@earendil-works/pi-ai 0.75.4 → 0.76.0

package/dist/models.generated.js

@@ -1720,6 +1720,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "anthropic",
             baseUrl: "https://api.anthropic.com",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "max" },
             input: ["text", "image"],
@@ -1738,6 +1739,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "anthropic",
             baseUrl: "https://api.anthropic.com",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
@@ -1824,6 +1826,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "anthropic",
             baseUrl: "https://api.anthropic.com",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -1916,7 +1919,7 @@ export const MODELS = {
             cost: {
                 input: 0.1,
                 output: 0.4,
-                cacheRead: 0.03,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 1047576,
@@ -2001,7 +2004,7 @@ export const MODELS = {
             cost: {
                 input: 0.15,
                 output: 0.6,
-                cacheRead: 0.08,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -2127,7 +2130,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.13,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -2552,7 +2555,7 @@ export const MODELS = {
             cost: {
                 input: 1.1,
                 output: 4.4,
-                cacheRead: 0.28,
+                cacheRead: 0.275,
                 cacheWrite: 0,
             },
             contextWindow: 200000,
@@ -2611,23 +2614,6 @@ export const MODELS = {
             contextWindow: 32000,
             maxTokens: 8000,
         },
-        "qwen-3-235b-a22b-instruct-2507": {
-            id: "qwen-3-235b-a22b-instruct-2507",
-            name: "Qwen 3 235B Instruct",
-            api: "openai-completions",
-            provider: "cerebras",
-            baseUrl: "https://api.cerebras.ai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.6,
-                output: 1.2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131000,
-            maxTokens: 32000,
-        },
         "zai-glm-4.7": {
             id: "zai-glm-4.7",
             name: "Z.AI GLM-4.7",
@@ -2823,6 +2809,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "cloudflare-ai-gateway",
             baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "max" },
             input: ["text", "image"],
@@ -2841,6 +2828,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "cloudflare-ai-gateway",
             baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
@@ -2893,6 +2881,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "cloudflare-ai-gateway",
             baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/anthropic",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -3275,6 +3264,42 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 16384,
         },
+        "@cf/ibm-granite/granite-4.0-h-micro": {
+            id: "@cf/ibm-granite/granite-4.0-h-micro",
+            name: "Granite 4.0 H Micro",
+            api: "openai-completions",
+            provider: "cloudflare-workers-ai",
+            baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+            compat: { "sendSessionAffinityHeaders": true },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.017,
+                output: 0.112,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 131000,
+            maxTokens: 131000,
+        },
+        "@cf/meta/llama-3.3-70b-instruct-fp8-fast": {
+            id: "@cf/meta/llama-3.3-70b-instruct-fp8-fast",
+            name: "Llama 3.3 70B Instruct fp8 Fast",
+            api: "openai-completions",
+            provider: "cloudflare-workers-ai",
+            baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+            compat: { "sendSessionAffinityHeaders": true },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.293,
+                output: 2.253,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 24000,
+            maxTokens: 24000,
+        },
         "@cf/meta/llama-4-scout-17b-16e-instruct": {
             id: "@cf/meta/llama-4-scout-17b-16e-instruct",
             name: "Llama 4 Scout 17B 16E Instruct",
@@ -3290,9 +3315,27 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
+            contextWindow: 131000,
             maxTokens: 16384,
         },
+        "@cf/mistralai/mistral-small-3.1-24b-instruct": {
+            id: "@cf/mistralai/mistral-small-3.1-24b-instruct",
+            name: "Mistral Small 3.1 24B Instruct",
+            api: "openai-completions",
+            provider: "cloudflare-workers-ai",
+            baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+            compat: { "sendSessionAffinityHeaders": true },
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.351,
+                output: 0.555,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 128000,
+        },
         "@cf/moonshotai/kimi-k2.5": {
             id: "@cf/moonshotai/kimi-k2.5",
             name: "Kimi K2.5",
@@ -3326,7 +3369,7 @@ export const MODELS = {
                 cacheRead: 0.16,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
+            contextWindow: 262144,
             maxTokens: 256000,
         },
         "@cf/nvidia/nemotron-3-120b-a12b": {
@@ -3383,6 +3426,24 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 16384,
         },
+        "@cf/qwen/qwen3-30b-a3b-fp8": {
+            id: "@cf/qwen/qwen3-30b-a3b-fp8",
+            name: "Qwen3 30B A3b fp8",
