@avadisabelle/ava-pi-ai 0.64.9 → 0.65.2

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 +2522,23 @@ 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,
+        },
         "o1": {
             id: "o1",
             name: "o1",
@@ -3134,6 +3185,24 @@ 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 +3320,7 @@ export const MODELS = {
             cost: {
                 input: 0.3,
                 output: 2.5,
-                cacheRead: 0.075,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -3370,7 +3439,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.31,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -3580,8 +3649,8 @@ 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",
@@ -4079,6 +4148,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
+        "gemini-3.1-pro-preview-customtools": {
+            id: "gemini-3.1-pro-preview-customtools",
+            name: "Gemini 3.1 Pro Preview Custom Tools (Vertex)",
+            api: "google-vertex",
+            provider: "google-vertex",
+            baseUrl: "https://{location}-aiplatform.googleapis.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 12,
+                cacheRead: 0.2,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
     },
     "groq": {
         "deepseek-r1-distill-llama-70b": {
@@ -4605,6 +4691,24 @@ 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",
@@ -4677,6 +4781,24 @@ 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",
@@ -4751,9 +4873,9 @@ export const MODELS = {
         },
     },
     "kimi-coding": {
-        "k2p5": {
-            id: "k2p5",
-            name: "Kimi K2.5",
+        "k2p6": {
+            id: "k2p6",
+            name: "Kimi K2.6",
             api: "anthropic-messages",
             provider: "kimi-coding",
             baseUrl: "https://api.kimi.com/coding",
@@ -4768,14 +4890,14 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
-        "kimi-k2-thinking": {
-            id: "kimi-k2-thinking",
-            name: "Kimi K2 Thinking",
+        "kimi-for-coding": {
+            id: "kimi-for-coding",
+            name: "Kimi For Coding",
             api: "anthropic-messages",
             provider: "kimi-coding",
             baseUrl: "https://api.kimi.com/coding",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 0,
                 output: 0,
@@ -4785,93 +4907,25 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
-    },
-    "minimax": {
-        "MiniMax-M2": {
-            id: "MiniMax-M2",
-            name: "MiniMax-M2",
-            api: "anthropic-messages",
-            provider: "minimax",
-            baseUrl: "https://api.minimax.io/anthropic",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 1.2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
-        "MiniMax-M2.1": {
-            id: "MiniMax-M2.1",
-            name: "MiniMax-M2.1",
-            api: "anthropic-messages",
-            provider: "minimax",
-            baseUrl: "https://api.minimax.io/anthropic",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 1.2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
-        "MiniMax-M2.1-highspeed": {
-            id: "MiniMax-M2.1-highspeed",
-            name: "MiniMax-M2.1-highspeed",
+        "kimi-k2-thinking": {
+            id: "kimi-k2-thinking",
+            name: "Kimi K2 Thinking",
             api: "anthropic-messages",
-            provider: "minimax",
-            baseUrl: "https://api.minimax.io/anthropic",
+            provider: "kimi-coding",
+            baseUrl: "https://api.kimi.com/coding",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.6,
-                output: 2.4,
+                input: 0,
+                output: 0,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
-        "MiniMax-M2.5": {
-            id: "MiniMax-M2.5",
-            name: "MiniMax-M2.5",
-            api: "anthropic-messages",
-            provider: "minimax",
-            baseUrl: "https://api.minimax.io/anthropic",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 1.2,
-                cacheRead: 0.03,
-                cacheWrite: 0.375,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
-        "MiniMax-M2.5-highspeed": {
-            id: "MiniMax-M2.5-highspeed",
-            name: "MiniMax-M2.5-highspeed",
-            api: "anthropic-messages",
-            provider: "minimax",
-            baseUrl: "https://api.minimax.io/anthropic",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.6,
-                output: 2.4,
-                cacheRead: 0.06,
-                cacheWrite: 0.375,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
+            contextWindow: 262144,
+            maxTokens: 32768,
         },
+    },
+    "minimax": {
         "MiniMax-M2.7": {
             id: "MiniMax-M2.7",
             name: "MiniMax-M2.7",
@@ -4908,91 +4962,6 @@ export const MODELS = {
         },
     },
     "minimax-cn": {
-        "MiniMax-M2": {
-            id: "MiniMax-M2",
-            name: "MiniMax-M2",
-            api: "anthropic-messages",
-            provider: "minimax-cn",
-            baseUrl: "https://api.minimaxi.com/anthropic",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 1.2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
-        "MiniMax-M2.1": {
-            id: "MiniMax-M2.1",
-            name: "MiniMax-M2.1",
-            api: "anthropic-messages",
-            provider: "minimax-cn",
-            baseUrl: "https://api.minimaxi.com/anthropic",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 1.2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
