             id: "kwaipilot/kat-coder-pro-v2",
             name: "Kwaipilot: KAT-Coder-Pro V2",
@@ -7978,7 +8440,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "meta-llama/llama-3.1-8b-instruct": {
             id: "meta-llama/llama-3.1-8b-instruct",
@@ -8006,13 +8468,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.12,
-                output: 0.38,
+                input: 0.09999999999999999,
+                output: 0.32,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 131072,
+            maxTokens: 16384,
         },
         "meta-llama/llama-3.3-70b-instruct:free": {
             id: "meta-llama/llama-3.3-70b-instruct:free",
@@ -8108,13 +8570,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.118,
-                output: 0.9900000000000001,
-                cacheRead: 0.059,
+                input: 0.15,
+                output: 1.15,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 196608,
-            maxTokens: 65536,
+            maxTokens: 131072,
         },
         "minimax/minimax-m2.5:free": {
             id: "minimax/minimax-m2.5:free",
@@ -8381,12 +8843,12 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.02,
-                output: 0.04,
+                output: 0.03,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 16384,
+            maxTokens: 4096,
         },
         "mistralai/mistral-saba": {
             id: "mistralai/mistral-saba",
@@ -8437,24 +8899,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 4096,
-        },
-        "mistralai/mistral-small-creative": {
-            id: "mistralai/mistral-small-creative",
-            name: "Mistral: Mistral Small Creative",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.09999999999999999,
-                output: 0.3,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 32768,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "mistralai/mixtral-8x22b-instruct": {
             id: "mistralai/mixtral-8x22b-instruct",
@@ -8592,6 +9037,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 4096,
         },
+        "moonshotai/kimi-k2.6": {
+            id: "moonshotai/kimi-k2.6",
+            name: "MoonshotAI: Kimi K2.6",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.74,
+                output: 3.49,
+                cacheRead: 0.14,
+                cacheWrite: 0,
+            },
+            contextWindow: 262142,
+            maxTokens: 262142,
+        },
         "nex-agi/deepseek-v3.1-nex-n1": {
             id: "nex-agi/deepseek-v3.1-nex-n1",
             name: "Nex AGI: DeepSeek V3.1 Nex N1",
@@ -8641,7 +9103,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "nvidia/nemotron-3-nano-30b-a3b": {
             id: "nvidia/nemotron-3-nano-30b-a3b",
@@ -8658,7 +9120,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 228000,
         },
         "nvidia/nemotron-3-nano-30b-a3b:free": {
             id: "nvidia/nemotron-3-nano-30b-a3b:free",
@@ -8677,16 +9139,33 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 4096,
         },
-        "nvidia/nemotron-3-super-120b-a12b": {
-            id: "nvidia/nemotron-3-super-120b-a12b",
-            name: "NVIDIA: Nemotron 3 Super",
+        "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": {
+            id: "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free",
+            name: "NVIDIA: Nemotron 3 Nano Omni (free)",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
-                input: 0.09,
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 65536,
+        },
+        "nvidia/nemotron-3-super-120b-a12b": {
+            id: "nvidia/nemotron-3-super-120b-a12b",
+            name: "NVIDIA: Nemotron 3 Super",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.09,
                 output: 0.44999999999999996,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -8743,7 +9222,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "nvidia/nemotron-nano-9b-v2:free": {
             id: "nvidia/nemotron-nano-9b-v2:free",
@@ -9102,40 +9581,6 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
-        "openai/gpt-5-image": {
-            id: "openai/gpt-5-image",
-            name: "OpenAI: GPT-5 Image",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 10,
-                output: 10,
-                cacheRead: 1.25,
-                cacheWrite: 0,
-            },
-            contextWindow: 400000,
-            maxTokens: 128000,
-        },
-        "openai/gpt-5-image-mini": {
-            id: "openai/gpt-5-image-mini",
-            name: "OpenAI: GPT-5 Image Mini",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 2.5,
-                output: 2,
-                cacheRead: 0.25,
-                cacheWrite: 0,
-            },
-            contextWindow: 400000,
-            maxTokens: 128000,
-        },
         "openai/gpt-5-mini": {