+            api: "openai-completions",
+            provider: "cloudflare-workers-ai",
+            baseUrl: "https://api.cloudflare.com/client/v4/accounts/{CLOUDFLARE_ACCOUNT_ID}/ai/v1",
+            compat: { "sendSessionAffinityHeaders": true },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.0509,
+                output: 0.335,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 32768,
+            maxTokens: 32768,
+        },
         "@cf/zai-org/glm-4.7-flash": {
             id: "@cf/zai-org/glm-4.7-flash",
             name: "GLM-4.7-Flash",
@@ -3393,7 +3454,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.06,
+                input: 0.0605,
                 output: 0.4,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -3443,42 +3504,6 @@ export const MODELS = {
         },
     },
     "fireworks": {
-        "accounts/fireworks/models/deepseek-v3p1": {
-            id: "accounts/fireworks/models/deepseek-v3p1",
-            name: "DeepSeek V3.1",
-            api: "anthropic-messages",
-            provider: "fireworks",
-            baseUrl: "https://api.fireworks.ai/inference",
-            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.56,
-                output: 1.68,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 163840,
-            maxTokens: 163840,
-        },
-        "accounts/fireworks/models/deepseek-v3p2": {
-            id: "accounts/fireworks/models/deepseek-v3p2",
-            name: "DeepSeek V3.2",
-            api: "anthropic-messages",
-            provider: "fireworks",
-            baseUrl: "https://api.fireworks.ai/inference",
-            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.56,
-                output: 1.68,
-                cacheRead: 0.28,
-                cacheWrite: 0,
-            },
-            contextWindow: 160000,
-            maxTokens: 160000,
-        },
         "accounts/fireworks/models/deepseek-v4-flash": {
             id: "accounts/fireworks/models/deepseek-v4-flash",
             name: "DeepSeek V4 Flash",
@@ -3509,84 +3534,12 @@ export const MODELS = {
             cost: {
                 input: 1.74,
                 output: 3.48,
-                cacheRead: 0.15,
+                cacheRead: 0.145,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
             maxTokens: 384000,
         },
-        "accounts/fireworks/models/glm-4p5": {
-            id: "accounts/fireworks/models/glm-4p5",
-            name: "GLM 4.5",
-            api: "anthropic-messages",
-            provider: "fireworks",
-            baseUrl: "https://api.fireworks.ai/inference",
-            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.55,
-                output: 2.19,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
-        "accounts/fireworks/models/glm-4p5-air": {
-            id: "accounts/fireworks/models/glm-4p5-air",
-            name: "GLM 4.5 Air",
-            api: "anthropic-messages",
-            provider: "fireworks",
-            baseUrl: "https://api.fireworks.ai/inference",
-            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.22,
-                output: 0.88,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
-        "accounts/fireworks/models/glm-4p7": {
-            id: "accounts/fireworks/models/glm-4p7",
-            name: "GLM 4.7",
-            api: "anthropic-messages",
-            provider: "fireworks",
-            baseUrl: "https://api.fireworks.ai/inference",
-            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.6,
-                output: 2.2,
-                cacheRead: 0.3,
-                cacheWrite: 0,
-            },
-            contextWindow: 198000,
-            maxTokens: 198000,
-        },
-        "accounts/fireworks/models/glm-5": {
-            id: "accounts/fireworks/models/glm-5",
-            name: "GLM 5",
-            api: "anthropic-messages",
-            provider: "fireworks",
-            baseUrl: "https://api.fireworks.ai/inference",
-            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 1,
-                output: 3.2,
-                cacheRead: 0.5,
-                cacheWrite: 0,
-            },
-            contextWindow: 202752,
-            maxTokens: 131072,
-        },
         "accounts/fireworks/models/glm-5p1": {
             id: "accounts/fireworks/models/glm-5p1",
             name: "GLM 5.1",
@@ -3617,7 +3570,7 @@ export const MODELS = {
             cost: {
                 input: 0.15,
                 output: 0.6,
-                cacheRead: 0,
+                cacheRead: 0.015,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -3633,50 +3586,14 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.05,
-                output: 0.2,
-                cacheRead: 0,
+                input: 0.07,
+                output: 0.3,
+                cacheRead: 0.035,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
             maxTokens: 32768,
         },
-        "accounts/fireworks/models/kimi-k2-instruct": {
-            id: "accounts/fireworks/models/kimi-k2-instruct",
-            name: "Kimi K2 Instruct",
-            api: "anthropic-messages",
-            provider: "fireworks",
-            baseUrl: "https://api.fireworks.ai/inference",
-            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 1,
-                output: 3,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 16384,
-        },
-        "accounts/fireworks/models/kimi-k2-thinking": {
