@draht/ai 2026.3.25 → 2026.4.23

package/dist/models.generated.js

@@ -257,6 +257,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "anthropic.claude-opus-4-7": {
+            id: "anthropic.claude-opus-4-7",
+            name: "Claude Opus 4.7",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "anthropic.claude-sonnet-4-20250514-v1:0": {
             id: "anthropic.claude-sonnet-4-20250514-v1:0",
             name: "Claude Sonnet 4",
@@ -410,6 +427,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "eu.anthropic.claude-opus-4-7": {
+            id: "eu.anthropic.claude-opus-4-7",
+            name: "Claude Opus 4.7 (EU)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "eu.anthropic.claude-sonnet-4-20250514-v1:0": {
             id: "eu.anthropic.claude-sonnet-4-20250514-v1:0",
             name: "Claude Sonnet 4 (EU)",
@@ -512,6 +546,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "global.anthropic.claude-opus-4-7": {
+            id: "global.anthropic.claude-opus-4-7",
+            name: "Claude Opus 4.7 (Global)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "global.anthropic.claude-sonnet-4-20250514-v1:0": {
             id: "global.anthropic.claude-sonnet-4-20250514-v1:0",
             name: "Claude Sonnet 4 (Global)",
@@ -815,8 +866,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 131072,
+            contextWindow: 196608,
+            maxTokens: 98304,
         },
         "mistral.devstral-2-123b": {
             id: "mistral.devstral-2-123b",
@@ -1056,6 +1107,23 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 4096,
         },
+        "nvidia.nemotron-super-3-120b": {
+            id: "nvidia.nemotron-super-3-120b",
+            name: "NVIDIA Nemotron 3 Super 120B A12B",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.15,
+                output: 0.65,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 131072,
+        },
         "openai.gpt-oss-120b-1:0": {
             id: "openai.gpt-oss-120b-1:0",
             name: "gpt-oss-120b",
@@ -1192,6 +1260,23 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 65536,
         },
+        "qwen.qwen3-coder-next": {
+            id: "qwen.qwen3-coder-next",
+            name: "Qwen3 Coder Next",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.22,
+                output: 1.8,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 65536,
+        },
         "qwen.qwen3-next-80b-a3b": {
             id: "qwen.qwen3-next-80b-a3b",
             name: "Qwen/Qwen3-Next-80B-A3B-Instruct",
@@ -1311,6 +1396,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "us.anthropic.claude-opus-4-7": {
+            id: "us.anthropic.claude-opus-4-7",
+            name: "Claude Opus 4.7 (US)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "us.anthropic.claude-sonnet-4-20250514-v1:0": {
             id: "us.anthropic.claude-sonnet-4-20250514-v1:0",
             name: "Claude Sonnet 4 (US)",
@@ -1444,8 +1546,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 200000,
-            maxTokens: 131072,
+            contextWindow: 202752,
+            maxTokens: 101376,
         },
     },
     "anthropic": {
@@ -1534,23 +1636,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 64000,
         },
-        "claude-3-7-sonnet-latest": {
-            id: "claude-3-7-sonnet-latest",
-            name: "Claude Sonnet 3.7 (latest)",
-            api: "anthropic-messages",
-            provider: "anthropic",
-            baseUrl: "https://api.anthropic.com",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 64000,
-        },
         "claude-3-haiku-20240307": {
             id: "claude-3-haiku-20240307",
             name: "Claude Haiku 3",
@@ -1755,6 +1840,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "claude-opus-4-7": {
+            id: "claude-opus-4-7",
+            name: "Claude Opus 4.7",
+            api: "anthropic-messages",
+            provider: "anthropic",
+            baseUrl: "https://api.anthropic.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "claude-sonnet-4-0": {
             id: "claude-sonnet-4-0",
             name: "Claude Sonnet 4 (latest)",
@@ -1842,23 +1944,6 @@ export const MODELS = {
         },
     },
     "azure-openai-responses": {
-        "codex-mini-latest": {
-            id: "codex-mini-latest",
-            name: "Codex Mini",
-            api: "azure-openai-responses",
-            provider: "azure-openai-responses",
-            baseUrl: "",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 1.5,
-                output: 6,
-                cacheRead: 0.375,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 100000,
-        },
         "gpt-4": {
             id: "gpt-4",
             name: "GPT-4",
@@ -2284,6 +2369,23 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
+        "gpt-5.3-chat-latest": {
+            id: "gpt-5.3-chat-latest",
+            name: "GPT-5.3 Chat (latest)",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 1.75,
+                output: 14,
+                cacheRead: 0.175,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
         "gpt-5.3-codex": {
             id: "gpt-5.3-codex",
             name: "GPT-5.3 Codex",
@@ -2648,6 +2750,24 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "claude-opus-4.7": {
+            id: "claude-opus-4.7",
+            name: "Claude Opus 4.7",
+            api: "anthropic-messages",
+            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: 144000,
+            maxTokens: 64000,
+        },
         "claude-sonnet-4": {
             id: "claude-sonnet-4",
             name: "Claude Sonnet 4",
@@ -2998,7 +3118,7 @@ export const MODELS = {
         },
         "gpt-5.4-mini": {
             id: "gpt-5.4-mini",
-            name: "GPT-5.4 mini",
+            name: "GPT-5.4 Mini",
             api: "openai-responses",
             provider: "github-copilot",
             baseUrl: "https://api.individual.githubcopilot.com",
@@ -3131,7 +3251,7 @@ export const MODELS = {
             cost: {
                 input: 0.3,
                 output: 2.5,
-                cacheRead: 0.075,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -3250,7 +3370,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.31,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -3443,6 +3563,57 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 65536,
         },
+        "gemma-3-27b-it": {
+            id: "gemma-3-27b-it",
+            name: "Gemma 3 27B",
+            api: "google-generative-ai",
+            provider: "google",
+            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 8192,
+        },
+        "gemma-4-26b-a4b-it": {
+            id: "gemma-4-26b-a4b-it",
+            name: "Gemma 4 26B",
+            api: "google-generative-ai",
+            provider: "google",
+            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 8192,
+        },
+        "gemma-4-31b-it": {
+            id: "gemma-4-31b-it",
+            name: "Gemma 4 31B",
+            api: "google-generative-ai",
+            provider: "google",
+            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 8192,
+        },
     },
     "google-antigravity": {
         "claude-opus-4-5-thinking": {
@@ -3908,6 +4079,23 @@ 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": {
@@ -3944,6 +4132,40 @@ export const MODELS = {
             contextWindow: 8192,
             maxTokens: 8192,
         },
+        "groq/compound": {
+            id: "groq/compound",
+            name: "Compound",
+            api: "openai-completions",
+            provider: "groq",
+            baseUrl: "https://api.groq.com/openai/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 8192,
+        },
+        "groq/compound-mini": {
+            id: "groq/compound-mini",
+            name: "Compound Mini",
+            api: "openai-completions",
+            provider: "groq",
+            baseUrl: "https://api.groq.com/openai/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 8192,
+        },
         "llama-3.1-8b-instant": {
             id: "llama-3.1-8b-instant",
             name: "Llama 3.1 8B Instant",
@@ -4131,9 +4353,26 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 65536,
         },
-        "qwen-qwq-32b": {
-            id: "qwen-qwq-32b",
-            name: "Qwen QwQ 32B",
+        "openai/gpt-oss-safeguard-20b": {
+            id: "openai/gpt-oss-safeguard-20b",