             id: "openai/gpt-5-mini",
             name: "OpenAI: GPT-5 Mini",
@@ -9442,6 +9887,40 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "openai/gpt-5.5": {
+            id: "openai/gpt-5.5",
+            name: "OpenAI: GPT-5.5",
+            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: 1050000,
+            maxTokens: 128000,
+        },
+        "openai/gpt-5.5-pro": {
+            id: "openai/gpt-5.5-pro",
+            name: "OpenAI: GPT-5.5 Pro",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 30,
+                output: 180,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
         "openai/gpt-audio": {
             id: "openai/gpt-audio",
             name: "OpenAI: GPT Audio",
@@ -9486,7 +9965,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.039,
-                output: 0.19,
+                output: 0.18,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -9525,7 +10004,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 4096,
+            maxTokens: 131072,
         },
         "openai/gpt-oss-20b:free": {
             id: "openai/gpt-oss-20b:free",
@@ -9731,9 +10210,26 @@ export const MODELS = {
             contextWindow: 2000000,
             maxTokens: 4096,
         },
-        "openrouter/elephant-alpha": {
-            id: "openrouter/elephant-alpha",
-            name: "Elephant",
+        "openrouter/free": {
+            id: "openrouter/free",
+            name: "Free Models Router",
+            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: 200000,
+            maxTokens: 4096,
+        },
+        "openrouter/owl-alpha": {
+            id: "openrouter/owl-alpha",
+            name: "Owl Alpha",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
@@ -9745,25 +10241,42 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 32768,
+            contextWindow: 1048756,
+            maxTokens: 262144,
         },
-        "openrouter/free": {
-            id: "openrouter/free",
-            name: "Free Models Router",
+        "poolside/laguna-m.1:free": {
+            id: "poolside/laguna-m.1:free",
+            name: "Poolside: Laguna M.1 (free)",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
                 input: 0,
                 output: 0,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 200000,
-            maxTokens: 4096,
+            contextWindow: 131072,
+            maxTokens: 8192,
+        },
+        "poolside/laguna-xs.2:free": {
+            id: "poolside/laguna-xs.2:free",
+            name: "Poolside: Laguna XS.2 (free)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 8192,
         },
         "prime-intellect/intellect-3": {
             id: "prime-intellect/intellect-3",
@@ -9791,8 +10304,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.12,
-                output: 0.39,
+                input: 0.36,
+                output: 0.39999999999999997,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -9967,7 +10480,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "qwen/qwen3-235b-a22b-thinking-2507": {
             id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -9978,13 +10491,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.13,
-                output: 0.6,
+                input: 0.14950000000000002,
+                output: 1.495,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 262144,
+            contextWindow: 131072,
+            maxTokens: 4096,
         },
         "qwen/qwen3-30b-a3b": {
             id: "qwen/qwen3-30b-a3b",
@@ -9995,13 +10508,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.08,
-                output: 0.28,
+                input: 0.09,
+                output: 0.44999999999999996,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 40960,
-            maxTokens: 40960,
+            maxTokens: 20000,
         },
         "qwen/qwen3-30b-a3b-instruct-2507": {
             id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -10081,12 +10594,12 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.22,
-                output: 1,
-                cacheRead: 0.022,
+                output: 1.7999999999999998,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 65536,
         },
         "qwen/qwen3-coder-30b-a3b-instruct": {
             id: "qwen/qwen3-coder-30b-a3b-instruct",
@@ -10131,9 +10644,9 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.15,
+                input: 0.12,
                 output: 0.7999999999999999,
-                cacheRead: 0.12,
+                cacheRead: 0.07,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -10222,7 +10735,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "qwen/qwen3-next-80b-a3b-instruct:free": {
             id: "qwen/qwen3-next-80b-a3b-instruct:free",
@@ -10273,7 +10786,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "qwen/qwen3-vl-235b-a22b-thinking": {