-            id: "accounts/fireworks/models/kimi-k2-thinking",
-            name: "Kimi K2 Thinking",
-            api: "anthropic-messages",
-            provider: "fireworks",
-            baseUrl: "https://api.fireworks.ai/inference",
-            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.6,
-                output: 2.5,
-                cacheRead: 0.3,
-                cacheWrite: 0,
-            },
-            contextWindow: 256000,
-            maxTokens: 256000,
-        },
         "accounts/fireworks/models/kimi-k2p5": {
             id: "accounts/fireworks/models/kimi-k2p5",
             name: "Kimi K2.5",
@@ -3713,24 +3630,6 @@ export const MODELS = {
             contextWindow: 262000,
             maxTokens: 262000,
         },
-        "accounts/fireworks/models/minimax-m2p1": {
-            id: "accounts/fireworks/models/minimax-m2p1",
-            name: "MiniMax-M2.1",
-            api: "anthropic-messages",
-            provider: "fireworks",
-            baseUrl: "https://api.fireworks.ai/inference",
-            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.3,
-                output: 1.2,
-                cacheRead: 0.03,
-                cacheWrite: 0,
-            },
-            contextWindow: 200000,
-            maxTokens: 200000,
-        },
         "accounts/fireworks/models/minimax-m2p5": {
             id: "accounts/fireworks/models/minimax-m2p5",
             name: "MiniMax-M2.5",
@@ -3761,7 +3660,7 @@ export const MODELS = {
             cost: {
                 input: 0.3,
                 output: 1.2,
-                cacheRead: 0.03,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
             contextWindow: 196608,
@@ -3785,9 +3684,27 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 8192,
         },
-        "accounts/fireworks/routers/kimi-k2p5-turbo": {
-            id: "accounts/fireworks/routers/kimi-k2p5-turbo",
-            name: "Kimi K2.5 Turbo",
+        "accounts/fireworks/routers/glm-5p1-fast": {
+            id: "accounts/fireworks/routers/glm-5p1-fast",
+            name: "GLM 5.1 Fast",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 2.8,
+                output: 8.8,
+                cacheRead: 0.52,
+                cacheWrite: 0,
+            },
+            contextWindow: 202800,
+            maxTokens: 131072,
+        },
+        "accounts/fireworks/routers/kimi-k2p6-turbo": {
+            id: "accounts/fireworks/routers/kimi-k2p6-turbo",
+            name: "Kimi K2.6 Turbo",
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
@@ -3795,13 +3712,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 2,
+                output: 8,
+                cacheRead: 0.3,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 256000,
+            contextWindow: 262000,
+            maxTokens: 262000,
         },
     },
     "github-copilot": {
@@ -3849,6 +3766,7 @@ export const MODELS = {
             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" },
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "max" },
             input: ["text", "image"],
@@ -3868,6 +3786,7 @@ export const MODELS = {
             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" },
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
@@ -3906,6 +3825,7 @@ export const MODELS = {
             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" },
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -3974,6 +3894,25 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 64000,
         },
+        "gemini-3.5-flash": {
+            id: "gemini-3.5-flash",
+            name: "Gemini 3.5 Flash",
+            api: "openai-completions",
+            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" },
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 64000,
+        },
         "gpt-4.1": {
             id: "gpt-4.1",
             name: "GPT-4.1",
@@ -4166,57 +4105,6 @@ export const MODELS = {
         },
     },
     "google": {
-        "gemini-1.5-flash": {
-            id: "gemini-1.5-flash",
-            name: "Gemini 1.5 Flash",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.075,
-                output: 0.3,
-                cacheRead: 0.01875,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 8192,
-        },
-        "gemini-1.5-flash-8b": {
-            id: "gemini-1.5-flash-8b",
-            name: "Gemini 1.5 Flash-8B",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.0375,
-                output: 0.15,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 8192,
-        },
-        "gemini-1.5-pro": {
-            id: "gemini-1.5-pro",
-            name: "Gemini 1.5 Pro",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 1.25,
-                output: 5,
-                cacheRead: 0.3125,
-                cacheWrite: 0,
-            },
-            contextWindow: 1000000,
-            maxTokens: 8192,
-        },
         "gemini-2.0-flash": {
             id: "gemini-2.0-flash",
             name: "Gemini 2.0 Flash",
@@ -4236,7 +4124,7 @@ export const MODELS = {
         },
         "gemini-2.0-flash-lite": {
             id: "gemini-2.0-flash-lite",
-            name: "Gemini 2.0 Flash Lite",
+            name: "Gemini 2.0 Flash-Lite",
             api: "google-generative-ai",
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
@@ -4270,143 +4158,24 @@ export const MODELS = {
         },
         "gemini-2.5-flash-lite": {
             id: "gemini-2.5-flash-lite",
-            name: "Gemini 2.5 Flash Lite",