+            name: "Safety GPT OSS 20B",
+            api: "openai-completions",
+            provider: "groq",
+            baseUrl: "https://api.groq.com/openai/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.075,
+                output: 0.3,
+                cacheRead: 0.037,
+                cacheWrite: 0,
+            },
+            contextWindow: 131072,
+            maxTokens: 65536,
+        },
+        "qwen-qwq-32b": {
+            id: "qwen-qwq-32b",
+            name: "Qwen QwQ 32B",
             api: "openai-completions",
             provider: "groq",
             baseUrl: "https://api.groq.com/openai/v1",
@@ -4163,7 +4402,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 16384,
+            maxTokens: 40960,
         },
     },
     "huggingface": {
@@ -4203,6 +4442,24 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131072,
         },
+        "MiniMaxAI/MiniMax-M2.7": {
+            id: "MiniMaxAI/MiniMax-M2.7",
+            name: "MiniMax-M2.7",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
+                cacheWrite: 0,
+            },
+            contextWindow: 204800,
+            maxTokens: 131072,
+        },
         "Qwen/Qwen3-235B-A22B-Thinking-2507": {
             id: "Qwen/Qwen3-235B-A22B-Thinking-2507",
             name: "Qwen3-235B-A22B-Thinking-2507",
@@ -4437,6 +4694,24 @@ 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",
@@ -4491,6 +4766,24 @@ export const MODELS = {
             contextWindow: 202752,
             maxTokens: 131072,
         },
+        "zai-org/GLM-5.1": {
+            id: "zai-org/GLM-5.1",
+            name: "GLM-5.1",
+            api: "openai-completions",
+            provider: "huggingface",
+            baseUrl: "https://router.huggingface.co/v1",
+            compat: { "supportsDeveloperRole": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1,
+                output: 3.2,
+                cacheRead: 0.2,
+                cacheWrite: 0,
+            },
+            contextWindow: 202752,
+            maxTokens: 131072,
+        },
     },
     "kimi-coding": {
         "k2p5": {
@@ -4510,14 +4803,14 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
-        "kimi-k2-thinking": {
-            id: "kimi-k2-thinking",
-            name: "Kimi K2 Thinking",
+        "k2p6": {
+            id: "k2p6",
+            name: "Kimi K2.6",
             api: "anthropic-messages",
             provider: "kimi-coding",
             baseUrl: "https://api.kimi.com/coding",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 0,
                 output: 0,
@@ -4527,93 +4820,25 @@ 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",
@@ -4650,91 +4875,6 @@ 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",
@@ -4774,9 +4914,9 @@ export const MODELS = {
         "codestral-latest": {
             id: "codestral-latest",
             name: "Codestral (latest)",
-            api: "mistral-conversations",
+            api: "openai-completions",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai",
+            baseUrl: "https://api.mistral.ai/v1",
             reasoning: false,
             input: ["text"],
             cost: {
@@ -4791,9 +4931,9 @@ export const MODELS = {
         "devstral-2512": {
             id: "devstral-2512",
             name: "Devstral 2",
-            api: "mistral-conversations",
+            api: "openai-completions",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai",
+            baseUrl: "https://api.mistral.ai/v1",
             reasoning: false,
             input: ["text"],
             cost: {
@@ -4808,9 +4948,9 @@ export const MODELS = {
         "devstral-medium-2507": {
             id: "devstral-medium-2507",
             name: "Devstral Medium",
-            api: "mistral-conversations",
+            api: "openai-completions",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai",
+            baseUrl: "https://api.mistral.ai/v1",
             reasoning: false,
             input: ["text"],
             cost: {
@@ -4825,9 +4965,9 @@ export const MODELS = {
         "devstral-medium-latest": {
             id: "devstral-medium-latest",
             name: "Devstral 2 (latest)",
-            api: "mistral-conversations",
+            api: "openai-completions",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai",
+            baseUrl: "https://api.mistral.ai/v1",
             reasoning: false,
             input: ["text"],
             cost: {
@@ -4842,9 +4982,9 @@ export const MODELS = {
         "devstral-small-2505": {
             id: "devstral-small-2505",
             name: "Devstral Small 2505",
-            api: "mistral-conversations",
+            api: "openai-completions",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai",
+            baseUrl: "https://api.mistral.ai/v1",
             reasoning: false,
             input: ["text"],
             cost: {
@@ -4859,9 +4999,9 @@ export const MODELS = {
         "devstral-small-2507": {
             id: "devstral-small-2507",
             name: "Devstral Small",
-            api: "mistral-conversations",
+            api: "openai-completions",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai",
+            baseUrl: "https://api.mistral.ai/v1",
             reasoning: false,
             input: ["text"],
             cost: {
@@ -4876,9 +5016,9 @@ export const MODELS = {
         "labs-devstral-small-2512": {
             id: "labs-devstral-small-2512",
             name: "Devstral Small 2",
-            api: "mistral-conversations",
+            api: "openai-completions",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai",
+            baseUrl: "https://api.mistral.ai/v1",
             reasoning: false,
             input: ["text", "image"],
             cost: {
@@ -4893,9 +5033,9 @@ export const MODELS = {
         "magistral-medium-latest": {
             id: "magistral-medium-latest",
             name: "Magistral Medium (latest)",
-            api: "mistral-conversations",
+            api: "openai-completions",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai",
+            baseUrl: "https://api.mistral.ai/v1",
             reasoning: true,
             input: ["text"],
             cost: {
@@ -4910,9 +5050,9 @@ export const MODELS = {
         "magistral-small": {
             id: "magistral-small",
             name: "Magistral Small",
-            api: "mistral-conversations",
+            api: "openai-completions",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai",
+            baseUrl: "https://api.mistral.ai/v1",
             reasoning: true,
             input: ["text"],
             cost: {
@@ -4927,9 +5067,9 @@ export const MODELS = {
         "ministral-3b-latest": {
             id: "ministral-3b-latest",
             name: "Ministral 3B (latest)",
-            api: "mistral-conversations",
+            api: "openai-completions",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai",
+            baseUrl: "https://api.mistral.ai/v1",
             reasoning: false,
             input: ["text"],
             cost: {
@@ -4944,9 +5084,9 @@ export const MODELS = {
         "ministral-8b-latest": {
             id: "ministral-8b-latest",
             name: "Ministral 8B (latest)",
-            api: "mistral-conversations",
+            api: "openai-completions",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai",
+            baseUrl: "https://api.mistral.ai/v1",
             reasoning: false,
             input: ["text"],
             cost: {
@@ -4961,9 +5101,9 @@ export const MODELS = {
         "mistral-large-2411": {
             id: "mistral-large-2411",
             name: "Mistral Large 2.1",
-            api: "mistral-conversations",
+            api: "openai-completions",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai",
+            baseUrl: "https://api.mistral.ai/v1",
             reasoning: false,
             input: ["text"],
             cost: {
@@ -4978,9 +5118,9 @@ export const MODELS = {
         "mistral-large-2512": {
             id: "mistral-large-2512",
             name: "Mistral Large 3",
-            api: "mistral-conversations",
+            api: "openai-completions",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai",
+            baseUrl: "https://api.mistral.ai/v1",
             reasoning: false,
             input: ["text", "image"],
             cost: {
@@ -4995,9 +5135,9 @@ export const MODELS = {
         "mistral-large-latest": {
