@dreb/ai 2.64.3 → 2.64.5

package/dist/models.generated.js

@@ -852,6 +852,23 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "global.xai.grok-4.6": {
+            id: "global.xai.grok-4.6",
+            name: "Grok 4.6 (Global)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 6,
+                cacheRead: 0.5,
+                cacheWrite: 0,
+            },
+            contextWindow: 500000,
+            maxTokens: 500000,
+        },
         "google.gemma-3-27b-it": {
             id: "google.gemma-3-27b-it",
             name: "Google Gemma 3 27B Instruct",
@@ -1957,6 +1974,23 @@ export const MODELS = {
             contextWindow: 3500000,
             maxTokens: 16384,
         },
+        "us.xai.grok-4.6": {
+            id: "us.xai.grok-4.6",
+            name: "Grok 4.6 (US)",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2.2,
+                output: 6.6,
+                cacheRead: 0.55,
+                cacheWrite: 0,
+            },
+            contextWindow: 500000,
+            maxTokens: 500000,
+        },
         "writer.palmyra-x4-v1:0": {
             id: "writer.palmyra-x4-v1:0",
             name: "Palmyra X4",
@@ -2896,6 +2930,23 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "gpt-6-astra": {
+            id: "gpt-6-astra",
+            name: "GPT-6 Astra",
+            api: "azure-openai-responses",
+            provider: "azure-openai-responses",
+            baseUrl: "",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 10,
+                output: 50,
+                cacheRead: 1,
+                cacheWrite: 12.5,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
         "gpt-realtime-2.1": {
             id: "gpt-realtime-2.1",
             name: "GPT-Realtime-2.1",
@@ -3017,39 +3068,39 @@ export const MODELS = {
         },
     },
     "cerebras": {
-        "gemma-4-31b": {
-            id: "gemma-4-31b",
-            name: "Gemma 4 31B IT",
+        "gpt-oss-120b": {
+            id: "gpt-oss-120b",
+            name: "GPT OSS 120B",
             api: "openai-completions",
             provider: "cerebras",
             baseUrl: "https://api.cerebras.ai/v1",
             reasoning: true,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
-                input: 0.99,
-                output: 1.49,
+                input: 0.35,
+                output: 0.75,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
             maxTokens: 40960,
         },
-        "gpt-oss-120b": {
-            id: "gpt-oss-120b",
-            name: "GPT OSS 120B",
+        "qwen-3.8-27b": {
+            id: "qwen-3.8-27b",
+            name: "Qwen3.8 27B",
             api: "openai-completions",
             provider: "cerebras",
             baseUrl: "https://api.cerebras.ai/v1",
             reasoning: true,
-            input: ["text"],
+            input: ["text", "image"],
             cost: {
-                input: 0.35,
-                output: 0.75,
+                input: 0.99,
+                output: 1.49,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 131072,
-            maxTokens: 40960,
+            contextWindow: 65536,
+            maxTokens: 32768,
         },
     },
     "github-copilot": {
@@ -3439,6 +3490,24 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "gpt-6-astra": {
+            id: "gpt-6-astra",
+            name: "GPT-6 Astra",
+            api: "openai-responses",
+            provider: "github-copilot",
+            baseUrl: "https://api.individual.githubcopilot.com",
+            headers: { "User-Agent": "GitHubCopilotChat/0.35.0", "Editor-Version": "vscode/1.107.0", "Editor-Plugin-Version": "copilot-chat/0.35.0", "Copilot-Integration-Id": "vscode-chat" },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 10,
+                output: 50,
+                cacheRead: 1,
+                cacheWrite: 12.5,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
         "grok-4.5": {
             id: "grok-4.5",
             name: "Grok 4.5",
@@ -7136,6 +7205,23 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "gpt-6-astra": {
+            id: "gpt-6-astra",
+            name: "GPT-6 Astra",
+            api: "openai-responses",
+            provider: "openai",
+            baseUrl: "https://api.openai.com/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 10,
+                output: 50,
+                cacheRead: 1,
+                cacheWrite: 12.5,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
         "gpt-realtime-2.1": {
             id: "gpt-realtime-2.1",
             name: "GPT-Realtime-2.1",
@@ -7257,108 +7343,6 @@ export const MODELS = {
         },
     },
     "openai-codex": {
-        "gpt-5.1": {
-            id: "gpt-5.1",
-            name: "GPT-5.1",
-            api: "openai-codex-responses",
-            provider: "openai-codex",