-        "MiniMax-M2.1-highspeed": {
-            id: "MiniMax-M2.1-highspeed",
-            name: "MiniMax-M2.1-highspeed",
-            api: "anthropic-messages",
-            provider: "minimax-cn",
-            baseUrl: "https://api.minimaxi.com/anthropic",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.6,
-                output: 2.4,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
-        "MiniMax-M2.5": {
-            id: "MiniMax-M2.5",
-            name: "MiniMax-M2.5",
-            api: "anthropic-messages",
-            provider: "minimax-cn",
-            baseUrl: "https://api.minimaxi.com/anthropic",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 1.2,
-                cacheRead: 0.03,
-                cacheWrite: 0.375,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
-        "MiniMax-M2.5-highspeed": {
-            id: "MiniMax-M2.5-highspeed",
-            name: "MiniMax-M2.5-highspeed",
-            api: "anthropic-messages",
-            provider: "minimax-cn",
-            baseUrl: "https://api.minimaxi.com/anthropic",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.6,
-                output: 2.4,
-                cacheRead: 0.06,
-                cacheWrite: 0.375,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
         "MiniMax-M2.7": {
             id: "MiniMax-M2.7",
             name: "MiniMax-M2.7",
@@ -6017,17 +5986,34 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
-        "o1": {
-            id: "o1",
-            name: "o1",
+        "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: 15,
-                output: 60,
+                input: 5,
+                output: 30,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
+        "o1": {
+            id: "o1",
+            name: "o1",
+            api: "openai-responses",
+            provider: "openai",
+            baseUrl: "https://api.openai.com/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 15,
+                output: 60,
                 cacheRead: 7.5,
                 cacheWrite: 0,
             },
@@ -6327,23 +6313,6 @@ 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",
@@ -6786,6 +6755,57 @@ 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",
@@ -6803,6 +6823,40 @@ 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,
+        },
+        "ling-2.6-flash-free": {
+            id: "ling-2.6-flash-free",
+            name: "Ling 2.6 Flash Free",
+            api: "openai-completions",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262100,
+            maxTokens: 32800,
+        },
         "minimax-m2.5": {
             id: "minimax-m2.5",
             name: "MiniMax M2.5",
@@ -6837,6 +6891,23 @@ 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",
@@ -6857,9 +6928,9 @@ 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: {
@@ -6874,9 +6945,9 @@ 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: {
@@ -6890,6 +6961,40 @@ export const MODELS = {
         },
     },
     "opencode-go": {
+        "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",
@@ -6941,6 +7046,23 @@ 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",
@@ -6956,7 +7078,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 64000,
+            maxTokens: 128000,
         },
         "mimo-v2-pro": {
             id: "mimo-v2-pro",
@@ -6973,7 +7095,41 @@ 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",
@@ -7012,9 +7168,9 @@ 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: {
@@ -7029,9 +7185,9 @@ 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: {
@@ -7094,7 +7250,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 65536,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "amazon/nova-2-lite-v1": {
             id: "amazon/nova-2-lite-v1",
@@ -7419,17 +7575,17 @@ 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,
             },
@@ -7655,7 +7811,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 163840,
+            maxTokens: 16384,
         },
         "deepseek/deepseek-chat-v3-0324": {
             id: "deepseek/deepseek-chat-v3-0324",
@@ -7672,7 +7828,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "deepseek/deepseek-chat-v3.1": {
             id: "deepseek/deepseek-chat-v3.1",
@@ -7723,7 +7879,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 4096,
+            maxTokens: 32768,
         },
         "deepseek/deepseek-v3.1-terminus": {
             id: "deepseek/deepseek-v3.1-terminus",
@@ -7736,11 +7892,11 @@ export const MODELS = {
             cost: {
                 input: 0.21,
                 output: 0.7899999999999999,
-                cacheRead: 0.1300000002,
+                cacheRead: 0.13,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 4096,
+            maxTokens: 32768,
         },
         "deepseek/deepseek-v3.2": {
             id: "deepseek/deepseek-v3.2",
@@ -7751,13 +7907,13 @@ 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",
@@ -7776,6 +7932,40 @@ 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",
@@ -7997,20 +8187,54 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "google/gemma-4-26b-a4b-it": {
-            id: "google/gemma-4-26b-a4b-it",
-            name: "Google: Gemma 4 26B A4B ",
+        "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: true,
+            reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.08,
-                output: 0.35,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
+                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 ",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.06,
+                output: 0.33,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