             id: "mistral-large-latest",
             name: "Mistral Large (latest)",
-            api: "mistral-conversations",
+            api: "openai-completions",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai",
+            baseUrl: "https://api.mistral.ai/v1",
             reasoning: false,
             input: ["text", "image"],
             cost: {
@@ -5012,9 +5152,9 @@ export const MODELS = {
         "mistral-medium-2505": {
             id: "mistral-medium-2505",
             name: "Mistral Medium 3",
-            api: "mistral-conversations",
+            api: "openai-completions",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai",
+            baseUrl: "https://api.mistral.ai/v1",
             reasoning: false,
             input: ["text", "image"],
             cost: {
@@ -5029,9 +5169,9 @@ export const MODELS = {
         "mistral-medium-2508": {
             id: "mistral-medium-2508",
             name: "Mistral Medium 3.1",
-            api: "mistral-conversations",
+            api: "openai-completions",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai",
+            baseUrl: "https://api.mistral.ai/v1",
             reasoning: false,
             input: ["text", "image"],
             cost: {
@@ -5046,9 +5186,9 @@ export const MODELS = {
         "mistral-medium-latest": {
             id: "mistral-medium-latest",
             name: "Mistral Medium (latest)",
-            api: "mistral-conversations",
+            api: "openai-completions",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai",
+            baseUrl: "https://api.mistral.ai/v1",
             reasoning: false,
             input: ["text", "image"],
             cost: {
@@ -5063,9 +5203,9 @@ export const MODELS = {
         "mistral-nemo": {
             id: "mistral-nemo",
             name: "Mistral Nemo",
-            api: "mistral-conversations",
+            api: "openai-completions",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai",
+            baseUrl: "https://api.mistral.ai/v1",
             reasoning: false,
             input: ["text"],
             cost: {
@@ -5080,9 +5220,9 @@ export const MODELS = {
         "mistral-small-2506": {
             id: "mistral-small-2506",
             name: "Mistral Small 3.2",
-            api: "mistral-conversations",
+            api: "openai-completions",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai",
+            baseUrl: "https://api.mistral.ai/v1",
             reasoning: false,
             input: ["text", "image"],
             cost: {
@@ -5094,29 +5234,46 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 16384,
         },
+        "mistral-small-2603": {
+            id: "mistral-small-2603",
+            name: "Mistral Small 4",
+            api: "openai-completions",
+            provider: "mistral",
+            baseUrl: "https://api.mistral.ai/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
         "mistral-small-latest": {
             id: "mistral-small-latest",
             name: "Mistral Small (latest)",
-            api: "mistral-conversations",
+            api: "openai-completions",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai",
-            reasoning: false,
+            baseUrl: "https://api.mistral.ai/v1",
+            reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.1,
-                output: 0.3,
+                input: 0.15,
+                output: 0.6,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 16384,
+            contextWindow: 256000,
+            maxTokens: 256000,
         },
         "open-mistral-7b": {
             id: "open-mistral-7b",
             name: "Mistral 7B",
-            api: "mistral-conversations",
+            api: "openai-completions",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai",
+            baseUrl: "https://api.mistral.ai/v1",
             reasoning: false,
             input: ["text"],
             cost: {
@@ -5131,9 +5288,9 @@ export const MODELS = {
         "open-mixtral-8x22b": {
             id: "open-mixtral-8x22b",
             name: "Mixtral 8x22B",
-            api: "mistral-conversations",
+            api: "openai-completions",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai",
+            baseUrl: "https://api.mistral.ai/v1",
             reasoning: false,
             input: ["text"],
             cost: {
@@ -5148,9 +5305,9 @@ export const MODELS = {
         "open-mixtral-8x7b": {
             id: "open-mixtral-8x7b",
             name: "Mixtral 8x7B",
-            api: "mistral-conversations",
+            api: "openai-completions",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai",
+            baseUrl: "https://api.mistral.ai/v1",
             reasoning: false,
             input: ["text"],
             cost: {
@@ -5165,9 +5322,9 @@ export const MODELS = {
         "pixtral-12b": {
             id: "pixtral-12b",
             name: "Pixtral 12B",
-            api: "mistral-conversations",
+            api: "openai-completions",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai",
+            baseUrl: "https://api.mistral.ai/v1",
             reasoning: false,
             input: ["text", "image"],
             cost: {
@@ -5182,9 +5339,9 @@ export const MODELS = {
         "pixtral-large-latest": {
             id: "pixtral-large-latest",
             name: "Pixtral Large (latest)",
-            api: "mistral-conversations",
+            api: "openai-completions",
             provider: "mistral",
-            baseUrl: "https://api.mistral.ai",
+            baseUrl: "https://api.mistral.ai/v1",
             reasoning: false,
             input: ["text", "image"],
             cost: {
@@ -5198,23 +5355,6 @@ export const MODELS = {
         },
     },
     "openai": {
-        "codex-mini-latest": {
-            id: "codex-mini-latest",
-            name: "Codex Mini",
-            api: "openai-responses",
-            provider: "openai",
-            baseUrl: "https://api.openai.com/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 1.5,
-                output: 6,
-                cacheRead: 0.375,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 100000,
-        },
         "gpt-4": {
             id: "gpt-4",
             name: "GPT-4",
@@ -5640,6 +5780,23 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
+        "gpt-5.3-chat-latest": {
+            id: "gpt-5.3-chat-latest",
+            name: "GPT-5.3 Chat (latest)",
+            api: "openai-responses",
+            provider: "openai",
+            baseUrl: "https://api.openai.com/v1",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 1.75,
+                output: 14,
+                cacheRead: 0.175,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
         "gpt-5.3-codex": {
             id: "gpt-5.3-codex",
             name: "GPT-5.3 Codex",
@@ -6137,6 +6294,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "claude-opus-4-7": {
+            id: "claude-opus-4-7",
+            name: "Claude Opus 4.7",
+            api: "anthropic-messages",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "claude-sonnet-4": {
             id: "claude-sonnet-4",
             name: "Claude Sonnet 4",
@@ -6239,6 +6413,23 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131072,
         },
+        "glm-5.1": {
+            id: "glm-5.1",
+            name: "GLM-5.1",
+            api: "openai-completions",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.4,
+                output: 4.4,
+                cacheRead: 0.26,
+                cacheWrite: 0,
+            },
+            contextWindow: 204800,
+            maxTokens: 131072,
+        },
         "gpt-5": {
             id: "gpt-5",
             name: "GPT-5",
@@ -6477,6 +6668,23 @@ export const MODELS = {
             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",
@@ -6494,30 +6702,30 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
-        "mimo-v2-omni-free": {
-            id: "mimo-v2-omni-free",
-            name: "MiMo V2 Omni Free",
+        "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,
-                output: 0,
-                cacheRead: 0,
+                input: 0.95,
+                output: 4,
+                cacheRead: 0.16,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 64000,
+            maxTokens: 65536,
         },
-        "mimo-v2-pro-free": {
-            id: "mimo-v2-pro-free",