-            baseUrl: "https://chatgpt.com/backend-api",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1.25,
-                output: 10,
-                cacheRead: 0.125,
-                cacheWrite: 0,
-            },
-            contextWindow: 272000,
-            maxTokens: 128000,
-        },
-        "gpt-5.1-codex-max": {
-            id: "gpt-5.1-codex-max",
-            name: "GPT-5.1 Codex Max",
-            api: "openai-codex-responses",
-            provider: "openai-codex",
-            baseUrl: "https://chatgpt.com/backend-api",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1.25,
-                output: 10,
-                cacheRead: 0.125,
-                cacheWrite: 0,
-            },
-            contextWindow: 272000,
-            maxTokens: 128000,
-        },
-        "gpt-5.1-codex-mini": {
-            id: "gpt-5.1-codex-mini",
-            name: "GPT-5.1 Codex Mini",
-            api: "openai-codex-responses",
-            provider: "openai-codex",
-            baseUrl: "https://chatgpt.com/backend-api",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.25,
-                output: 2,
-                cacheRead: 0.025,
-                cacheWrite: 0,
-            },
-            contextWindow: 272000,
-            maxTokens: 128000,
-        },
-        "gpt-5.3-codex": {
-            id: "gpt-5.3-codex",
-            name: "GPT-5.3 Codex",
-            api: "openai-codex-responses",
-            provider: "openai-codex",
-            baseUrl: "https://chatgpt.com/backend-api",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 1.75,
-                output: 14,
-                cacheRead: 0.175,
-                cacheWrite: 0,
-            },
-            contextWindow: 272000,
-            maxTokens: 128000,
-        },
-        "gpt-5.3-codex-spark": {
-            id: "gpt-5.3-codex-spark",
-            name: "GPT-5.3 Codex Spark",
-            api: "openai-codex-responses",
-            provider: "openai-codex",
-            baseUrl: "https://chatgpt.com/backend-api",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 128000,
-            maxTokens: 128000,
-        },
-        "gpt-5.4": {
-            id: "gpt-5.4",
-            name: "GPT-5.4",
-            api: "openai-codex-responses",
-            provider: "openai-codex",
-            baseUrl: "https://chatgpt.com/backend-api",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 2.5,
-                output: 15,
-                cacheRead: 0.25,
-                cacheWrite: 0,
-            },
-            contextWindow: 272000,
-            maxTokens: 128000,
-        },
         "gpt-5.4-mini": {
             id: "gpt-5.4-mini",
             name: "GPT-5.4 Mini",
@@ -7444,6 +7428,23 @@ export const MODELS = {
             contextWindow: 372000,
             maxTokens: 128000,
         },
+        "gpt-6-astra": {
+            id: "gpt-6-astra",
+            name: "GPT-6 Astra",
+            api: "openai-codex-responses",
+            provider: "openai-codex",
+            baseUrl: "https://chatgpt.com/backend-api",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 10,
+                output: 50,
+                cacheRead: 1,
+                cacheWrite: 12.5,
+            },
+            contextWindow: 272000,
+            maxTokens: 128000,
+        },
     },
     "opencode": {
         "big-pickle": {
@@ -7684,6 +7685,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 384000,
         },
+        "deepseek-v4-flash-vision-exp": {
+            id: "deepseek-v4-flash-vision-exp",
+            name: "DeepSeek V4 Flash Vision Exp",
+            api: "openai-completions",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.14,
+                output: 0.28,
+                cacheRead: 0.028,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
         "deepseek-v4-pro": {
             id: "deepseek-v4-pro",
             name: "DeepSeek V4 Pro",
@@ -7871,6 +7889,40 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 131072,
         },
+        "glm-5.3": {
+            id: "glm-5.3",
+            name: "GLM-5.3",
+            api: "openai-completions",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.4,
+                output: 4.4,
+                cacheRead: 0.26,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
+        "glm-5.3-flash": {
+            id: "glm-5.3-flash",
+            name: "GLM-5.3-Flash",
+            api: "openai-completions",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.15,
+                output: 0.5,
+                cacheRead: 0.03,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
         "gpt-5": {
             id: "gpt-5",
             name: "GPT-5",
@@ -8194,6 +8246,23 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "gpt-6-astra": {
+            id: "gpt-6-astra",
+            name: "GPT-6 Astra",