             contextWindow: 262144,
             maxTokens: 4096,
         },
@@ -8042,11 +8266,11 @@ 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",
@@ -8082,6 +8306,40 @@ 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:free": {
+            id: "inclusionai/ling-2.6-flash:free",
+            name: "inclusionAI: Ling-2.6-flash (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,
+        },
         "kwaipilot/kat-coder-pro-v2": {
             id: "kwaipilot/kat-coder-pro-v2",
             name: "Kwaipilot: KAT-Coder-Pro V2",
@@ -8131,7 +8389,7 @@ 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",
@@ -8159,13 +8417,13 @@ 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",
@@ -8261,13 +8519,13 @@ 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",
@@ -8590,7 +8848,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "mistralai/mistral-small-creative": {
             id: "mistralai/mistral-small-creative",
@@ -8745,6 +9003,23 @@ 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: 0.7448,
+                output: 4.655,
+                cacheRead: 0.1463,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 65536,
+        },
         "nex-agi/deepseek-v3.1-nex-n1": {
             id: "nex-agi/deepseek-v3.1-nex-n1",
             name: "Nex AGI: DeepSeek V3.1 Nex N1",
@@ -8794,7 +9069,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "nvidia/nemotron-3-nano-30b-a3b": {
             id: "nvidia/nemotron-3-nano-30b-a3b",
@@ -8811,7 +9086,7 @@ 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",
@@ -8896,7 +9171,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "nvidia/nemotron-nano-9b-v2:free": {
             id: "nvidia/nemotron-nano-9b-v2:free",
@@ -9255,40 +9530,6 @@ 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",
@@ -9595,6 +9836,40 @@ 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",
@@ -9644,7 +9919,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 4096,
+            maxTokens: 131072,
         },
         "openai/gpt-oss-120b:free": {
             id: "openai/gpt-oss-120b:free",
@@ -9678,7 +9953,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 4096,
+            maxTokens: 131072,
         },
         "openai/gpt-oss-20b:free": {
             id: "openai/gpt-oss-20b:free",
@@ -9884,23 +10159,6 @@ export const MODELS = {
             contextWindow: 2000000,
             maxTokens: 4096,
         },
-        "openrouter/elephant-alpha": {
-            id: "openrouter/elephant-alpha",
-            name: "Elephant",
-            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,
-        },
         "openrouter/free": {
             id: "openrouter/free",
             name: "Free Models Router",
@@ -9944,8 +10202,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.12,
-                output: 0.39,
+                input: 0.36,
+                output: 0.39999999999999997,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -10120,7 +10378,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "qwen/qwen3-235b-a22b-thinking-2507": {
             id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -10131,13 +10389,13 @@ 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",
@@ -10154,7 +10412,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 40960,
-            maxTokens: 40960,
+            maxTokens: 16384,
         },
         "qwen/qwen3-30b-a3b-instruct-2507": {
             id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -10234,12 +10492,12 @@ 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",
@@ -10284,9 +10542,9 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.15,
+                input: 0.14,
                 output: 0.7999999999999999,
-                cacheRead: 0.12,
+                cacheRead: 0.09,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -10375,7 +10633,7 @@ 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",
@@ -10426,7 +10684,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "qwen/qwen3-vl-235b-a22b-thinking": {
             id: "qwen/qwen3-vl-235b-a22b-thinking",
@@ -10649,6 +10907,74 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 65536,
         },
+        "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: 0.39999999999999997,
+                output: 2.4,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 65536,
+        },
+        "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", "image"],
+            cost: {
+                input: 0.5,
+                output: 2,
+                cacheRead: 0.25,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 65536,
+        },
+        "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: 1.3,
+                output: 7.8,
+                cacheRead: 0,
+                cacheWrite: 1.625,
+            },
+            contextWindow: 262144,
+            maxTokens: 65536,
+        },
         "qwen/qwen3.6-plus": {
             id: "qwen/qwen3.6-plus",
             name: "Qwen: Qwen3.6 Plus",
@@ -10768,6 +11094,23 @@ 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",
@@ -11040,6 +11383,40 @@ 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 ",
@@ -11153,11 +11530,11 @@ 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",
@@ -11168,13 +11545,13 @@ 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",
@@ -11187,11 +11564,11 @@ 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",
@@ -11207,8 +11584,8 @@ 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",
@@ -11236,30 +11613,166 @@ 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,