-            name: "MiMo V2 Pro Free",
+        "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: true,
+            reasoning: false,
             input: ["text"],
             cost: {
                 input: 0,
@@ -6525,8 +6733,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 1048576,
-            maxTokens: 64000,
+            contextWindow: 262100,
+            maxTokens: 32800,
         },
         "minimax-m2.5": {
             id: "minimax-m2.5",
@@ -6562,6 +6770,23 @@ 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",
@@ -6576,9 +6801,43 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
+            contextWindow: 204800,
             maxTokens: 128000,
         },
+        "qwen3.5-plus": {
+            id: "qwen3.5-plus",
+            name: "Qwen3.5 Plus",
+            api: "anthropic-messages",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.2,
+                output: 1.2,
+                cacheRead: 0.02,
+                cacheWrite: 0.25,
+            },
+            contextWindow: 262144,
+            maxTokens: 65536,
+        },
+        "qwen3.6-plus": {
+            id: "qwen3.6-plus",
+            name: "Qwen3.6 Plus",
+            api: "anthropic-messages",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.5,
+                output: 3,
+                cacheRead: 0.05,
+                cacheWrite: 0.625,
+            },
+            contextWindow: 262144,
+            maxTokens: 65536,
+        },
     },
     "opencode-go": {
         "glm-5": {
@@ -6598,6 +6857,23 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131072,
         },
+        "glm-5.1": {
+            id: "glm-5.1",
+            name: "GLM-5.1",
+            api: "openai-completions",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.4,
+                output: 4.4,
+                cacheRead: 0.26,
+                cacheWrite: 0,
+            },
+            contextWindow: 204800,
+            maxTokens: 131072,
+        },
         "kimi-k2.5": {
             id: "kimi-k2.5",
             name: "Kimi K2.5",
@@ -6615,12 +6891,97 @@ 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",
+            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: 262144,
+            maxTokens: 128000,
+        },
+        "mimo-v2-pro": {
+            id: "mimo-v2-pro",
+            name: "MiMo V2 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,
+        },
+        "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: 262144,
+            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",
             name: "MiniMax M2.5",
-            api: "anthropic-messages",
+            api: "openai-completions",
             provider: "opencode-go",
-            baseUrl: "https://opencode.ai/zen/go",
+            baseUrl: "https://opencode.ai/zen/go/v1",
             reasoning: true,
             input: ["text"],
             cost: {
@@ -6630,7 +6991,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 204800,
-            maxTokens: 131072,
+            maxTokens: 65536,
         },
         "minimax-m2.7": {
             id: "minimax-m2.7",
@@ -6649,6 +7010,40 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131072,
         },
+        "qwen3.5-plus": {
+            id: "qwen3.5-plus",
+            name: "Qwen3.5 Plus",
+            api: "anthropic-messages",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.2,
+                output: 1.2,
+                cacheRead: 0.02,
+                cacheWrite: 0.25,
+            },
+            contextWindow: 262144,
+            maxTokens: 65536,
+        },
+        "qwen3.6-plus": {
+            id: "qwen3.6-plus",
+            name: "Qwen3.6 Plus",
+            api: "anthropic-messages",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.5,
+                output: 3,
+                cacheRead: 0.05,
+                cacheWrite: 0.625,
+            },
+            contextWindow: 262144,
+            maxTokens: 65536,
+        },
     },
     "openrouter": {
         "ai21/jamba-large-1.7": {
@@ -6821,23 +7216,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 8192,
         },
-        "anthropic/claude-3.5-sonnet": {
-            id: "anthropic/claude-3.5-sonnet",
-            name: "Anthropic: Claude 3.5 Sonnet",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 6,
-                output: 30,
-                cacheRead: 0.6,
-                cacheWrite: 7.5,
-            },
-            contextWindow: 200000,
-            maxTokens: 8192,
-        },
         "anthropic/claude-3.7-sonnet": {
             id: "anthropic/claude-3.7-sonnet",
             name: "Anthropic: Claude 3.7 Sonnet",
@@ -6853,7 +7231,7 @@ export const MODELS = {
                 cacheWrite: 3.75,
             },
             contextWindow: 200000,
-            maxTokens: 64000,
+            maxTokens: 128000,
         },
         "anthropic/claude-3.7-sonnet:thinking": {
             id: "anthropic/claude-3.7-sonnet:thinking",
@@ -6957,6 +7335,40 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "anthropic/claude-opus-4.6-fast": {
+            id: "anthropic/claude-opus-4.6-fast",
+            name: "Anthropic: Claude Opus 4.6 (Fast)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 30,
+                output: 150,
+                cacheRead: 3,
+                cacheWrite: 37.5,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
+        "anthropic/claude-opus-4.7": {
+            id: "anthropic/claude-opus-4.7",
+            name: "Anthropic: Claude Opus 4.7",
+            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-4": {
             id: "anthropic/claude-sonnet-4",
             name: "Anthropic: Claude Sonnet 4",
@@ -6971,7 +7383,7 @@ export const MODELS = {
                 cacheRead: 0.3,
                 cacheWrite: 3.75,
             },
-            contextWindow: 200000,
+            contextWindow: 1000000,
             maxTokens: 64000,
         },
         "anthropic/claude-sonnet-4.5": {
@@ -7008,56 +7420,56 @@ 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,
             },
             contextWindow: 131000,
             maxTokens: 4096,
         },
-        "arcee-ai/trinity-mini": {
-            id: "arcee-ai/trinity-mini",
-            name: "Arcee AI: Trinity Mini",
+        "arcee-ai/trinity-large-thinking": {
+            id: "arcee-ai/trinity-large-thinking",
+            name: "Arcee AI: Trinity Large Thinking",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.045,
-                output: 0.15,
-                cacheRead: 0,
+                input: 0.22,
+                output: 0.85,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 131072,
+            contextWindow: 262144,
+            maxTokens: 262144,
         },
-        "arcee-ai/trinity-mini:free": {
-            id: "arcee-ai/trinity-mini:free",
-            name: "Arcee AI: Trinity Mini (free)",
+        "arcee-ai/trinity-mini": {
+            id: "arcee-ai/trinity-mini",
+            name: "Arcee AI: Trinity Mini",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0,
-                output: 0,
+                input: 0.045,
+                output: 0.15,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 4096,
+            maxTokens: 131072,
         },
         "arcee-ai/virtuoso-large": {
             id: "arcee-ai/virtuoso-large",
@@ -7252,7 +7664,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
+            reasoning: false,
             input: ["text"],
             cost: {
                 input: 0.19999999999999998,
@@ -7306,13 +7718,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.44999999999999996,
+                input: 0.5,
                 output: 2.1500000000000004,
-                cacheRead: 0.22499999999999998,
+                cacheRead: 0.35,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 65536,
+            maxTokens: 4096,
         },
         "deepseek/deepseek-v3.1-terminus": {
             id: "deepseek/deepseek-v3.1-terminus",
@@ -7340,13 +7752,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.26,
-                output: 0.38,
-                cacheRead: 0.13,
+                input: 0.252,
+                output: 0.378,
+                cacheRead: 0.0252,
                 cacheWrite: 0,
             },
-            contextWindow: 163840,
-            maxTokens: 4096,
+            contextWindow: 131072,
+            maxTokens: 65536,
         },
         "deepseek/deepseek-v3.2-exp": {