+            name: "Gemini 2.5 Flash-Lite",
             api: "google-generative-ai",
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
             reasoning: true,
             input: ["text", "image"],
-            cost: {
-                input: 0.1,
-                output: 0.4,
-                cacheRead: 0.01,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
-        "gemini-2.5-flash-lite-preview-06-17": {
-            id: "gemini-2.5-flash-lite-preview-06-17",
-            name: "Gemini 2.5 Flash Lite Preview 06-17",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.1,
-                output: 0.4,
-                cacheRead: 0.025,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
-        "gemini-2.5-flash-lite-preview-09-2025": {
-            id: "gemini-2.5-flash-lite-preview-09-2025",
-            name: "Gemini 2.5 Flash Lite Preview 09-25",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.1,
-                output: 0.4,
-                cacheRead: 0.025,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
-        "gemini-2.5-flash-preview-04-17": {
-            id: "gemini-2.5-flash-preview-04-17",
-            name: "Gemini 2.5 Flash Preview 04-17",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0.0375,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
-        "gemini-2.5-flash-preview-05-20": {
-            id: "gemini-2.5-flash-preview-05-20",
-            name: "Gemini 2.5 Flash Preview 05-20",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0.0375,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
-        "gemini-2.5-flash-preview-09-2025": {
-            id: "gemini-2.5-flash-preview-09-2025",
-            name: "Gemini 2.5 Flash Preview 09-25",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.3,
-                output: 2.5,
-                cacheRead: 0.075,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
-        "gemini-2.5-pro": {
-            id: "gemini-2.5-pro",
-            name: "Gemini 2.5 Pro",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1.25,
-                output: 10,
-                cacheRead: 0.125,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
-        "gemini-2.5-pro-preview-05-06": {
-            id: "gemini-2.5-pro-preview-05-06",
-            name: "Gemini 2.5 Pro Preview 05-06",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1.25,
-                output: 10,
-                cacheRead: 0.31,
+            cost: {
+                input: 0.1,
+                output: 0.4,
+                cacheRead: 0.01,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "gemini-2.5-pro-preview-06-05": {
-            id: "gemini-2.5-pro-preview-06-05",
-            name: "Gemini 2.5 Pro Preview 06-05",
+        "gemini-2.5-pro": {
+            id: "gemini-2.5-pro",
+            name: "Gemini 2.5 Pro",
             api: "google-generative-ai",
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
@@ -4415,7 +4184,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.31,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -4454,8 +4223,8 @@ export const MODELS = {
                 cacheRead: 0.2,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 64000,
+            contextWindow: 1048576,
+            maxTokens: 65536,
         },
         "gemini-3.1-flash-lite": {
             id: "gemini-3.1-flash-lite",
@@ -4581,60 +4350,9 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "gemini-live-2.5-flash": {
-            id: "gemini-live-2.5-flash",
-            name: "Gemini Live 2.5 Flash",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.5,
-                output: 2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 8000,
-        },
-        "gemini-live-2.5-flash-preview-native-audio": {
-            id: "gemini-live-2.5-flash-preview-native-audio",
-            name: "Gemini Live 2.5 Flash Preview Native Audio",
-            api: "google-generative-ai",
-            provider: "google",
-            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.5,
-                output: 2,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            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",
+            name: "Gemma 4 26B A4B IT",
             api: "google-generative-ai",
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
@@ -4647,12 +4365,12 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 8192,
+            contextWindow: 262144,
+            maxTokens: 32768,
         },
         "gemma-4-31b-it": {
             id: "gemma-4-31b-it",
-            name: "Gemma 4 31B",
+            name: "Gemma 4 31B IT",
             api: "google-generative-ai",
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
@@ -4665,8 +4383,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 8192,
+            contextWindow: 262144,
+            maxTokens: 32768,
         },
     },
     "google-vertex": {
@@ -5112,7 +4830,7 @@ export const MODELS = {
             cost: {
                 input: 1,
                 output: 3,
-                cacheRead: 0,
+                cacheRead: 0.5,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -5129,7 +4847,7 @@ export const MODELS = {
             cost: {
                 input: 0.15,
                 output: 0.6,
-                cacheRead: 0,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -5146,7 +4864,7 @@ export const MODELS = {
             cost: {
                 input: 0.075,
                 output: 0.3,
