@entelligentsia/forgecli 0.15.0 → 0.20.0

package/node_modules/@earendil-works/pi-ai/dist/models.generated.js

@@ -908,8 +908,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 256000,
+            contextWindow: 262143,
+            maxTokens: 16000,
         },
         "moonshotai.kimi-k2.5": {
             id: "moonshotai.kimi-k2.5",
@@ -925,8 +925,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 256000,
+            contextWindow: 262143,
+            maxTokens: 16000,
         },
         "nvidia.nemotron-nano-12b-v2": {
             id: "nvidia.nemotron-nano-12b-v2",
@@ -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: {
@@ -2823,6 +2826,7 @@ 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 +2845,7 @@ 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 +2898,7 @@ 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 +3281,42 @@ 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 +3332,27 @@ 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 +3386,7 @@ export const MODELS = {
                 cacheRead: 0.16,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
+            contextWindow: 262144,
             maxTokens: 256000,
         },
         "@cf/nvidia/nemotron-3-120b-a12b": {
@@ -3383,6 +3443,24 @@ 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 +3471,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.06,
+                input: 0.0605,
                 output: 0.4,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -3443,27 +3521,9 @@ 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",
+        "accounts/fireworks/models/deepseek-v4-flash": {
+            id: "accounts/fireworks/models/deepseek-v4-flash",
+            name: "DeepSeek V4 Flash",
             api: "anthropic-messages",
             provider: "fireworks",
             baseUrl: "https://api.fireworks.ai/inference",
@@ -3471,13 +3531,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.56,
-                output: 1.68,
-                cacheRead: 0.28,
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
-            contextWindow: 160000,
-            maxTokens: 160000,
+            contextWindow: 1000000,
+            maxTokens: 384000,
         },
         "accounts/fireworks/models/deepseek-v4-pro": {
             id: "accounts/fireworks/models/deepseek-v4-pro",
@@ -3491,84 +3551,12 @@ 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",
@@ -3599,7 +3587,7 @@ export const MODELS = {
             cost: {
                 input: 0.15,
                 output: 0.6,
-                cacheRead: 0,
+                cacheRead: 0.015,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -3615,50 +3603,14 @@ 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",
@@ -3695,24 +3647,6 @@ 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",
@@ -3743,7 +3677,7 @@ export const MODELS = {
             cost: {
                 input: 0.3,
                 output: 1.2,
-                cacheRead: 0.03,
+                cacheRead: 0.06,
                 cacheWrite: 0,
             },
             contextWindow: 196608,
@@ -3767,9 +3701,27 @@ 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",
@@ -3777,13 +3729,13 @@ 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": {
@@ -3831,6 +3783,7 @@ 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"],
@@ -3850,6 +3803,7 @@ 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"],
@@ -3888,6 +3842,7 @@ 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: {
@@ -3956,6 +3911,25 @@ 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",
@@ -4137,68 +4111,17 @@ export const MODELS = {
             compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false },
             reasoning: true,
             input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 64000,
-        },
-    },
-    "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,
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 8192,
+            contextWindow: 128000,
+            maxTokens: 64000,
         },
+    },
+    "google": {
         "gemini-2.0-flash": {
             id: "gemini-2.0-flash",
             name: "Gemini 2.0 Flash",
@@ -4218,7 +4141,7 @@ 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",
@@ -4252,7 +4175,7 @@ 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",
@@ -4267,91 +4190,6 @@ export const MODELS = {
             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",
@@ -4369,40 +4207,6 @@ export const MODELS = {
             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,
-                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",
-            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,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 65536,
-        },
         "gemini-3-flash-preview": {
             id: "gemini-3-flash-preview",
             name: "Gemini 3 Flash Preview",
@@ -4436,8 +4240,8 @@ 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",
@@ -4511,6 +4315,24 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
+        "gemini-3.5-flash": {
+            id: "gemini-3.5-flash",
+            name: "Gemini 3.5 Flash",
+            api: "google-generative-ai",
+            provider: "google",
+            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+            reasoning: true,
+            thinkingLevelMap: { "off": null },
+            input: ["text", "image"],
+            cost: {
+                input: 1.5,
+                output: 9,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
         "gemini-flash-latest": {
             id: "gemini-flash-latest",
             name: "Gemini Flash Latest",
@@ -4545,60 +4367,9 @@ 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",
@@ -4611,12 +4382,12 @@ 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",
@@ -4629,8 +4400,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 256000,
-            maxTokens: 8192,
+            contextWindow: 262144,
+            maxTokens: 32768,
         },
     },
     "google-vertex": {
@@ -7336,6 +7107,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "max" },
             input: ["text", "image"],
@@ -7354,6 +7126,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
@@ -7406,6 +7179,7 @@ export const MODELS = {
             api: "anthropic-messages",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen",
+            compat: { "forceAdaptiveThinking": true },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -7472,6 +7246,24 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
+        "gemini-3.5-flash": {
+            id: "gemini-3.5-flash",
+            name: "Gemini 3.5 Flash",
+            api: "google-generative-ai",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            thinkingLevelMap: { "off": null },