             id: "deepseek/deepseek-v3.2-exp",
@@ -7396,7 +7808,7 @@ export const MODELS = {
                 cacheRead: 0.024999999999999998,
                 cacheWrite: 0.08333333333333334,
             },
-            contextWindow: 1048576,
+            contextWindow: 1000000,
             maxTokens: 8192,
         },
         "google/gemini-2.0-flash-lite-001": {
@@ -7465,7 +7877,7 @@ export const MODELS = {
                 cacheWrite: 0.08333333333333334,
             },
             contextWindow: 1048576,
-            maxTokens: 65536,
+            maxTokens: 65535,
         },
         "google/gemini-2.5-pro": {
             id: "google/gemini-2.5-pro",
@@ -7535,23 +7947,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "google/gemini-3-pro-preview": {
-            id: "google/gemini-3-pro-preview",
-            name: "Google: Gemini 3 Pro Preview",
-            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,
-        },
         "google/gemini-3.1-flash-lite-preview": {
             id: "google/gemini-3.1-flash-lite-preview",
             name: "Google: Gemini 3.1 Flash Lite Preview",
@@ -7603,22 +7998,73 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "inception/mercury": {
-            id: "inception/mercury",
-            name: "Inception: Mercury",
+        "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,
+        },
+        "google/gemma-4-26b-a4b-it:free": {
+            id: "google/gemma-4-26b-a4b-it:free",
+            name: "Google: Gemma 4 26B A4B  (free)",
+            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: 262144,
+            maxTokens: 32768,
+        },
+        "google/gemma-4-31b-it": {
+            id: "google/gemma-4-31b-it",
+            name: "Google: Gemma 4 31B",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.13,
+                output: 0.38,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 4096,
+        },
+        "google/gemma-4-31b-it:free": {
+            id: "google/gemma-4-31b-it:free",
+            name: "Google: Gemma 4 31B (free)",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
+            reasoning: true,
+            input: ["text", "image"],
             cost: {
-                input: 0.25,
-                output: 0.75,
-                cacheRead: 0.024999999999999998,
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 32000,
+            contextWindow: 262144,
+            maxTokens: 32768,
         },
         "inception/mercury-2": {
             id: "inception/mercury-2",
@@ -7637,56 +8083,39 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 50000,
         },
-        "inception/mercury-coder": {
-            id: "inception/mercury-coder",
-            name: "Inception: Mercury Coder",
+        "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: 0.25,
-                output: 0.75,
-                cacheRead: 0.024999999999999998,
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 32000,
+            contextWindow: 262144,
+            maxTokens: 32768,
         },
-        "kwaipilot/kat-coder-pro": {
-            id: "kwaipilot/kat-coder-pro",
-            name: "Kwaipilot: KAT-Coder-Pro V1",
+        "kwaipilot/kat-coder-pro-v2": {
+            id: "kwaipilot/kat-coder-pro-v2",
+            name: "Kwaipilot: KAT-Coder-Pro V2",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.207,
-                output: 0.828,
-                cacheRead: 0.0414,
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
-            maxTokens: 128000,
-        },
-        "meituan/longcat-flash-chat": {
-            id: "meituan/longcat-flash-chat",
-            name: "Meituan: LongCat Flash Chat",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.19999999999999998,
-                output: 0.7999999999999999,
-                cacheRead: 0.19999999999999998,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
+            maxTokens: 80000,
         },
         "meta-llama/llama-3-8b-instruct": {
             id: "meta-llama/llama-3-8b-instruct",
@@ -7773,23 +8202,6 @@ export const MODELS = {
             contextWindow: 65536,
             maxTokens: 4096,
         },
-        "meta-llama/llama-4-maverick": {
-            id: "meta-llama/llama-4-maverick",
-            name: "Meta: Llama 4 Maverick",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 16384,
-        },
         "meta-llama/llama-4-scout": {
             id: "meta-llama/llama-4-scout",
             name: "Meta: Llama 4 Scout",
@@ -7850,13 +8262,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.27,
+                input: 0.29,
                 output: 0.95,
-                cacheRead: 0.0290000007,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 196608,
-            maxTokens: 4096,
+            maxTokens: 196608,
         },
         "minimax/minimax-m2.5": {
             id: "minimax/minimax-m2.5",
@@ -7867,9 +8279,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.19999999999999998,
-                output: 1.17,
-                cacheRead: 0.09999999999999999,
+                input: 0.15,
+                output: 1.2,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 196608,
@@ -7890,7 +8302,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 196608,
-            maxTokens: 196608,
+            maxTokens: 8192,
         },
         "minimax/minimax-m2.7": {
             id: "minimax/minimax-m2.7",
@@ -7903,11 +8315,11 @@ export const MODELS = {
             cost: {
                 input: 0.3,
                 output: 1.2,
-                cacheRead: 0.06,
+                cacheRead: 0.059,
                 cacheWrite: 0,
             },
-            contextWindow: 204800,
-            maxTokens: 131072,
+            contextWindow: 196608,
+            maxTokens: 4096,
         },
         "mistralai/codestral-2508": {
             id: "mistralai/codestral-2508",
@@ -8139,13 +8551,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.02,
-                output: 0.04,
+                input: 0.01,
+                output: 0.03,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 16384,
+            maxTokens: 4096,
         },
         "mistralai/mistral-saba": {
             id: "mistralai/mistral-saba",
@@ -8164,23 +8576,6 @@ export const MODELS = {
             contextWindow: 32768,
             maxTokens: 4096,
         },
-        "mistralai/mistral-small-24b-instruct-2501": {
-            id: "mistralai/mistral-small-24b-instruct-2501",
-            name: "Mistral: Mistral Small 3",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.049999999999999996,
-                output: 0.08,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 32768,
-            maxTokens: 16384,
-        },
         "mistralai/mistral-small-2603": {
             id: "mistralai/mistral-small-2603",
             name: "Mistral: Mistral Small 4",
@@ -8198,23 +8593,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 4096,
         },
-        "mistralai/mistral-small-3.1-24b-instruct:free": {
-            id: "mistralai/mistral-small-3.1-24b-instruct:free",
-            name: "Mistral: Mistral Small 3.1 24B (free)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 4096,
-        },
         "mistralai/mistral-small-3.2-24b-instruct": {
             id: "mistralai/mistral-small-3.2-24b-instruct",
             name: "Mistral: Mistral Small 3.2 24B",
@@ -8332,7 +8710,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 131072,
+            maxTokens: 32768,
         },
         "moonshotai/kimi-k2-0905": {
             id: "moonshotai/kimi-k2-0905",
@@ -8345,11 +8723,11 @@ export const MODELS = {
             cost: {
                 input: 0.39999999999999997,
                 output: 2,
-                cacheRead: 0.15,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 4096,
+            contextWindow: 262144,
+            maxTokens: 262144,
         },
         "moonshotai/kimi-k2-thinking": {
             id: "moonshotai/kimi-k2-thinking",
@@ -8360,13 +8738,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.47,
-                output: 2,
-                cacheRead: 0.14100000000000001,
+                input: 0.6,
+                output: 2.5,
+                cacheRead: 0.15,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 4096,
+            contextWindow: 262144,
+            maxTokens: 262144,
         },
         "moonshotai/kimi-k2.5": {
             id: "moonshotai/kimi-k2.5",