             id: "qwen/qwen3-vl-235b-a22b-thinking",
@@ -10496,39 +11009,90 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 65536,
         },
-        "qwen/qwen3.6-plus": {
-            id: "qwen/qwen3.6-plus",
-            name: "Qwen: Qwen3.6 Plus",
+        "qwen/qwen3.5-plus-20260420": {
+            id: "qwen/qwen3.5-plus-20260420",
+            name: "Qwen: Qwen3.5 Plus 2026-04-20",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.325,
-                output: 1.95,
+                input: 0.39999999999999997,
+                output: 2.4,
                 cacheRead: 0,
-                cacheWrite: 0.40625,
+                cacheWrite: 0,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
         },
-        "qwen/qwq-32b": {
-            id: "qwen/qwq-32b",
-            name: "Qwen: QwQ 32B",
+        "qwen/qwen3.6-27b": {
+            id: "qwen/qwen3.6-27b",
+            name: "Qwen: Qwen3.6 27B",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
-                input: 0.15,
-                output: 0.58,
+                input: 0.32,
+                output: 3.1999999999999997,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 131072,
+            contextWindow: 262144,
+            maxTokens: 81920,
+        },
+        "qwen/qwen3.6-flash": {
+            id: "qwen/qwen3.6-flash",
+            name: "Qwen: Qwen3.6 Flash",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.25,
+                output: 1.5,
+                cacheRead: 0,
+                cacheWrite: 0.3125,
+            },
+            contextWindow: 1000000,
+            maxTokens: 65536,
+        },
+        "qwen/qwen3.6-max-preview": {
+            id: "qwen/qwen3.6-max-preview",
+            name: "Qwen: Qwen3.6 Max Preview",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.04,
+                output: 6.24,
+                cacheRead: 0,
+                cacheWrite: 1.3,
+            },
+            contextWindow: 262144,
+            maxTokens: 65536,
+        },
+        "qwen/qwen3.6-plus": {
+            id: "qwen/qwen3.6-plus",
+            name: "Qwen: Qwen3.6 Plus",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.325,
+                output: 1.95,
+                cacheRead: 0,
+                cacheWrite: 0.40625,
+            },
+            contextWindow: 1000000,
+            maxTokens: 65536,
         },
         "rekaai/reka-edge": {
             id: "rekaai/reka-edge",
@@ -10615,6 +11179,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
+        "tencent/hy3-preview:free": {
+            id: "tencent/hy3-preview:free",
+            name: "Tencent: Hy3 preview (free)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
         "thedrummer/rocinante-12b": {
             id: "thedrummer/rocinante-12b",
             name: "TheDrummer: Rocinante 12B",
@@ -10811,14 +11392,31 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 6,
+                input: 1.25,
+                output: 2.5,
                 cacheRead: 0.19999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 2000000,
             maxTokens: 4096,
         },
+        "x-ai/grok-4.3": {
+            id: "x-ai/grok-4.3",
+            name: "xAI: Grok 4.3",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.25,
+                output: 2.5,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 4096,
+        },
         "x-ai/grok-code-fast-1": {
             id: "x-ai/grok-code-fast-1",
             name: "xAI: Grok Code Fast 1",
@@ -10887,6 +11485,40 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 131072,
         },
+        "xiaomi/mimo-v2.5": {
+            id: "xiaomi/mimo-v2.5",
+            name: "Xiaomi: MiMo-V2.5",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.39999999999999997,
+                output: 2,
+                cacheRead: 0.08,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
+        "xiaomi/mimo-v2.5-pro": {
+            id: "xiaomi/mimo-v2.5-pro",
+            name: "Xiaomi: MiMo-V2.5-Pro",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1,
+                output: 3,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
         "z-ai/glm-4-32b": {
             id: "z-ai/glm-4-32b",
             name: "Z.ai: GLM 4 32B ",
@@ -11000,11 +11632,11 @@ export const MODELS = {
             cost: {
                 input: 0.3,
                 output: 0.8999999999999999,
-                cacheRead: 0,
+                cacheRead: 0.049999999999999996,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 131072,
+            maxTokens: 24000,
         },
         "z-ai/glm-4.7": {
             id: "z-ai/glm-4.7",
@@ -11015,13 +11647,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.39,
-                output: 1.75,
-                cacheRead: 0.195,
+                input: 0.38,