+            input: ["text", "image"],
+            cost: {
+                input: 1.5,
+                output: 9,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
         "glm-5": {
             id: "glm-5",
             name: "GLM-5",
@@ -7794,6 +7586,23 @@ 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",
@@ -7845,23 +7654,6 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131072,
         },
-        "minimax-m2.5-free": {
-            id: "minimax-m2.5-free",
-            name: "MiniMax M2.5 Free",
-            api: "anthropic-messages",
-            provider: "opencode",
-            baseUrl: "https://opencode.ai/zen",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 204800,
-            maxTokens: 131072,
-        },
         "minimax-m2.7": {
             id: "minimax-m2.7",
             name: "MiniMax M2.7",
@@ -7930,23 +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": {
@@ -8505,23 +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",
@@ -8907,13 +8665,13 @@ 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",
@@ -8984,7 +8742,7 @@ export const MODELS = {
                 cacheRead: 0.024999999999999998,
                 cacheWrite: 0.08333333333333334,
             },
-            contextWindow: 1048576,
+            contextWindow: 1000000,
             maxTokens: 8192,
         },
         "google/gemini-2.0-flash-lite-001": {
@@ -9191,6 +8949,23 @@ export const MODELS = {
             contextWindow: 1048756,
             maxTokens: 65536,
         },
+        "google/gemini-3.5-flash": {
+            id: "google/gemini-3.5-flash",
+            name: "Google: Gemini 3.5 Flash",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.5,
+                output: 9,
+                cacheRead: 0.15,
+                cacheWrite: 0.08333333333333334,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
         "google/gemma-3-12b-it": {
             id: "google/gemma-3-12b-it",
             name: "Google: Gemma 3 12B",
@@ -9337,9 +9112,9 @@ 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,
@@ -11837,7 +11612,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 65536,
+            maxTokens: 262144,
         },
         "qwen/qwen3.5-27b": {
             id: "qwen/qwen3.5-27b",
@@ -11865,13 +11640,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.14,
+                input: 0.13899999999999998,
                 output: 1,
-                cacheRead: 0.049999999999999996,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 81920,
+            maxTokens: 4096,
         },
         "qwen/qwen3.5-397b-a17b": {
             id: "qwen/qwen3.5-397b-a17b",
@@ -11884,7 +11659,7 @@ export const MODELS = {
             cost: {
                 input: 0.39,
                 output: 2.34,
-                cacheRead: 0.195,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -11967,13 +11742,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.32,
+                input: 0.3,
                 output: 3.1999999999999997,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 81920,
+            maxTokens: 262144,
         },
         "qwen/qwen3.6-35b-a3b": {
             id: "qwen/qwen3.6-35b-a3b",
@@ -11986,11 +11761,11 @@ export const MODELS = {
             cost: {
                 input: 0.15,
                 output: 1,
-                cacheRead: 0.049999999999999996,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 262140,
         },
         "qwen/qwen3.6-flash": {
             id: "qwen/qwen3.6-flash",
@@ -12043,6 +11818,23 @@ 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: 2.5,
+                output: 7.5,
+                cacheRead: 0,
+                cacheWrite: 3.125,
+            },
+            contextWindow: 1000000,
+            maxTokens: 65536,
+        },
         "rekaai/reka-edge": {
             id: "rekaai/reka-edge",
             name: "Reka Edge",
@@ -12120,13 +11912,13 @@ 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",
@@ -12230,6 +12022,23 @@ 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",
@@ -12596,9 +12405,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.5,
-                output: 3,
-                cacheRead: 0.049999999999999996,
+                input: 1.5,
+                output: 9,
+                cacheRead: 0.15,
                 cacheWrite: 0.08333333333333334,
             },
             contextWindow: 1048576,
@@ -12806,6 +12615,25 @@ 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",
@@ -13302,6 +13130,23 @@ 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",
@@ -13410,6 +13255,7 @@ 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"],
@@ -13428,6 +13274,7 @@ 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"],
@@ -13480,6 +13327,7 @@ 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: {
@@ -13865,6 +13713,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 64000,
         },
+        "google/gemini-3.5-flash": {
+            id: "google/gemini-3.5-flash",
+            name: "Gemini 3.5 Flash",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.5,
+                output: 9,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 64000,
+        },
         "google/gemma-4-26b-a4b-it": {
             id: "google/gemma-4-26b-a4b-it",
             name: "Gemma 4 26B A4B IT",
@@ -14173,7 +14038,7 @@ 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",
@@ -14324,6 +14189,23 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 64000,
         },
+        "mistral/mistral-medium-3.5": {
+            id: "mistral/mistral-medium-3.5",
+            name: "Mistral Medium Latest",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.5,
+                output: 7.5,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 256000,
+            maxTokens: 256000,
+        },
         "mistral/mistral-small": {
             id: "mistral/mistral-small",
             name: "Mistral Small",
@@ -15339,6 +15221,23 @@ 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",
@@ -15630,108 +15529,6 @@ 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",
@@ -15775,8 +15572,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 6,
+                input: 1.25,
+                output: 2.5,
                 cacheRead: 0.2,
                 cacheWrite: 0,
             },
@@ -15792,8 +15589,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 6,
+                input: 1.25,
+                output: 2.5,
                 cacheRead: 0.2,
                 cacheWrite: 0,
             },
@@ -15817,22 +15614,22 @@ 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",
@@ -15851,23 +15648,6 @@ 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": {