-                cacheRead: 0,
+                cacheRead: 0.0375,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -5432,9 +5150,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.74,
-                output: 3.48,
-                cacheRead: 0.145,
+                input: 0.435,
+                output: 0.87,
+                cacheRead: 0.003625,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -6527,7 +6245,7 @@ export const MODELS = {
             cost: {
                 input: 0.1,
                 output: 0.4,
-                cacheRead: 0.03,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 1047576,
@@ -6612,7 +6330,7 @@ export const MODELS = {
             cost: {
                 input: 0.15,
                 output: 0.6,
-                cacheRead: 0.08,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
@@ -6738,7 +6456,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.13,
+                cacheRead: 0.125,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -7163,7 +6881,7 @@ export const MODELS = {
             cost: {
                 input: 1.1,
                 output: 4.4,
-                cacheRead: 0.28,
+                cacheRead: 0.275,
                 cacheWrite: 0,
             },
             contextWindow: 200000,
@@ -7239,7 +6957,7 @@ export const MODELS = {
                 cacheRead: 0.175,
                 cacheWrite: 0,
             },
-            contextWindow: 272000,
+            contextWindow: 128000,
             maxTokens: 128000,
         },
         "gpt-5.4": {
@@ -7313,7 +7031,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 200000,
-            maxTokens: 128000,
+            maxTokens: 32000,
         },
         "claude-haiku-4-5": {
             id: "claude-haiku-4-5",
@@ -7372,6 +7090,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "max" },
             input: ["text", "image"],
@@ -7390,6 +7109,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
@@ -7442,6 +7162,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -7848,6 +7569,23 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "grok-build-0.1": {
+            id: "grok-build-0.1",
+            name: "Grok Build 0.1",
+            api: "openai-completions",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1,
+                output: 2,
+                cacheRead: 0.2,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
         "kimi-k2.5": {
             id: "kimi-k2.5",
             name: "Kimi K2.5",
@@ -7882,35 +7620,35 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
-        "minimax-m2.5": {
-            id: "minimax-m2.5",
-            name: "MiniMax M2.5",
+        "mimo-v2.5-free": {
+            id: "mimo-v2.5-free",
+            name: "MiMo V2.5 Free",
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
-                input: 0.3,
-                output: 1.2,
-                cacheRead: 0.06,
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 204800,
-            maxTokens: 131072,
+            contextWindow: 1000000,
+            maxTokens: 128000,
         },
-        "minimax-m2.5-free": {
-            id: "minimax-m2.5-free",
-            name: "MiniMax M2.5 Free",
-            api: "anthropic-messages",
+        "minimax-m2.5": {
+            id: "minimax-m2.5",
+            name: "MiniMax M2.5",
+            api: "openai-completions",
             provider: "opencode",
-            baseUrl: "https://opencode.ai/zen",
+            baseUrl: "https://opencode.ai/zen/v1",
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
             contextWindow: 204800,
@@ -7984,23 +7722,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
-        "qwen3.6-plus-free": {
-            id: "qwen3.6-plus-free",
-            name: "Qwen3.6 Plus Free",
-            api: "anthropic-messages",
-            provider: "opencode",
-            baseUrl: "https://opencode.ai/zen",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 65536,
-        },
     },
     "opencode-go": {
         "deepseek-v4-flash": {
@@ -8118,9 +7839,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.4,
-                output: 2,
-                cacheRead: 0.08,
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.0028,
                 cacheWrite: 0,
             },
             contextWindow: 1000000,
@@ -8135,9 +7856,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1,
-                output: 3,
-                cacheRead: 0.2,
+                input: 1.74,
+                output: 3.48,
+                cacheRead: 0.0145,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -8213,6 +7934,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
+        "qwen3.7-max": {
+            id: "qwen3.7-max",
+            name: "Qwen3.7 Max",
+            api: "anthropic-messages",
+            provider: "opencode-go",
+            baseUrl: "https://opencode.ai/zen/go",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 2.5,
+                output: 7.5,
+                cacheRead: 0.5,
+                cacheWrite: 3.125,
+            },
+            contextWindow: 1000000,
+            maxTokens: 65536,
+        },
     },
     "openrouter": {
         "ai21/jamba-large-1.7": {
@@ -8232,23 +7970,6 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 4096,
         },
-        "alibaba/tongyi-deepresearch-30b-a3b": {
-            id: "alibaba/tongyi-deepresearch-30b-a3b",
-            name: "Tongyi DeepResearch 30B A3B",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0.09,
