@dreb/ai 2.64.2 → 2.64.4

package/dist/models.generated.js

@@ -2896,6 +2896,23 @@ 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",
@@ -3413,10 +3430,10 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 0.2,
-                cacheWrite: 2.5,
+                input: 4,
+                output: 20,
+                cacheRead: 0.4,
+                cacheWrite: 5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -3439,6 +3456,25 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "gpt-6-astra": {
+            id: "gpt-6-astra",
+            name: "GPT-6 Astra",
+            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: 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 +7172,23 @@ 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",
@@ -7684,6 +7737,23 @@ 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 +7941,40 @@ 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 +8298,23 @@ 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",
@@ -8432,6 +8553,23 @@ export const MODELS = {
             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: 1.25,
+                output: 4.25,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
         "muse-spark-1.3-contributor-free": {
             id: "muse-spark-1.3-contributor-free",
             name: "Muse Spark 1.3 Free",
@@ -9907,9 +10045,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.088606,
-                output: 0.177212,
-                cacheRead: 0.017721200000000003,
+                input: 0.08078,
+                output: 0.16156,
+                cacheRead: 0.016156,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -9924,13 +10062,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.065,
-                output: 0.18,
-                cacheRead: 0.016,
+                input: 0.049980000000000004,
+                output: 0.09996000000000001,
+                cacheRead: 0.009996000000000001,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
-            maxTokens: 943718,
+            maxTokens: 131072,
         },
         "deepseek/deepseek-v4-flash-0731:batch": {
             id: "deepseek/deepseek-v4-flash-0731:batch",
@@ -9975,9 +10113,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.04226,
-                output: 2.08452,
-                cacheRead: 0.086855,
+                input: 0.69774,
+                output: 1.39548,
+                cacheRead: 0.058145,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -9992,9 +10130,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.1154,
-                output: 3.3461999999999996,
-                cacheRead: 0.03718,
+                input: 1.12068,
+                output: 3.36204,
+                cacheRead: 0.037356,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -10612,23 +10750,6 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
-        "ibm-granite/granite-4.1-8b": {
-            id: "ibm-granite/granite-4.1-8b",
-            name: "IBM: Granite 4.1 8B",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 0.049999999999999996,
-                output: 0.09999999999999999,
-                cacheRead: 0.049999999999999996,
-                cacheWrite: 0,
-            },
-            contextWindow: 131072,
-            maxTokens: 117964,
-        },
         "ibm-granite/granite-4.2-8b": {
             id: "ibm-granite/granite-4.2-8b",
             name: "IBM: Granite 4.2 8B",
@@ -10682,7 +10803,7 @@ export const MODELS = {
         },
         "inclusionai/ling-3.0-flash": {
             id: "inclusionai/ling-3.0-flash",
-            name: "Ling-3.0-flash",
+            name: "inclusionAI: Ling 3.0 Flash",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
@@ -10699,7 +10820,7 @@ export const MODELS = {
         },
         "inclusionai/ling-3.0-flash-fin": {
             id: "inclusionai/ling-3.0-flash-fin",
-            name: "Ling 3.0 Flash Fin",
+            name: "inclusionAI: Ling 3.0 Flash Fin",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
@@ -10716,7 +10837,24 @@ export const MODELS = {
         },
         "inclusionai/ling-3.0-flash-fin:free": {
             id: "inclusionai/ling-3.0-flash-fin:free",
-            name: "Ling 3.0 Flash Fin (free)",
+            name: "inclusionAI: Ling 3.0 Flash Fin (free)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 32768,
+        },
+        "inclusionai/ling-3.0-flash-sante:free": {
+            id: "inclusionai/ling-3.0-flash-sante:free",
+            name: "inclusionAI: Ling 3.0 Flash Sante (free)",
             api: "openai-completions",
             provider: "openrouter",
             baseUrl: "https://openrouter.ai/api/v1",
@@ -12890,6 +13028,74 @@ 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",
@@ -13409,13 +13615,13 @@ 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",
@@ -13834,13 +14040,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.25,
+                input: 0.3125,
                 output: 1.25,
-                cacheRead: 0.25,
+                cacheRead: 0.15625,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 235929,
+            maxTokens: 16384,
         },
         "qwen/qwen3.5-397b-a17b": {
             id: "qwen/qwen3.5-397b-a17b",
@@ -13953,13 +14159,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.6,
-                output: 3.5999999999999996,
-                cacheRead: 0.12,
+                input: 0.3,
+                output: 2,
+                cacheRead: 0.03,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 235929,
+            maxTokens: 65536,
         },
         "qwen/qwen3.6-35b-a3b": {
             id: "qwen/qwen3.6-35b-a3b",
@@ -14148,9 +14354,9 @@ 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",
@@ -14350,7 +14556,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 1024000,
-            maxTokens: 26214,
+            maxTokens: 819200,
         },
         "thinkingmachines/inkling": {
             id: "thinkingmachines/inkling",
@@ -14973,13 +15179,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.049999999999999996,
-                output: 0.16,
-                cacheRead: 0.013000000000000001,
+                input: 0.045,
+                output: 0.09,
+                cacheRead: 0.009,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
-            maxTokens: 393216,
+            maxTokens: 943718,
         },
         "~google/gemini-flash-latest": {
             id: "~google/gemini-flash-latest",
@@ -15024,9 +15230,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2.5,
-                output: 14,
-                cacheRead: 0.29,
+                input: 2.5500000000000003,
+                output: 12.75,
+                cacheRead: 0.25599998999999996,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -15109,9 +15315,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.15,
-                output: 3.5,
-                cacheRead: 0.09999999999999999,
+                input: 1.17,
+                output: 3.9600000000000004,
+                cacheRead: 0.234,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
@@ -16530,6 +16736,40 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 32000,
         },
+        "inclusionai/ling-3.0-flash-sante": {
+            id: "inclusionai/ling-3.0-flash-sante",
+            name: "Ling 3.0 Flash Sante",
+            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: 256000,
+            maxTokens: 32000,
+        },
+        "inclusionai/ling-3.0-flash-sante-free": {
+            id: "inclusionai/ling-3.0-flash-sante-free",
+            name: "Ling 3.0 Flash Sante (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: 256000,
+            maxTokens: 32000,
+        },
         "interfaze/interfaze-beta": {
             id: "interfaze/interfaze-beta",
             name: "Interfaze Beta",
@@ -18106,7 +18346,7 @@ export const MODELS = {
                 input: 0.39999999999999997,
                 output: 2.4,
                 cacheRead: 0.04,
-                cacheWrite: 0.25,
+                cacheWrite: 0.5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -18140,7 +18380,7 @@ export const MODELS = {
                 input: 4,
                 output: 20,
                 cacheRead: 0.39999999999999997,
-                cacheWrite: 2.5,
+                cacheWrite: 5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -18174,7 +18414,41 @@ 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,