@@ -8385,6 +8763,23 @@ 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: 0.56,
+                output: 3.5,
+                cacheRead: 0.11,
+                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",
@@ -8479,9 +8874,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.5,
-                cacheRead: 0.09999999999999999,
+                input: 0.09,
+                output: 0.44999999999999996,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -8706,7 +9101,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1047576,
-            maxTokens: 32768,
+            maxTokens: 4096,
         },
         "openai/gpt-4.1-mini": {
             id: "openai/gpt-4.1-mini",
@@ -8753,7 +9148,7 @@ export const MODELS = {
             cost: {
                 input: 2.5,
                 output: 10,
-                cacheRead: 1.25,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -8861,23 +9256,6 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 16384,
         },
-        "openai/gpt-4o:extended": {
-            id: "openai/gpt-4o:extended",
-            name: "OpenAI: GPT-4o (extended)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 6,
-                output: 18,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 64000,
-        },
         "openai/gpt-5": {
             id: "openai/gpt-5",
             name: "OpenAI: GPT-5",
@@ -8912,40 +9290,6 @@ 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",
@@ -8974,11 +9318,11 @@ export const MODELS = {
             cost: {
                 input: 0.049999999999999996,
                 output: 0.39999999999999997,
-                cacheRead: 0.005,
+                cacheRead: 0.01,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
-            maxTokens: 128000,
+            maxTokens: 4096,
         },
         "openai/gpt-5-pro": {
             id: "openai/gpt-5-pro",
@@ -9008,7 +9352,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.125,
+                cacheRead: 0.13,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -9076,11 +9420,11 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 2,
-                cacheRead: 0.024999999999999998,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
-            maxTokens: 100000,
+            maxTokens: 128000,
         },
         "openai/gpt-5.2": {
             id: "openai/gpt-5.2",
@@ -9114,7 +9458,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 16384,
+            maxTokens: 32000,
         },
         "openai/gpt-5.2-codex": {
             id: "openai/gpt-5.2-codex",
@@ -9252,6 +9596,40 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "openai/gpt-audio": {
+            id: "openai/gpt-audio",
+            name: "OpenAI: GPT Audio",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 2.5,
+                output: 10,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
+        "openai/gpt-audio-mini": {
+            id: "openai/gpt-audio-mini",
+            name: "OpenAI: GPT Audio Mini",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.6,
+                output: 2.4,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
         "openai/gpt-oss-120b": {
             id: "openai/gpt-oss-120b",
             name: "OpenAI: gpt-oss-120b",
@@ -9296,12 +9674,12 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.03,
-                output: 0.11,
-                cacheRead: 0.015,
+                output: 0.14,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 131072,
+            maxTokens: 4096,
         },
         "openai/gpt-oss-20b:free": {
             id: "openai/gpt-oss-20b:free",
@@ -9318,7 +9696,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 131072,
+            maxTokens: 8192,
         },
         "openai/gpt-oss-safeguard-20b": {
             id: "openai/gpt-oss-safeguard-20b",
@@ -9604,7 +9982,7 @@ export const MODELS = {
                 input: 0.26,
                 output: 0.78,
                 cacheRead: 0.052000000000000005,
-                cacheWrite: 0,
+                cacheWrite: 0.325,
             },
             contextWindow: 1000000,
             maxTokens: 32768,
@@ -9621,7 +9999,7 @@ export const MODELS = {
                 input: 0.26,
                 output: 0.78,
                 cacheRead: 0,
-                cacheWrite: 0,
+                cacheWrite: 0.325,
             },
             contextWindow: 1000000,
             maxTokens: 32768,
@@ -9638,7 +10016,7 @@ export const MODELS = {
                 input: 0.26,
                 output: 0.78,
                 cacheRead: 0,
-                cacheWrite: 0,
+                cacheWrite: 0.325,
             },
             contextWindow: 1000000,
             maxTokens: 32768,
@@ -9717,7 +10095,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
+            reasoning: false,
             input: ["text"],
             cost: {
                 input: 0.071,
@@ -9793,42 +10171,25 @@ export const MODELS = {
                 cacheRead: 0.08,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
-        "qwen/qwen3-32b": {
-            id: "qwen/qwen3-32b",
-            name: "Qwen: Qwen3 32B",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.08,
-                output: 0.24,
-                cacheRead: 0.04,
-                cacheWrite: 0,
-            },
-            contextWindow: 40960,
-            maxTokens: 40960,
+            contextWindow: 131072,
+            maxTokens: 131072,
         },
-        "qwen/qwen3-4b:free": {
-            id: "qwen/qwen3-4b:free",
-            name: "Qwen: Qwen3 4B (free)",
+        "qwen/qwen3-32b": {
+            id: "qwen/qwen3-32b",
+            name: "Qwen: Qwen3 32B",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 0.08,
+                output: 0.24,
+                cacheRead: 0.04,
                 cacheWrite: 0,
             },
             contextWindow: 40960,
-            maxTokens: 4096,
+            maxTokens: 40960,
         },
         "qwen/qwen3-8b": {
             id: "qwen/qwen3-8b",
@@ -9893,7 +10254,7 @@ export const MODELS = {
                 input: 0.195,
                 output: 0.975,
                 cacheRead: 0.039,
-                cacheWrite: 0,
+                cacheWrite: 0.24375,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
@@ -9907,13 +10268,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.12,
-                output: 0.75,
-                cacheRead: 0.06,
+                input: 0.15,
+                output: 0.7999999999999999,
+                cacheRead: 0.11,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 65536,
+            maxTokens: 262144,
         },
         "qwen/qwen3-coder-plus": {
             id: "qwen/qwen3-coder-plus",
@@ -9927,7 +10288,7 @@ export const MODELS = {
                 input: 0.65,
                 output: 3.25,
                 cacheRead: 0.13,
-                cacheWrite: 0,
+                cacheWrite: 0.8125,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
@@ -9961,7 +10322,7 @@ export const MODELS = {
                 input: 0.78,
                 output: 3.9,
                 cacheRead: 0.156,
-                cacheWrite: 0,
+                cacheWrite: 0.975,
             },
             contextWindow: 262144,
             maxTokens: 32768,
@@ -10215,7 +10576,7 @@ export const MODELS = {
             cost: {
                 input: 0.39,
                 output: 2.34,
-                cacheRead: 0,
+                cacheRead: 0.195,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -10230,13 +10591,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.049999999999999996,
+                input: 0.09999999999999999,
                 output: 0.15,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 65536,
+            contextWindow: 262144,
+            maxTokens: 4096,
         },
         "qwen/qwen3.5-flash-02-23": {
             id: "qwen/qwen3.5-flash-02-23",
@@ -10250,7 +10611,7 @@ export const MODELS = {
                 input: 0.065,
                 output: 0.26,
                 cacheRead: 0,
-                cacheWrite: 0,
+                cacheWrite: 0.08125,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
@@ -10267,7 +10628,24 @@ export const MODELS = {
                 input: 0.26,
                 output: 1.56,
                 cacheRead: 0,
-                cacheWrite: 0,
+                cacheWrite: 0.325,
+            },
+            contextWindow: 1000000,