-                output: 0.44999999999999996,
-                cacheRead: 0.09,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 131072,
-        },
         "amazon/nova-2-lite-v1": {
             id: "amazon/nova-2-lite-v1",
             name: "Amazon: Nova 2 Lite",
@@ -8559,23 +8280,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 128000,
         },
-        "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: 0.15,
-                output: 0.44999999999999996,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131000,
-            maxTokens: 4096,
-        },
         "arcee-ai/trinity-large-thinking": {
             id: "arcee-ai/trinity-large-thinking",
             name: "Arcee AI: Trinity Large Thinking",
@@ -8593,23 +8297,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 262144,
         },
-        "arcee-ai/trinity-large-thinking:free": {
-            id: "arcee-ai/trinity-large-thinking:free",
-            name: "Arcee AI: Trinity Large Thinking (free)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 80000,
-        },
         "arcee-ai/trinity-mini": {
             id: "arcee-ai/trinity-mini",
             name: "Arcee AI: Trinity Mini",
@@ -8661,23 +8348,6 @@ export const MODELS = {
             contextWindow: 2000000,
             maxTokens: 30000,
         },
-        "baidu/cobuddy:free": {
-            id: "baidu/cobuddy:free",
-            name: "Baidu Qianfan: CoBuddy (free)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 65536,
-        },
         "baidu/ernie-4.5-21b-a3b": {
             id: "baidu/ernie-4.5-21b-a3b",
             name: "Baidu: ERNIE 4.5 21B A3B",
@@ -8823,13 +8493,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.32,
-                output: 0.8899999999999999,
+                input: 0.2288,
+                output: 0.9144,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 163840,
-            maxTokens: 16384,
+            contextWindow: 131072,
+            maxTokens: 16000,
         },
         "deepseek/deepseek-chat-v3-0324": {
             id: "deepseek/deepseek-chat-v3-0324",
@@ -8961,13 +8631,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
             cost: {
-                input: 0.112,
-                output: 0.224,
-                cacheRead: 0.022,
+                input: 0.09999999999999999,
+                output: 0.19999999999999998,
+                cacheRead: 0.02,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 4096,
+            maxTokens: 16384,
         },
         "deepseek/deepseek-v4-flash:free": {
             id: "deepseek/deepseek-v4-flash:free",
@@ -9408,9 +9078,9 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.3,
-                output: 2.5,
-                cacheRead: 0.06,
+                input: 0.075,
+                output: 0.625,
+                cacheRead: 0.015,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -10096,6 +9766,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 262142,
         },
+        "moonshotai/kimi-k2.6:free": {
+            id: "moonshotai/kimi-k2.6:free",
+            name: "MoonshotAI: Kimi K2.6 (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: 4096,
+        },
         "nex-agi/deepseek-v3.1-nex-n1": {
             id: "nex-agi/deepseek-v3.1-nex-n1",
             name: "Nex AGI: DeepSeek V3.1 Nex N1",
@@ -10685,11 +10372,11 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.125,
+                cacheRead: 0.13,
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 16384,
+            maxTokens: 32000,
         },
         "openai/gpt-5.1-codex": {
             id: "openai/gpt-5.1-codex",
@@ -10702,7 +10389,7 @@ export const MODELS = {
             cost: {
                 input: 1.25,
                 output: 10,
-                cacheRead: 0.125,
+                cacheRead: 0.13,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
@@ -10736,11 +10423,11 @@ export const MODELS = {
             cost: {
                 input: 0.25,
                 output: 2,
-                cacheRead: 0.03,
+                cacheRead: 0.024999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 400000,
-            maxTokens: 128000,
+            maxTokens: 100000,
         },
         "openai/gpt-5.2": {
             id: "openai/gpt-5.2",
@@ -10776,7 +10463,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 128000,
-            maxTokens: 32000,
+            maxTokens: 16384,
         },
         "openai/gpt-5.2-codex": {
             id: "openai/gpt-5.2-codex",
@@ -11312,8 +10999,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 8192,
+            contextWindow: 262144,
+            maxTokens: 32768,
         },
         "poolside/laguna-xs.2:free": {
             id: "poolside/laguna-xs.2:free",
@@ -11329,8 +11016,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 8192,
+            contextWindow: 262144,
+            maxTokens: 32768,
         },
         "prime-intellect/intellect-3": {
             id: "prime-intellect/intellect-3",
@@ -11412,7 +11099,7 @@ export const MODELS = {
                 input: 0.26,
                 output: 0.78,
                 cacheRead: 0,
-                cacheWrite: 0.325,
+                cacheWrite: 0,
             },
             contextWindow: 1000000,
             maxTokens: 32768,
@@ -11908,7 +11595,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 65536,
+            maxTokens: 262144,
         },
         "qwen/qwen3.5-27b": {
             id: "qwen/qwen3.5-27b",