+            api: "openai-responses",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 10,
+                output: 50,
+                cacheRead: 1,
+                cacheWrite: 12.5,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
         "grok-4.5": {
             id: "grok-4.5",
             name: "Grok 4.5",
@@ -8415,18 +8484,35 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 131072,
         },
-        "muse-spark-1.2-contributor-free": {
-            id: "muse-spark-1.2-contributor-free",
-            name: "Muse Spark 1.2 Free",
+        "muse-spark-1.2-contributor-free": {
+            id: "muse-spark-1.2-contributor-free",
+            name: "Muse Spark 1.2 Free",
+            api: "openai-responses",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
+        "muse-spark-1.3": {
+            id: "muse-spark-1.3",
+            name: "Muse Spark 1.3",
             api: "openai-responses",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
+                input: 1.25,
+                output: 4.25,
+                cacheRead: 0.15,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -9788,9 +9874,9 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.25,
-                output: 1,
-                cacheRead: 0,
+                input: 0.29,
+                output: 1.1400000000000001,
+                cacheRead: 0.11,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
@@ -9805,13 +9891,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.55,
-                output: 1.6500000000000001,
-                cacheRead: 0.55,
+                input: 0.25,
+                output: 0.95,
+                cacheRead: 0.13,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 144900,
+            maxTokens: 32768,
         },
         "deepseek/deepseek-r1": {
             id: "deepseek/deepseek-r1",
@@ -9907,9 +9993,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.0875,
-                output: 0.175,
-                cacheRead: 0.0175,
+                input: 0.088606,
+                output: 0.177212,
+                cacheRead: 0.017721200000000003,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -9975,9 +10061,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.9918,
-                output: 1.9836,
-                cacheRead: 0.08265,
+                input: 0.9552599999999999,
+                output: 1.9105199999999998,
+                cacheRead: 0.07960500000000001,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -9992,9 +10078,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.57948,
-                output: 1.73844,
-                cacheRead: 0.019316,
+                input: 1.0494,
+                output: 3.1482,
+                cacheRead: 0.03498,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -11012,7 +11098,7 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.55,
+                input: 0.39999999999999997,
                 output: 2.2,
                 cacheRead: 0,
                 cacheWrite: 0,
@@ -11088,23 +11174,6 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131072,
         },
-        "minimax/minimax-m2.7:free": {
-            id: "minimax/minimax-m2.7:free",
-            name: "MiniMax: MiniMax M2.7 (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: 196608,
-            maxTokens: 176947,
-        },
         "minimax/minimax-m3": {
             id: "minimax/minimax-m3",
             name: "MiniMax: MiniMax M3",
@@ -11139,23 +11208,6 @@ export const MODELS = {
             contextWindow: 524288,
             maxTokens: 471859,
         },
-        "minimax/minimax-m3:free": {
-            id: "minimax/minimax-m3:free",
-            name: "MiniMax: MiniMax M3 (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: 1048576,
-            maxTokens: 943718,
-        },
         "mistralai/codestral-2508": {
             id: "mistralai/codestral-2508",
             name: "Mistral: Codestral 2508",
@@ -11340,8 +11392,8 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 32768,
-            maxTokens: 26214,
+            contextWindow: 262144,
+            maxTokens: 209715,
         },
         "mistralai/mistral-medium-3.1": {
             id: "mistralai/mistral-medium-3.1",
@@ -11507,11 +11559,11 @@ export const MODELS = {
             cost: {
                 input: 0.6,
                 output: 2.5,
-                cacheRead: 0.15,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 100352,
+            maxTokens: 235929,
         },
         "moonshotai/kimi-k2.5": {
             id: "moonshotai/kimi-k2.5",
@@ -11556,9 +11608,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.66,
-                output: 3.4,
-                cacheRead: 0.18,
+                input: 0.71,
+                output: 3.5,
+                cacheRead: 0.15,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -11598,40 +11650,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 943718,