+            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,
@@ -10289,6 +10667,23 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 131072,
         },
+        "rekaai/reka-edge": {
+            id: "rekaai/reka-edge",
+            name: "Reka Edge",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.09999999999999999,
+                output: 0.09999999999999999,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 16384,
+            maxTokens: 16384,
+        },
         "relace/relace-search": {
             id: "relace/relace-search",
             name: "Relace: Relace Search",
@@ -10351,15 +10746,15 @@ export const MODELS = {
             cost: {
                 input: 0.09999999999999999,
                 output: 0.3,
-                cacheRead: 0.02,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 256000,
+            contextWindow: 262144,
+            maxTokens: 65536,
         },
-        "stepfun/step-3.5-flash:free": {
-            id: "stepfun/step-3.5-flash:free",
-            name: "StepFun: Step 3.5 Flash (free)",
+        "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",
@@ -10371,8 +10766,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 256000,
+            contextWindow: 262144,
+            maxTokens: 262144,
         },
         "thedrummer/rocinante-12b": {
             id: "thedrummer/rocinante-12b",
@@ -10561,9 +10956,9 @@ export const MODELS = {
             contextWindow: 2000000,
             maxTokens: 30000,
         },
-        "x-ai/grok-4.20-beta": {
-            id: "x-ai/grok-4.20-beta",
-            name: "xAI: Grok 4.20 Beta",
+        "x-ai/grok-4.20": {
+            id: "x-ai/grok-4.20",
+            name: "xAI: Grok 4.20",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
@@ -10646,6 +11041,40 @@ 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 ",
@@ -10774,13 +11203,13 @@ 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",
@@ -10813,8 +11242,8 @@ export const MODELS = {
                 cacheRead: 0.119,
                 cacheWrite: 0,
             },
-            contextWindow: 80000,
-            maxTokens: 131072,
+            contextWindow: 202752,
+            maxTokens: 4096,
         },
         "z-ai/glm-5-turbo": {
             id: "z-ai/glm-5-turbo",
@@ -10833,6 +11262,57 @@ export const MODELS = {
             contextWindow: 202752,
             maxTokens: 131072,
         },
+        "z-ai/glm-5.1": {
+            id: "z-ai/glm-5.1",
+            name: "Z.ai: GLM 5.1",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                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",
+            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-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,
+        },
     },
     "vercel-ai-gateway": {
         "alibaba/qwen-3-14b": {
@@ -10854,20 +11334,20 @@ export const MODELS = {
         },
         "alibaba/qwen-3-235b": {
             id: "alibaba/qwen-3-235b",
-            name: "Qwen3-235B-A22B",
+            name: "Qwen3 235B A22b Instruct 2507",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.071,
-                output: 0.463,
-                cacheRead: 0,
+                input: 0.6,
+                output: 1.2,
+                cacheRead: 0.6,
                 cacheWrite: 0,
             },
-            contextWindow: 40960,
-            maxTokens: 16384,
+            contextWindow: 131000,
+            maxTokens: 40000,
         },
         "alibaba/qwen-3-30b": {
             id: "alibaba/qwen-3-30b",
@@ -10895,13 +11375,30 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.29,
-                output: 0.59,
-                cacheRead: 0.145,
+                input: 0.16,
+                output: 0.64,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 40960,
+            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",
@@ -10929,13 +11426,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.39999999999999997,
-                output: 1.5999999999999999,
-                cacheRead: 0.022,
+                input: 1.5,
+                output: 7.5,
+                cacheRead: 0.3,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 66536,
+            maxTokens: 65536,
         },
         "alibaba/qwen3-coder-30b-a3b": {
             id: "alibaba/qwen3-coder-30b-a3b",
@@ -11048,13 +11545,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.22,
-                output: 0.88,
+                input: 0.39999999999999997,
+                output: 4,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 256000,
+            contextWindow: 131072,
+            maxTokens: 32768,
         },
         "alibaba/qwen3.5-flash": {
             id: "alibaba/qwen3.5-flash",
@@ -11090,6 +11587,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "alibaba/qwen3.6-plus": {
+            id: "alibaba/qwen3.6-plus",
+            name: "Qwen 3.6 Plus",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.5,
+                output: 3,
+                cacheRead: 0.09999999999999999,
+                cacheWrite: 0.625,
+            },
+            contextWindow: 1000000,
+            maxTokens: 64000,
+        },
         "anthropic/claude-3-haiku": {
             id: "anthropic/claude-3-haiku",
             name: "Claude 3 Haiku",
@@ -11124,40 +11638,6 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 8192,
         },
-        "anthropic/claude-3.5-sonnet": {
-            id: "anthropic/claude-3.5-sonnet",
-            name: "Claude 3.5 Sonnet",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 8192,
-        },
-        "anthropic/claude-3.5-sonnet-20240620": {
-            id: "anthropic/claude-3.5-sonnet-20240620",
-            name: "Claude 3.5 Sonnet (2024-06-20)",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
-                cacheWrite: 3.75,
-            },
-            contextWindow: 200000,
-            maxTokens: 8192,
-        },
         "anthropic/claude-3.7-sonnet": {
             id: "anthropic/claude-3.7-sonnet",
             name: "Claude 3.7 Sonnet",
@@ -11260,6 +11740,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
+        "anthropic/claude-opus-4.7": {
+            id: "anthropic/claude-opus-4.7",
+            name: "Claude Opus 4.7",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "anthropic/claude-sonnet-4": {
             id: "anthropic/claude-sonnet-4",
             name: "Claude Sonnet 4",
@@ -11328,6 +11825,23 @@ export const MODELS = {
             contextWindow: 131000,
             maxTokens: 131000,
         },
+        "arcee-ai/trinity-large-thinking": {
+            id: "arcee-ai/trinity-large-thinking",
+            name: "Trinity Large Thinking",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.25,
+                output: 0.8999999999999999,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262100,
+            maxTokens: 80000,
+        },
         "bytedance/seed-1.6": {
             id: "bytedance/seed-1.6",
             name: "Seed 1.6",
@@ -11405,13 +11919,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.5,
-                output: 1.5,
-                cacheRead: 0,
+                input: 0.56,
+                output: 1.68,
+                cacheRead: 0.28,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 16384,
+            maxTokens: 8192,
         },
         "deepseek/deepseek-v3.1-terminus": {
             id: "deepseek/deepseek-v3.1-terminus",
@@ -11594,7 +12108,7 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 1.5,
-                cacheRead: 0,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -11617,6 +12131,40 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "google/gemma-4-26b-a4b-it": {
+            id: "google/gemma-4-26b-a4b-it",
+            name: "Gemma 4 26B A4B IT",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.13,
+                output: 0.39999999999999997,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 131072,
+        },
+        "google/gemma-4-31b-it": {
+            id: "google/gemma-4-31b-it",
+            name: "Gemma 4 31B IT",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 0.14,
+                output: 0.39999999999999997,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 131072,
+        },
         "inception/mercury-2": {
             id: "inception/mercury-2",
             name: "Mercury 2",
@@ -11651,39 +12199,39 @@ export const MODELS = {
             contextWindow: 32000,