@@ -11955,7 +11642,7 @@ export const MODELS = {
             cost: {
                 input: 0.39,
                 output: 2.34,
-                cacheRead: 0.195,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -11990,7 +11677,7 @@ export const MODELS = {
                 input: 0.065,
                 output: 0.26,
                 cacheRead: 0,
-                cacheWrite: 0.08125,
+                cacheWrite: 0,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
@@ -12007,7 +11694,7 @@ export const MODELS = {
                 input: 0.26,
                 output: 1.56,
                 cacheRead: 0,
-                cacheWrite: 0.325,
+                cacheWrite: 0,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
@@ -12024,7 +11711,7 @@ export const MODELS = {
                 input: 0.3,
                 output: 1.7999999999999998,
                 cacheRead: 0,
-                cacheWrite: 0,
+                cacheWrite: 0.375,
             },
             contextWindow: 1000000,
             maxTokens: 65536,
@@ -12038,13 +11725,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.32,
+                input: 0.29,
                 output: 3.1999999999999997,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 81920,
+            maxTokens: 262140,
         },
         "qwen/qwen3.6-35b-a3b": {
             id: "qwen/qwen3.6-35b-a3b",
@@ -12055,13 +11742,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.149,
+                input: 0.14,
                 output: 1,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 262140,
         },
         "qwen/qwen3.6-flash": {
             id: "qwen/qwen3.6-flash",
@@ -12114,6 +11801,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 65536,
         },
+        "qwen/qwen3.7-max": {
+            id: "qwen/qwen3.7-max",
+            name: "Qwen: Qwen3.7 Max",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.25,
+                output: 3.75,
+                cacheRead: 0.25,
+                cacheWrite: 1.5625,
+            },
+            contextWindow: 1000000,
+            maxTokens: 65536,
+        },
         "rekaai/reka-edge": {
             id: "rekaai/reka-edge",
             name: "Reka Edge",
@@ -12191,13 +11895,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.09999999999999999,
+                input: 0.09,
                 output: 0.3,
-                cacheRead: 0,
+                cacheRead: 0.02,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 65536,
+            maxTokens: 16384,
         },
         "tencent/hy3-preview": {
             id: "tencent/hy3-preview",
@@ -12301,6 +12005,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 4096,
         },
+        "x-ai/grok-build-0.1": {
+            id: "x-ai/grok-build-0.1",
+            name: "xAI: Grok Build 0.1",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1,
+                output: 2,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 4096,
+        },
         "xiaomi/mimo-v2-flash": {
             id: "xiaomi/mimo-v2-flash",
             name: "Xiaomi: MiMo-V2-Flash",
@@ -12361,9 +12082,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.39999999999999997,
-                output: 2,
-                cacheRead: 0.08,
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.0028,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -12378,13 +12099,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1,
-                output: 3,
-                cacheRead: 0.19999999999999998,
+                input: 0.435,
+                output: 0.87,
+                cacheRead: 0.0036,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 16384,
+            maxTokens: 131072,
         },
         "z-ai/glm-4-32b": {
             id: "z-ai/glm-4-32b",
@@ -12429,13 +12150,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.13,
-                output: 0.85,
-                cacheRead: 0.024999999999999998,
+                input: 0.125,
+                output: 0.84,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 98304,
+            maxTokens: 131070,
         },
         "z-ai/glm-4.5-air:free": {
             id: "z-ai/glm-4.5-air:free",
@@ -12582,13 +12303,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 0.98,
+                output: 3.08,
+                cacheRead: 0.182,
                 cacheWrite: 0,
             },
-            contextWindow: 202800,
-            maxTokens: 202800,
+            contextWindow: 202752,
+            maxTokens: 4096,
         },
         "z-ai/glm-5v-turbo": {
             id: "z-ai/glm-5v-turbo",
@@ -12877,6 +12598,25 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 500000,
         },
+        "Qwen/Qwen3.7-Max": {
+            id: "Qwen/Qwen3.7-Max",
+            name: "Qwen3.7 Max",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
+            input: ["text"],
+            cost: {
+                input: 2.5,
+                output: 7.5,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 500000,
+        },
         "deepseek-ai/DeepSeek-V3": {
             id: "deepseek-ai/DeepSeek-V3",
             name: "DeepSeek V3",
@@ -13373,6 +13113,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "alibaba/qwen3.7-max": {
+            id: "alibaba/qwen3.7-max",
+            name: "Qwen 3.7 Max",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.25,
+                output: 3.75,
+                cacheRead: 0.25,
+                cacheWrite: 1.5625,
+            },