         },
-        "nex-agi/nex-n2-mini": {
-            id: "nex-agi/nex-n2-mini",
-            name: "Nex AGI: Nex-N2-Mini",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.024999999999999998,
-                output: 0.09999999999999999,
-                cacheRead: 0.0025,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 235929,
-        },
-        "nex-agi/nex-n2-pro": {
-            id: "nex-agi/nex-n2-pro",
-            name: "Nex AGI: Nex-N2-Pro",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0.25,
-                output: 1,
-                cacheRead: 0.024999999999999998,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 235929,
-        },
         "nvidia/nemotron-3-nano-30b-a3b": {
             id: "nvidia/nemotron-3-nano-30b-a3b",
             name: "NVIDIA: Nemotron 3 Nano 30B A3B",
@@ -12890,6 +12908,74 @@ export const MODELS = {
             contextWindow: 400000,
             maxTokens: 128000,
         },
+        "openai/gpt-6-astra": {
+            id: "openai/gpt-6-astra",
+            name: "OpenAI: GPT-6 Astra",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 10,
+                output: 50,
+                cacheRead: 1,
+                cacheWrite: 12.5,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
+        "openai/gpt-6-astra-pro": {
+            id: "openai/gpt-6-astra-pro",
+            name: "OpenAI: GPT-6 Astra Pro",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 10,
+                output: 50,
+                cacheRead: 1,
+                cacheWrite: 12.5,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
+        "openai/gpt-6-astra-pro:batch": {
+            id: "openai/gpt-6-astra-pro:batch",
+            name: "OpenAI: GPT-6 Astra Pro (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
+        "openai/gpt-6-astra:batch": {
+            id: "openai/gpt-6-astra:batch",
+            name: "OpenAI: GPT-6 Astra (batch)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 5,
+                output: 25,
+                cacheRead: 0.5,
+                cacheWrite: 6.25,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
         "openai/gpt-audio": {
             id: "openai/gpt-audio",
             name: "OpenAI: GPT Audio",
@@ -13375,13 +13461,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.12,
-                output: 0.24,
+                input: 0.22749999999999998,
+                output: 0.9099999999999999,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 16384,
+            maxTokens: 8192,
         },
         "qwen/qwen3-235b-a22b": {
             id: "qwen/qwen3-235b-a22b",
@@ -13409,13 +13495,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.0875,
-                output: 0.35,
-                cacheRead: 0.0175,
+                input: 0.09,
+                output: 0.55,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 235929,
+            maxTokens: 16384,
         },
         "qwen/qwen3-235b-a22b-thinking-2507": {
             id: "qwen/qwen3-235b-a22b-thinking-2507",
@@ -13670,7 +13756,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 32768,
+            maxTokens: 235929,
         },
         "qwen/qwen3-vl-235b-a22b-instruct": {
             id: "qwen/qwen3-vl-235b-a22b-instruct",
@@ -13834,9 +13920,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.08,
-                output: 0.75,
-                cacheRead: 0,
+                input: 0.3125,
+                output: 1.25,
+                cacheRead: 0.15625,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -14148,9 +14234,9 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 131072,
         },
-        "qwen/qwen3.8-max": {
-            id: "qwen/qwen3.8-max",
-            name: "Qwen: Qwen3.8 Max",
+        "qwen/qwen3.8-max-0902": {
+            id: "qwen/qwen3.8-max-0902",
+            name: "Qwen: Qwen3.8 Max (0902)",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
@@ -14293,9 +14379,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.0825,
-                output: 0.33,
-                cacheRead: 0.020625,
+                input: 0.13199999999999998,
+                output: 0.5279999999999999,
+                cacheRead: 0.032999999999999995,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
@@ -14350,7 +14436,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1024000,
-            maxTokens: 26214,
+            maxTokens: 819200,
         },
         "thinkingmachines/inkling": {
             id: "thinkingmachines/inkling",
@@ -14735,13 +14821,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.06,
+                input: 0.060500000000000005,
                 output: 0.39999999999999997,
-                cacheRead: 0.01,
+                cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 202752,
-            maxTokens: 16384,