+                output: 1.74,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 202752,
-            maxTokens: 65535,
+            maxTokens: 4096,
         },
         "z-ai/glm-4.7-flash": {
             id: "z-ai/glm-4.7-flash",
@@ -11034,11 +11666,11 @@ export const MODELS = {
             cost: {
                 input: 0.06,
                 output: 0.39999999999999997,
-                cacheRead: 0.0100000002,
+                cacheRead: 0.01,
                 cacheWrite: 0,
             },
             contextWindow: 202752,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "z-ai/glm-5": {
             id: "z-ai/glm-5",
@@ -11054,8 +11686,8 @@ export const MODELS = {
                 cacheRead: 0.119,
                 cacheWrite: 0,
             },
-            contextWindow: 80000,
-            maxTokens: 131072,
+            contextWindow: 202752,
+            maxTokens: 16384,
         },
         "z-ai/glm-5-turbo": {
             id: "z-ai/glm-5-turbo",
@@ -11083,9 +11715,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.95,
-                output: 3.15,
-                cacheRead: 0.475,
+                input: 1.0499999999999998,
+                output: 3.5,
+                cacheRead: 0.5249999999999999,
                 cacheWrite: 0,
             },
             contextWindow: 202752,
@@ -11108,6 +11740,142 @@ export const MODELS = {
             contextWindow: 202752,
             maxTokens: 131072,
         },
+        "~anthropic/claude-haiku-latest": {
+            id: "~anthropic/claude-haiku-latest",
+            name: "Anthropic Claude Haiku Latest",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1,
+                output: 5,
+                cacheRead: 0.09999999999999999,
+                cacheWrite: 1.25,
+            },
+            contextWindow: 200000,
+            maxTokens: 64000,
+        },
+        "~anthropic/claude-opus-latest": {
+            id: "~anthropic/claude-opus-latest",
+            name: "Anthropic: Claude Opus Latest",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
+        "~anthropic/claude-sonnet-latest": {
+            id: "~anthropic/claude-sonnet-latest",
+            name: "Anthropic Claude Sonnet Latest",
+            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: 3.75,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
+        "~google/gemini-flash-latest": {
+            id: "~google/gemini-flash-latest",
+            name: "Google Gemini Flash Latest",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.5,
+                output: 3,
+                cacheRead: 0.049999999999999996,
+                cacheWrite: 0.08333333333333334,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
+        "~google/gemini-pro-latest": {
+            id: "~google/gemini-pro-latest",
+            name: "Google Gemini Pro 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: 0.375,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
+        "~moonshotai/kimi-latest": {
+            id: "~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: 0.74,
+                output: 3.49,
+                cacheRead: 0.14,
+                cacheWrite: 0,
+            },
+            contextWindow: 262142,
+            maxTokens: 262142,
+        },
+        "~openai/gpt-latest": {
+            id: "~openai/gpt-latest",
+            name: "OpenAI GPT Latest",
+            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: 1050000,
+            maxTokens: 128000,
+        },
+        "~openai/gpt-mini-latest": {
+            id: "~openai/gpt-mini-latest",
+            name: "OpenAI GPT Mini Latest",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.75,
+                output: 4.5,
+                cacheRead: 0.075,
+                cacheWrite: 0,
+            },
+            contextWindow: 400000,
+            maxTokens: 128000,
+        },
     },
     "vercel-ai-gateway": {
         "alibaba/qwen-3-14b": {
@@ -11178,22 +11946,39 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 8192,
         },
+        "alibaba/qwen-3.6-max-preview": {
+            id: "alibaba/qwen-3.6-max-preview",
+            name: "Qwen 3.6 Max Preview",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.3,
+                output: 7.8,
+                cacheRead: 0.26,
+                cacheWrite: 1.625,
+            },
+            contextWindow: 240000,
+            maxTokens: 64000,
+        },
         "alibaba/qwen3-235b-a22b-thinking": {
             id: "alibaba/qwen3-235b-a22b-thinking",
-            name: "Qwen3 235B A22B Thinking 2507",
+            name: "Qwen3 VL 235B A22B Thinking",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.22999999999999998,
-                output: 2.3,
-                cacheRead: 0.19999999999999998,
+                input: 0.39999999999999997,
+                output: 4,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262114,