+            contextWindow: 991000,
+            maxTokens: 64000,
+        },
         "anthropic/claude-3-haiku": {
             id: "anthropic/claude-3-haiku",
             name: "Claude 3 Haiku",
@@ -13481,6 +13238,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "max" },
             input: ["text", "image"],
@@ -13499,6 +13257,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
@@ -13551,6 +13310,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -14261,7 +14021,7 @@ export const MODELS = {
         },
         "minimax/minimax-m2.7": {
             id: "minimax/minimax-m2.7",
-            name: "Minimax M2.7",
+            name: "MiniMax M2.7",
             api: "anthropic-messages",
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
@@ -15444,6 +15204,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 1000000,
         },
+        "xai/grok-build-0.1": {
+            id: "xai/grok-build-0.1",
+            name: "Grok Build 0.1",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1,
+                output: 2,
+                cacheRead: 0.19999999999999998,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
         "xiaomi/mimo-v2-flash": {
             id: "xiaomi/mimo-v2-flash",
             name: "MiMo V2 Flash",
@@ -15487,9 +15264,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.39999999999999997,
-                output: 2,
-                cacheRead: 0.08,
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.0028,
                 cacheWrite: 0,
             },
             contextWindow: 1050000,
@@ -15504,9 +15281,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 1,
-                output: 3,
-                cacheRead: 0.19999999999999998,
+                input: 0.435,
+                output: 0.87,
+                cacheRead: 0.0036,
                 cacheWrite: 0,
             },
             contextWindow: 1050000,
@@ -15735,108 +15512,6 @@ export const MODELS = {
         },
     },
     "xai": {
-        "grok-2": {
-            id: "grok-2",
-            name: "Grok 2",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 2,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "grok-2-1212": {
-            id: "grok-2-1212",
-            name: "Grok 2 (1212)",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 2,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "grok-2-latest": {
-            id: "grok-2-latest",
-            name: "Grok 2 Latest",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 2,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 8192,
-        },
-        "grok-2-vision": {
-            id: "grok-2-vision",
-            name: "Grok 2 Vision",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 2,
-                cacheWrite: 0,
-            },
-            contextWindow: 8192,
-            maxTokens: 4096,
-        },
-        "grok-2-vision-1212": {
-            id: "grok-2-vision-1212",
-            name: "Grok 2 Vision (1212)",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 2,
-                cacheWrite: 0,
-            },
-            contextWindow: 8192,
-            maxTokens: 4096,
-        },
-        "grok-2-vision-latest": {
-            id: "grok-2-vision-latest",
-            name: "Grok 2 Vision Latest",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 2,
-                cacheWrite: 0,
-            },
-            contextWindow: 8192,
-            maxTokens: 4096,
-        },
         "grok-3": {
             id: "grok-3",
             name: "Grok 3",
@@ -15880,8 +15555,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 6,
+                input: 1.25,
+                output: 2.5,
                 cacheRead: 0.2,
                 cacheWrite: 0,
             },
@@ -15897,8 +15572,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 6,
+                input: 1.25,
+                output: 2.5,
                 cacheRead: 0.2,
                 cacheWrite: 0,
             },
@@ -15922,22 +15597,22 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 30000,
         },
-        "grok-beta": {
-            id: "grok-beta",
-            name: "Grok Beta",
+        "grok-build-0.1": {
+            id: "grok-build-0.1",
+            name: "Grok Build 0.1",
             api: "openai-completions",
             provider: "xai",
             baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text"],
+            reasoning: true,
+            input: ["text", "image"],
             cost: {
-                input: 5,
-                output: 15,
-                cacheRead: 5,
+                input: 1,
+                output: 2,
+                cacheRead: 0.2,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 4096,
+            contextWindow: 256000,
+            maxTokens: 256000,
         },
         "grok-code-fast-1": {
             id: "grok-code-fast-1",
@@ -15956,23 +15631,6 @@ export const MODELS = {
             contextWindow: 32768,
             maxTokens: 8192,
         },
-        "grok-vision-beta": {
-            id: "grok-vision-beta",
-            name: "Grok Vision Beta",
-            api: "openai-completions",
-            provider: "xai",
-            baseUrl: "https://api.x.ai/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 5,
-                output: 15,
-                cacheRead: 5,
-                cacheWrite: 0,
-            },
-            contextWindow: 8192,
-            maxTokens: 4096,
-        },
     },
     "xiaomi": {
         "mimo-v2-flash": {