+            maxTokens: 117964,
         },
         "z-ai/glm-5": {
             id: "z-ai/glm-5",
@@ -14811,23 +14897,6 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 131072,
         },
-        "z-ai/glm-5.2:free": {
-            id: "z-ai/glm-5.2:free",
-            name: "Z.ai: GLM 5.2 (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: 256000,
-            maxTokens: 230400,
-        },
         "z-ai/glm-5.3": {
             id: "z-ai/glm-5.3",
             name: "Z.ai: GLM 5.3",
@@ -14839,11 +14908,11 @@ export const MODELS = {
             cost: {
                 input: 1.4,
                 output: 4.4,
-                cacheRead: 0.14,
+                cacheRead: 0.26,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
-            maxTokens: 262144,
+            maxTokens: 943718,
         },
         "z-ai/glm-5.3-flash": {
             id: "z-ai/glm-5.3-flash",
@@ -14973,13 +15042,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.049980000000000004,
-                output: 0.09996000000000001,
-                cacheRead: 0.009996000000000001,
+                input: 0.049999999999999996,
+                output: 0.16,
+                cacheRead: 0.013000000000000001,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
-            maxTokens: 131072,
+            maxTokens: 393216,
         },
         "~google/gemini-flash-latest": {
             id: "~google/gemini-flash-latest",
@@ -15092,13 +15161,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.075,
-                output: 0.25,
-                cacheRead: 0.015,
+                input: 0.07125000000000001,
+                output: 0.2375,
+                cacheRead: 0.01425,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
-            maxTokens: 943718,
+            maxTokens: 131072,
         },
         "~z-ai/glm-latest": {
             id: "~z-ai/glm-latest",
@@ -15109,13 +15178,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.15,
-                output: 3.5,
-                cacheRead: 0.09999999999999999,
+                input: 1.12,
+                output: 3.52,
+                cacheRead: 0.20800000000000002,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
-            maxTokens: 235929,
+            maxTokens: 943718,
         },
     },
     "vercel-ai-gateway": {
@@ -16938,23 +17007,6 @@ export const MODELS = {
             contextWindow: 204800,
             maxTokens: 131000,
         },
-        "minimax/minimax-m2.7-free": {
-            id: "minimax/minimax-m2.7-free",
-            name: "MiniMax M2.7 (Free)",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 196608,
-            maxTokens: 196608,
-        },
         "minimax/minimax-m2.7-highspeed": {
             id: "minimax/minimax-m2.7-highspeed",
             name: "MiniMax M2.7 High Speed",
@@ -16989,23 +17041,6 @@ export const MODELS = {
             contextWindow: 512000,
             maxTokens: 512000,
         },
-        "minimax/minimax-m3-free": {
-            id: "minimax/minimax-m3-free",
-            name: "MiniMax M3 (Free)",
-            api: "anthropic-messages",
-            provider: "vercel-ai-gateway",
-            baseUrl: "https://ai-gateway.vercel.sh",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 1048576,
-        },
         "mistral/codestral": {
             id: "mistral/codestral",
             name: "Mistral Codestral",
@@ -18140,7 +18175,7 @@ export const MODELS = {
                 input: 0.39999999999999997,
                 output: 2.4,
                 cacheRead: 0.04,
-                cacheWrite: 0.25,
+                cacheWrite: 0.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -18174,7 +18209,7 @@ export const MODELS = {
                 input: 4,
                 output: 20,
                 cacheRead: 0.39999999999999997,
-                cacheWrite: 2.5,
+                cacheWrite: 5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -18208,7 +18243,41 @@ export const MODELS = {
                 input: 4,
                 output: 24,
                 cacheRead: 0.39999999999999997,
-                cacheWrite: 2.5,
+                cacheWrite: 5,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
+        "openai/gpt-6-astra": {
+            id: "openai/gpt-6-astra",
+            name: "GPT-6 Astra",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 10,
+                output: 50,
+                cacheRead: 1,
+                cacheWrite: 12.5,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
+        "openai/gpt-6-astra-fast": {
+            id: "openai/gpt-6-astra-fast",
+            name: "GPT-6 Astra (Fast)",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 20,
+                output: 100,
+                cacheRead: 2,
+                cacheWrite: 25,
             },
             contextWindow: 1050000,
             maxTokens: 128000,