-            maxTokens: 262114,
+            contextWindow: 131072,
+            maxTokens: 32768,
         },
         "alibaba/qwen3-coder": {
             id: "alibaba/qwen3-coder",
@@ -11365,6 +12150,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "alibaba/qwen3.6-27b": {
+            id: "alibaba/qwen3.6-27b",
+            name: "Qwen 3.6 27B",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.6,
+                output: 3.5999999999999996,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
         "alibaba/qwen3.6-plus": {
             id: "alibaba/qwen3.6-plus",
             name: "Qwen 3.6 Plus",
@@ -11377,7 +12179,7 @@ export const MODELS = {
                 input: 0.5,
                 output: 3,
                 cacheRead: 0.09999999999999999,
-                cacheWrite: 0,
+                cacheWrite: 0.625,
             },
             contextWindow: 1000000,
             maxTokens: 64000,
@@ -11745,16 +12547,50 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.62,
+                output: 1.85,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 8000,
+        },
+        "deepseek/deepseek-v4-flash": {
+            id: "deepseek/deepseek-v4-flash",
+            name: "DeepSeek V4 Flash",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.0028,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
+        "deepseek/deepseek-v4-pro": {
+            id: "deepseek/deepseek-v4-pro",
+            name: "DeepSeek V4 Pro",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.28,
-                output: 0.42,
-                cacheRead: 0.028,
+                input: 0.435,
+                output: 0.87,
+                cacheRead: 0.0036,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 64000,
+            contextWindow: 1000000,
+            maxTokens: 384000,
         },
         "google/gemini-2.0-flash": {
             id: "google/gemini-2.0-flash",
@@ -12521,6 +13357,23 @@ export const MODELS = {
             contextWindow: 262114,
             maxTokens: 262114,
         },
+        "moonshotai/kimi-k2.6": {
+            id: "moonshotai/kimi-k2.6",
+            name: "Kimi K2.6",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.95,
+                output: 4,
+                cacheRead: 0.16,
+                cacheWrite: 0,
+            },
+            contextWindow: 262000,
+            maxTokens: 262000,
+        },
         "nvidia/nemotron-nano-12b-v2-vl": {
             id: "nvidia/nemotron-nano-12b-v2-vl",
             name: "Nvidia Nemotron Nano 12B V2 VL",
@@ -13014,6 +13867,40 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "openai/gpt-5.5": {
+            id: "openai/gpt-5.5",
+            name: "GPT 5.5",
+            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: 128000,
+        },
+        "openai/gpt-5.5-pro": {
+            id: "openai/gpt-5.5-pro",
+            name: "GPT 5.5 Pro",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 30,
+                output: 180,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "openai/gpt-oss-20b": {
             id: "openai/gpt-oss-20b",
             name: "GPT OSS 120B",
@@ -13184,23 +14071,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 8000,
         },
-        "prime-intellect/intellect-3": {
-            id: "prime-intellect/intellect-3",
-            name: "INTELLECT 3",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.19999999999999998,
-                output: 1.1,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
         "xai/grok-3": {
             id: "xai/grok-3",
             name: "Grok 3 Beta",
@@ -13456,6 +14326,23 @@ export const MODELS = {
             contextWindow: 2000000,
             maxTokens: 2000000,
         },
+        "xai/grok-4.3": {
+            id: "xai/grok-4.3",
+            name: "Grok 4.3",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.25,
+                output: 2.5,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 1000000,
+        },
         "xai/grok-code-fast-1": {
             id: "xai/grok-code-fast-1",
             name: "Grok Code Fast 1",
@@ -13482,9 +14369,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09,
-                output: 0.29,
-                cacheRead: 0.045,
+                input: 0.09999999999999999,
+                output: 0.3,
+                cacheRead: 0.01,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -13507,6 +14394,40 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "xiaomi/mimo-v2.5": {
+            id: "xiaomi/mimo-v2.5",
+            name: "MiMo M2.5",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.39999999999999997,
+                output: 2,
+                cacheRead: 0.08,
+                cacheWrite: 0,
+            },
+            contextWindow: 1050000,
+            maxTokens: 131100,