             maxTokens: 16384,
         },
-        "meituan/longcat-flash-chat": {
-            id: "meituan/longcat-flash-chat",
-            name: "LongCat Flash Chat",
+        "kwaipilot/kat-coder-pro-v2": {
+            id: "kwaipilot/kat-coder-pro-v2",
+            name: "Kat Coder Pro V2",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
+            reasoning: true,
             input: ["text"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 100000,
+            contextWindow: 256000,
+            maxTokens: 256000,
         },
-        "meituan/longcat-flash-thinking": {
-            id: "meituan/longcat-flash-thinking",
-            name: "LongCat Flash Thinking",
+        "meituan/longcat-flash-chat": {
+            id: "meituan/longcat-flash-chat",
+            name: "LongCat Flash Chat",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
+            reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.15,
-                output: 1.5,
+                input: 0,
+                output: 0,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 8192,
+            maxTokens: 100000,
         },
         "meta/llama-3.1-70b": {
             id: "meta/llama-3.1-70b",
@@ -11711,13 +12259,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
-                output: 0.09999999999999999,
-                cacheRead: 0.09999999999999999,
+                input: 0.22,
+                output: 0.22,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 16384,
+            maxTokens: 8192,
         },
         "meta/llama-3.2-11b": {
             id: "meta/llama-3.2-11b",
@@ -12095,20 +12643,20 @@ export const MODELS = {
         },
         "moonshotai/kimi-k2": {
             id: "moonshotai/kimi-k2",
-            name: "Kimi K2",
+            name: "Kimi K2 Instruct",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.6,
-                output: 2.5,
-                cacheRead: 0.15,
+                input: 0.5700000000000001,
+                output: 2.3,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 16384,
+            maxTokens: 131072,
         },
         "moonshotai/kimi-k2-0905": {
             id: "moonshotai/kimi-k2-0905",
@@ -12121,11 +12669,11 @@ export const MODELS = {
             cost: {
                 input: 0.6,
                 output: 2.5,
-                cacheRead: 0.15,
+                cacheRead: 0.3,
                 cacheWrite: 0,
             },
             contextWindow: 256000,
-            maxTokens: 16384,
+            maxTokens: 128000,
         },
         "moonshotai/kimi-k2-thinking": {
             id: "moonshotai/kimi-k2-thinking",
@@ -12195,6 +12743,23 @@ 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",
@@ -12690,24 +13255,24 @@ export const MODELS = {
         },
         "openai/gpt-oss-20b": {
             id: "openai/gpt-oss-20b",
-            name: "gpt-oss-20b",
+            name: "GPT OSS 120B",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.07,
-                output: 0.3,
+                input: 0.049999999999999996,
+                output: 0.19999999999999998,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 131072,
             maxTokens: 8192,
         },
         "openai/gpt-oss-safeguard-20b": {
             id: "openai/gpt-oss-safeguard-20b",
-            name: "gpt-oss-safeguard-20b",
+            name: "GPT OSS Safeguard 20B",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
@@ -12875,23 +13440,6 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 131072,
         },
-        "xai/grok-2-vision": {
-            id: "xai/grok-2-vision",
-            name: "Grok 2 Vision",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 32768,
-            maxTokens: 32768,
-        },
         "xai/grok-3": {
             id: "xai/grok-3",
             name: "Grok 3 Beta",
@@ -12984,7 +13532,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: false,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 0.19999999999999998,
                 output: 0.5,
@@ -13001,7 +13549,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 0.19999999999999998,
                 output: 0.5,
@@ -13018,7 +13566,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: false,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 0.19999999999999998,
                 output: 0.5,
@@ -13035,7 +13583,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 0.19999999999999998,
                 output: 0.5,
@@ -13052,7 +13600,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 2,
                 output: 6,
@@ -13069,7 +13617,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
                 input: 2,
                 output: 6,
@@ -13175,7 +13723,7 @@ export const MODELS = {
             cost: {
                 input: 0.09999999999999999,
                 output: 0.3,
-                cacheRead: 0.02,
+                cacheRead: 0.01,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -13309,13 +13857,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.6,
-                output: 2.2,
-                cacheRead: 0,
+                input: 2.25,
+                output: 2.75,
+                cacheRead: 2.25,
                 cacheWrite: 0,
             },
-            contextWindow: 200000,
-            maxTokens: 120000,
+            contextWindow: 131000,
+            maxTokens: 40000,
         },
         "zai/glm-4.7-flash": {
             id: "zai/glm-4.7-flash",
@@ -13385,6 +13933,40 @@ export const MODELS = {
             contextWindow: 202800,
             maxTokens: 131100,
         },
+        "zai/glm-5.1": {
+            id: "zai/glm-5.1",
+            name: "GLM 5.1",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.4,
+                output: 4.4,
+                cacheRead: 0.26,
+                cacheWrite: 0,
+            },
+            contextWindow: 202800,
+            maxTokens: 64000,
+        },
+        "zai/glm-5v-turbo": {
+            id: "zai/glm-5v-turbo",
+            name: "GLM 5V Turbo",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.2,
+                output: 4,
+                cacheRead: 0.24,
+                cacheWrite: 0,
+            },
+            contextWindow: 200000,
+            maxTokens: 128000,
+        },
     },
     "xai": {
         "grok-2": {
@@ -13807,9 +14389,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.6,
-                output: 2.2,
-                cacheRead: 0.11,
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -13825,9 +14407,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.2,
-                output: 1.1,
-                cacheRead: 0.03,
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -13861,8 +14443,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.6,
-                output: 1.8,
+                input: 0,
+                output: 0,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -13875,13 +14457,13 @@ 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: 0.6,
-                output: 2.2,
-                cacheRead: 0.11,
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
@@ -13893,12 +14475,12 @@ 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", "image"],
             cost: {
-                input: 0.3,
-                output: 0.9,
+                input: 0,
+                output: 0,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -13911,13 +14493,13 @@ 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: 0.6,
-                output: 2.2,
-                cacheRead: 0.11,
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
@@ -13929,7 +14511,7 @@ 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: {
@@ -13941,19 +14523,37 @@ export const MODELS = {
             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" },
+            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "zaiToolStream": true },
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1,
-                output: 3.2,
-                cacheRead: 0.2,
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
@@ -13965,13 +14565,49 @@ 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,
+            maxTokens: 131072,
+        },
+        "glm-5.1": {
+            id: "glm-5.1",
+            name: "GLM-5.1",
+            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-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", "zaiToolStream": true },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 200000,