@earendil-works/pi-ai 0.79.3 → 0.79.5

package/dist/models.generated.js

@@ -3810,6 +3810,24 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 131072,
         },
+        "@cf/zai-org/glm-5.2": {
+            id: "@cf/zai-org/glm-5.2",
+            name: "Glm 5.2",
+            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: 1.4,
+                output: 4.4,
+                cacheRead: 0.26,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
     },
     "deepseek": {
         "deepseek-v4-flash": {
@@ -3918,7 +3936,7 @@ export const MODELS = {
             cost: {
                 input: 0.15,
                 output: 0.6,
-                cacheRead: 0.015,
+                cacheRead: 0.01,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
@@ -4191,7 +4209,7 @@ export const MODELS = {
             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, "supportsTemperature": false },
             reasoning: true,
-            thinkingLevelMap: { "xhigh": "xhigh" },
+            thinkingLevelMap: { "xhigh": "xhigh", "minimal": "low" },
             input: ["text", "image"],
             cost: {
                 input: 5,
@@ -4211,7 +4229,7 @@ export const MODELS = {
             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, "supportsTemperature": false },
             reasoning: true,
-            thinkingLevelMap: { "xhigh": "xhigh" },
+            thinkingLevelMap: { "xhigh": "xhigh", "minimal": "low" },
             input: ["text", "image"],
             cost: {
                 input: 5,
@@ -4269,6 +4287,7 @@ export const MODELS = {
             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: { "minimal": "low", "xhigh": "max" },
             input: ["text", "image"],
             cost: {
                 input: 3,
@@ -4765,11 +4784,12 @@ export const MODELS = {
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
             reasoning: true,
+            thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 0.3,
-                output: 2.5,
-                cacheRead: 0.075,
+                input: 1.5,
+                output: 9,
+                cacheRead: 0.15,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -4782,10 +4802,11 @@ export const MODELS = {
             provider: "google",
             baseUrl: "https://generativelanguage.googleapis.com/v1beta",
             reasoning: true,
+            thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 0.1,
-                output: 0.4,
+                input: 0.25,
+                output: 1.5,
                 cacheRead: 0.025,
                 cacheWrite: 0,
             },
@@ -4828,96 +4849,47 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
-    },
-    "google-vertex": {
-        "gemini-1.5-flash": {
-            id: "gemini-1.5-flash",
-            name: "Gemini 1.5 Flash (Vertex)",
-            api: "google-vertex",
-            provider: "google-vertex",
-            baseUrl: "https://{location}-aiplatform.googleapis.com",
-            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 (Vertex)",
-            api: "google-vertex",
-            provider: "google-vertex",
-            baseUrl: "https://{location}-aiplatform.googleapis.com",
-            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 (Vertex)",
-            api: "google-vertex",
-            provider: "google-vertex",
-            baseUrl: "https://{location}-aiplatform.googleapis.com",
-            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 (Vertex)",
-            api: "google-vertex",
-            provider: "google-vertex",
-            baseUrl: "https://{location}-aiplatform.googleapis.com",
-            reasoning: false,
+        "gemma-4-E2B-it": {
+            id: "gemma-4-E2B-it",
+            name: "Gemma 4 E2B IT",
+            api: "google-generative-ai",
+            provider: "google",
+            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": null, "medium": null, "high": "HIGH" },
             input: ["text", "image"],
             cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0.0375,
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 1048576,
+            contextWindow: 131072,
             maxTokens: 8192,
         },
-        "gemini-2.0-flash-lite": {
-            id: "gemini-2.0-flash-lite",
-            name: "Gemini 2.0 Flash Lite (Vertex)",
-            api: "google-vertex",
-            provider: "google-vertex",
-            baseUrl: "https://{location}-aiplatform.googleapis.com",
+        "gemma-4-E4B-it": {
+            id: "gemma-4-E4B-it",
+            name: "Gemma 4 E4B IT",
+            api: "google-generative-ai",
+            provider: "google",
+            baseUrl: "https://generativelanguage.googleapis.com/v1beta",
             reasoning: true,
+            thinkingLevelMap: { "off": null, "minimal": "MINIMAL", "low": null, "medium": null, "high": "HIGH" },
             input: ["text", "image"],
             cost: {
-                input: 0.075,
-                output: 0.3,
-                cacheRead: 0.01875,
+                input: 0,
+                output: 0,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 1048576,
-            maxTokens: 65536,
+            contextWindow: 131072,
+            maxTokens: 8192,
         },
+    },
+    "google-vertex": {
         "gemini-2.5-flash": {
             id: "gemini-2.5-flash",
-            name: "Gemini 2.5 Flash (Vertex)",