+        },
+        "xiaomi/mimo-v2.5-pro": {
+            id: "xiaomi/mimo-v2.5-pro",
+            name: "MiMo V2.5 Pro",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1,
+                output: 3,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 0,
+            },
+            contextWindow: 1050000,
+            maxTokens: 131000,
+        },
         "zai/glm-4.5": {
             id: "zai/glm-4.5",
             name: "GLM-4.5",
@@ -13701,15 +14622,15 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
                 input: 1.4,
                 output: 4.4,
                 cacheRead: 0.26,
                 cacheWrite: 0,
             },
-            contextWindow: 202752,
-            maxTokens: 202752,
+            contextWindow: 202800,
+            maxTokens: 64000,
         },
         "zai/glm-5v-turbo": {
             id: "zai/glm-5v-turbo",
@@ -14087,6 +15008,23 @@ export const MODELS = {
             contextWindow: 2000000,
             maxTokens: 30000,
         },
+        "grok-4.3": {
+            id: "grok-4.3",
+            name: "Grok 4.3",
+            api: "openai-completions",
+            provider: "xai",
+            baseUrl: "https://api.x.ai/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.25,
+                output: 2.5,
+                cacheRead: 0.2,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 30000,
+        },
         "grok-beta": {
             id: "grok-beta",
             name: "Grok Beta",
@@ -14140,24 +15078,6 @@ export const MODELS = {
         },
     },
     "zai": {
-        "glm-4.5": {
-            id: "glm-4.5",
-            name: "GLM-4.5",
-            api: "openai-completions",
-            provider: "zai",
-            baseUrl: "https://api.z.ai/api/coding/paas/v4",
-            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 98304,
-        },
         "glm-4.5-air": {
             id: "glm-4.5-air",
             name: "GLM-4.5-Air",
@@ -14176,78 +15096,6 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 98304,
         },
-        "glm-4.5-flash": {
-            id: "glm-4.5-flash",
-            name: "GLM-4.5-Flash",
-            api: "openai-completions",
-            provider: "zai",
-            baseUrl: "https://api.z.ai/api/coding/paas/v4",
-            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 98304,
-        },
-        "glm-4.5v": {
-            id: "glm-4.5v",
-            name: "GLM-4.5V",
-            api: "openai-completions",
-            provider: "zai",
-            baseUrl: "https://api.z.ai/api/coding/paas/v4",
-            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 64000,
-            maxTokens: 16384,
-        },
-        "glm-4.6": {
-            id: "glm-4.6",
-            name: "GLM-4.6",
-            api: "openai-completions",
-            provider: "zai",
-            baseUrl: "https://api.z.ai/api/coding/paas/v4",
-            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
-        "glm-4.6v": {
-            id: "glm-4.6v",
-            name: "GLM-4.6V",
-            api: "openai-completions",
-            provider: "zai",
-            baseUrl: "https://api.z.ai/api/coding/paas/v4",
-            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 32768,
-        },
         "glm-4.7": {
             id: "glm-4.7",
             name: "GLM-4.7",
@@ -14266,60 +15114,6 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131072,
         },
-        "glm-4.7-flash": {
-            id: "glm-4.7-flash",
-            name: "GLM-4.7-Flash",
-            api: "openai-completions",
-            provider: "zai",
-            baseUrl: "https://api.z.ai/api/coding/paas/v4",
-            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 131072,
-        },
-        "glm-4.7-flashx": {
-            id: "glm-4.7-flashx",
-            name: "GLM-4.7-FlashX",
-            api: "openai-completions",
-            provider: "zai",
-            baseUrl: "https://api.z.ai/api/coding/paas/v4",
-            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.07,
-                output: 0.4,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 131072,
-        },
-        "glm-5": {
-            id: "glm-5",
-            name: "GLM-5",
-            api: "openai-completions",
-            provider: "zai",
-            baseUrl: "https://api.z.ai/api/coding/paas/v4",
-            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
         "glm-5-turbo": {
             id: "glm-5-turbo",
             name: "GLM-5-Turbo",
@@ -14358,7 +15152,7 @@ export const MODELS = {
         },
         "glm-5v-turbo": {
             id: "glm-5v-turbo",
-            name: "glm-5v-turbo",
+            name: "GLM-5V-Turbo",
             api: "openai-completions",
             provider: "zai",
             baseUrl: "https://api.z.ai/api/coding/paas/v4",