             maxTokens: 65535,
         },
-        "z-ai/glm-5v-turbo": {
-            id: "z-ai/glm-5v-turbo",
-            name: "Z.ai: GLM 5V Turbo",
+        "z-ai/glm-5v-turbo": {
+            id: "z-ai/glm-5v-turbo",
+            name: "Z.ai: GLM 5V Turbo",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.2,
+                output: 4,
+                cacheRead: 0.24,
+                cacheWrite: 0,
+            },
+            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: 0.7448,
+                output: 4.655,
+                cacheRead: 0.1463,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 65536,
+        },
+        "~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: 1.2,
-                output: 4,
-                cacheRead: 0.24,
+                input: 0.75,
+                output: 4.5,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
-            contextWindow: 202752,
-            maxTokens: 131072,
+            contextWindow: 400000,
+            maxTokens: 128000,
         },
     },
     "vercel-ai-gateway": {
@@ -11331,6 +11844,23 @@ 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",
@@ -11530,7 +12060,7 @@ export const MODELS = {
                 input: 0.5,
                 output: 3,
                 cacheRead: 0.09999999999999999,
-                cacheWrite: 0,
+                cacheWrite: 0.625,
             },
             contextWindow: 1000000,
             maxTokens: 64000,
@@ -11909,6 +12439,40 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 64000,
         },
+        "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: 0.028,
+                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: 0.435,
+                output: 0.87,
+                cacheRead: 0.0036,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
         "google/gemini-2.0-flash": {
             id: "google/gemini-2.0-flash",
             name: "Gemini 2.0 Flash",
@@ -12674,6 +13238,23 @@ 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",
@@ -13167,6 +13748,40 @@ 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",
@@ -13635,9 +14250,9 @@ 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,
@@ -13854,15 +14469,15 @@ 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",
@@ -14293,24 +14908,6 @@ 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: 0.6,
-                output: 2.2,
-                cacheRead: 0.11,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 98304,
-        },
         "glm-4.5-air": {
             id: "glm-4.5-air",
             name: "GLM-4.5-Air",
@@ -14320,24 +14917,6 @@ export const MODELS = {
             compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
             reasoning: true,
             input: ["text"],
-            cost: {
-                input: 0.2,
-                output: 1.1,
-                cacheRead: 0.03,
-                cacheWrite: 0,
-            },
-            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,
@@ -14347,85 +14926,13 @@ export const MODELS = {
             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: 0.6,
-                output: 1.8,
-                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" },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.6,
-                output: 2.2,
-                cacheRead: 0.11,
-                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" },
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.3,
-                output: 0.9,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 32768,
-        },
         "glm-4.7": {
             id: "glm-4.7",
             name: "GLM-4.7",
             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: 0.6,
-                output: 2.2,
-                cacheRead: 0.11,
-                cacheWrite: 0,
-            },
-            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" },
+            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -14434,42 +14941,6 @@ export const MODELS = {
                 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" },
-            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" },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 1,
-                output: 3.2,
-                cacheRead: 0.2,
-                cacheWrite: 0,
-            },
             contextWindow: 204800,
             maxTokens: 131072,
         },
@@ -14479,13 +14950,13 @@ export const MODELS = {
             api: "openai-completions",
             provider: "zai",
             baseUrl: "https://api.z.ai/api/coding/paas/v4",
-            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
+            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.2,
-                output: 4,
-                cacheRead: 0.24,
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 200000,
@@ -14497,31 +14968,13 @@ export const MODELS = {
             api: "openai-completions",
             provider: "zai",
             baseUrl: "https://api.z.ai/api/coding/paas/v4",
-            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai" },
+            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.4,
-                output: 4.4,
-                cacheRead: 0.26,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 131072,
-        },
-        "glm-5v-turbo": {
-            id: "glm-5v-turbo",
-            name: "glm-5v-turbo",
-            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: 1.2,
-                output: 4,
-                cacheRead: 0.24,
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 200000,