+            name: "Gemini 2.5 Flash",
             api: "google-vertex",
             provider: "google-vertex",
             baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -4934,24 +4906,7 @@ export const MODELS = {
         },
         "gemini-2.5-flash-lite": {
             id: "gemini-2.5-flash-lite",
-            name: "Gemini 2.5 Flash Lite (Vertex)",
-            api: "google-vertex",
-            provider: "google-vertex",
-            baseUrl: "https://{location}-aiplatform.googleapis.com",
-            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-09-2025": {
-            id: "gemini-2.5-flash-lite-preview-09-2025",
-            name: "Gemini 2.5 Flash Lite Preview 09-25 (Vertex)",
+            name: "Gemini 2.5 Flash-Lite",
             api: "google-vertex",
             provider: "google-vertex",
             baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -4968,7 +4923,7 @@ export const MODELS = {
         },
         "gemini-2.5-pro": {
             id: "gemini-2.5-pro",
-            name: "Gemini 2.5 Pro (Vertex)",
+            name: "Gemini 2.5 Pro",
             api: "google-vertex",
             provider: "google-vertex",
             baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -4985,7 +4940,7 @@ export const MODELS = {
         },
         "gemini-3-flash-preview": {
             id: "gemini-3-flash-preview",
-            name: "Gemini 3 Flash Preview (Vertex)",
+            name: "Gemini 3 Flash Preview",
             api: "google-vertex",
             provider: "google-vertex",
             baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -5001,27 +4956,27 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
-        "gemini-3-pro-preview": {
-            id: "gemini-3-pro-preview",
-            name: "Gemini 3 Pro Preview (Vertex)",
+        "gemini-3.1-flash-lite": {
+            id: "gemini-3.1-flash-lite",
+            name: "Gemini 3.1 Flash Lite",
             api: "google-vertex",
             provider: "google-vertex",
             baseUrl: "https://{location}-aiplatform.googleapis.com",
             reasoning: true,
-            thinkingLevelMap: { "off": null, "minimal": null, "low": "LOW", "medium": null, "high": "HIGH" },
+            thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 12,
-                cacheRead: 0.2,
+                input: 0.25,
+                output: 1.5,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
-            contextWindow: 1000000,
-            maxTokens: 64000,
+            contextWindow: 1048576,
+            maxTokens: 65536,
         },
         "gemini-3.1-pro-preview": {
             id: "gemini-3.1-pro-preview",
-            name: "Gemini 3.1 Pro Preview (Vertex)",
+            name: "Gemini 3.1 Pro Preview",
             api: "google-vertex",
             provider: "google-vertex",
             baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -5039,7 +4994,7 @@ export const MODELS = {
         },
         "gemini-3.1-pro-preview-customtools": {
             id: "gemini-3.1-pro-preview-customtools",
-            name: "Gemini 3.1 Pro Preview Custom Tools (Vertex)",
+            name: "Gemini 3.1 Pro Preview Custom Tools",
             api: "google-vertex",
             provider: "google-vertex",
             baseUrl: "https://{location}-aiplatform.googleapis.com",
@@ -5055,6 +5010,60 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 65536,
         },
+        "gemini-3.5-flash": {
+            id: "gemini-3.5-flash",
+            name: "Gemini 3.5 Flash",
+            api: "google-vertex",
+            provider: "google-vertex",
+            baseUrl: "https://{location}-aiplatform.googleapis.com",
+            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",
+            api: "google-vertex",
+            provider: "google-vertex",
+            baseUrl: "https://{location}-aiplatform.googleapis.com",
+            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-lite-latest": {
+            id: "gemini-flash-lite-latest",
+            name: "Gemini Flash-Lite Latest",
+            api: "google-vertex",
+            provider: "google-vertex",
+            baseUrl: "https://{location}-aiplatform.googleapis.com",
+            reasoning: true,
+            thinkingLevelMap: { "off": null },
+            input: ["text", "image"],
+            cost: {
+                input: 0.25,
+                output: 1.5,
+                cacheRead: 0.025,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 65536,
+        },
     },
     "groq": {
         "llama-3.1-8b-instant": {
@@ -6385,6 +6394,7 @@ export const MODELS = {
             baseUrl: "https://api.moonshot.ai/v1",
             compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "thinkingFormat": "deepseek" },
             reasoning: true,
+            thinkingLevelMap: { "off": null },
             input: ["text", "image"],
             cost: {
                 input: 0.95,
@@ -6395,6 +6405,25 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 262144,
         },
+        "kimi-k2.7-code-highspeed": {
+            id: "kimi-k2.7-code-highspeed",
+            name: "Kimi K2.7 Code HighSpeed",
+            api: "openai-completions",
+            provider: "moonshotai",
+            baseUrl: "https://api.moonshot.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "thinkingFormat": "deepseek" },
+            reasoning: true,
+            thinkingLevelMap: { "off": null },
+            input: ["text", "image"],
+            cost: {
+                input: 1.9,
+                output: 8,
+                cacheRead: 0.38,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
     },
     "moonshotai-cn": {
         "kimi-k2-0711-preview": {
@@ -6523,6 +6552,44 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 262144,
         },
+        "kimi-k2.7-code": {
+            id: "kimi-k2.7-code",
+            name: "Kimi K2.7 Code",
+            api: "openai-completions",
+            provider: "moonshotai-cn",
+            baseUrl: "https://api.moonshot.cn/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "thinkingFormat": "deepseek" },
+            reasoning: true,
+            thinkingLevelMap: { "off": null },
+            input: ["text", "image"],
+            cost: {
+                input: 0.95,
+                output: 4,
+                cacheRead: 0.19,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
+        "kimi-k2.7-code-highspeed": {
+            id: "kimi-k2.7-code-highspeed",
+            name: "Kimi K2.7 Code HighSpeed",
+            api: "openai-completions",
+            provider: "moonshotai-cn",
+            baseUrl: "https://api.moonshot.cn/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "thinkingFormat": "deepseek" },
+            reasoning: true,
+            thinkingLevelMap: { "off": null },
+            input: ["text", "image"],
+            cost: {
+                input: 1.9,
+                output: 8,
+                cacheRead: 0.38,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 262144,
+        },
     },
     "nvidia": {
         "meta/llama-3.1-70b-instruct": {
@@ -7886,7 +7953,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
-            compat: { "maxTokensField": "max_tokens", "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            compat: { "maxTokensField": "max_tokens", "supportsLongCacheRetention": false, "requiresReasoningContentOnAssistantMessages": true },
             reasoning: true,
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
@@ -7905,7 +7972,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
-            compat: { "maxTokensField": "max_tokens", "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            compat: { "maxTokensField": "max_tokens", "requiresReasoningContentOnAssistantMessages": true },
             reasoning: true,
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
@@ -7924,7 +7991,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
-            compat: { "maxTokensField": "max_tokens", "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            compat: { "maxTokensField": "max_tokens", "supportsLongCacheRetention": false, "requiresReasoningContentOnAssistantMessages": true },
             reasoning: true,
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
@@ -8340,7 +8407,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
-            compat: { "maxTokensField": "max_tokens" },
+            compat: { "maxTokensField": "max_tokens", "supportsLongCacheRetention": false },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -8358,7 +8425,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
-            compat: { "thinkingFormat": "deepseek", "supportsReasoningEffort": false, "maxTokensField": "max_tokens" },
+            compat: { "thinkingFormat": "deepseek", "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsLongCacheRetention": false },
             reasoning: true,
             input: ["text", "image"],
             cost: {
@@ -8412,7 +8479,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
-            compat: { "maxTokensField": "max_tokens" },
+            compat: { "maxTokensField": "max_tokens", "supportsLongCacheRetention": false },
             reasoning: true,
             input: ["text"],
             cost: {
@@ -8502,7 +8569,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
-            compat: { "maxTokensField": "max_tokens", "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            compat: { "maxTokensField": "max_tokens", "requiresReasoningContentOnAssistantMessages": true },
             reasoning: true,
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
@@ -8521,7 +8588,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
-            compat: { "maxTokensField": "max_tokens", "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            compat: { "maxTokensField": "max_tokens", "requiresReasoningContentOnAssistantMessages": true },
             reasoning: true,
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
             input: ["text"],
@@ -8576,7 +8643,7 @@ export const MODELS = {
             api: "openai-completions",
             provider: "opencode-go",
             baseUrl: "https://opencode.ai/zen/go/v1",
-            compat: { "thinkingFormat": "deepseek", "supportsReasoningEffort": false, "maxTokensField": "max_tokens" },
+            compat: { "thinkingFormat": "deepseek", "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsLongCacheRetention": false },
             reasoning: true,
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
             input: ["text", "image"],
@@ -10470,13 +10537,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.95,
-                output: 4,
-                cacheRead: 0.19,
+                input: 0.75,
+                output: 3.5,
+                cacheRead: 0.16,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 262144,
         },
         "nex-agi/nex-n2-pro:free": {
             id: "nex-agi/nex-n2-pro:free",
@@ -12273,7 +12340,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 262144,
+            maxTokens: 81920,
         },
         "qwen/qwen3.5-397b-a17b": {
             id: "qwen/qwen3.5-397b-a17b",
@@ -12284,13 +12351,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.39,
-                output: 2.34,
+                input: 0.385,
+                output: 2.45,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
-            maxTokens: 65536,
+            contextWindow: 256000,
+            maxTokens: 4096,
         },
         "qwen/qwen3.5-9b": {
             id: "qwen/qwen3.5-9b",
@@ -12573,13 +12640,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.063,
-                output: 0.21,
-                cacheRead: 0.021,
+                input: 0.066,
+                output: 0.26,
+                cacheRead: 0.029,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 4096,
+            maxTokens: 262144,
         },
         "thedrummer/rocinante-12b": {
             id: "thedrummer/rocinante-12b",
@@ -12760,13 +12827,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.125,
+                input: 0.13,
                 output: 0.85,
-                cacheRead: 0.06,
+                cacheRead: 0.025,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 131070,
+            maxTokens: 98304,
         },
         "z-ai/glm-4.5v": {
             id: "z-ai/glm-4.5v",
@@ -12904,6 +12971,23 @@ export const MODELS = {
             contextWindow: 202752,
             maxTokens: 4096,
         },
+        "z-ai/glm-5.2": {
+            id: "z-ai/glm-5.2",
+            name: "Z.ai: GLM 5.2",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.4,
+                output: 4.4,
+                cacheRead: 0.26,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
         "~anthropic/claude-fable-latest": {
             id: "~anthropic/claude-fable-latest",
             name: "Anthropic: Claude Fable Latest",
@@ -13200,8 +13284,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 2.5,
-                output: 7.5,
+                input: 1.25,
+                output: 3.75,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -13301,6 +13385,25 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 131000,
         },
+        "moonshotai/Kimi-K2.7-Code": {
+            id: "moonshotai/Kimi-K2.7-Code",
+            name: "Kimi K2.7 Code",
+            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: 0.95,
+                output: 4,
+                cacheRead: 0.19,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 131072,
+        },
         "nvidia/nemotron-3-ultra-550b-a55b": {
             id: "nvidia/nemotron-3-ultra-550b-a55b",
             name: "Nemotron 3 Ultra 550B A55B",
@@ -14986,6 +15089,23 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 32768,
         },
+        "moonshotai/kimi-k2.7-code-highspeed": {
+            id: "moonshotai/kimi-k2.7-code-highspeed",
+            name: "Kimi K2.7 Code High Speed",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 1.9,
+                output: 8,
+                cacheRead: 0.38,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 4096,
+        },
         "nvidia/nemotron-3-super-120b-a12b": {
             id: "nvidia/nemotron-3-super-120b-a12b",
             name: "NVIDIA Nemotron 3 Super 120B A12B",
@@ -16222,6 +16342,23 @@ export const MODELS = {
             contextWindow: 202800,
             maxTokens: 64000,
         },
+        "zai/glm-5.2": {
+            id: "zai/glm-5.2",
+            name: "GLM 5.2",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.4,
+                output: 4.4,
+                cacheRead: 0.26,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 128000,
+        },
         "zai/glm-5v-turbo": {
             id: "zai/glm-5v-turbo",
             name: "GLM 5V Turbo",
@@ -16820,6 +16957,25 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 131072,
         },
+        "glm-5.2": {
+            id: "glm-5.2",
+            name: "GLM-5.2",
+            api: "openai-completions",
+            provider: "zai",
+            baseUrl: "https://api.z.ai/api/coding/paas/v4",
+            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "supportsReasoningEffort": true, "zaiToolStream": true },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": "high", "medium": "high", "high": "high", "xhigh": "max" },
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
         "glm-5v-turbo": {
             id: "glm-5v-turbo",
             name: "GLM-5V-Turbo",
@@ -16912,6 +17068,25 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 131072,
         },
+        "glm-5.2": {
+            id: "glm-5.2",
+            name: "GLM-5.2",
+            api: "openai-completions",
+            provider: "zai-coding-cn",
+            baseUrl: "https://open.bigmodel.cn/api/coding/paas/v4",
+            compat: { "supportsDeveloperRole": false, "thinkingFormat": "zai", "supportsReasoningEffort": true, "zaiToolStream": true },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": "high", "medium": "high", "high": "high", "xhigh": "max" },
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
         "glm-5v-turbo": {
             id: "glm-5v-turbo",
             name: "GLM-5V-Turbo",