@fleetagent/pi-ai 0.2.5 → 0.2.7

package/dist/models.generated.js

@@ -4288,6 +4288,24 @@ export const MODELS = {
             contextWindow: 1050000,
             maxTokens: 128000,
         },
+        "gpt-6-astra": {
+            id: "gpt-6-astra",
+            name: "GPT-6 Astra",
+            api: "openai-responses",
+            provider: "cloudflare-ai-gateway",
+            baseUrl: "https://gateway.ai.cloudflare.com/v1/{CLOUDFLARE_ACCOUNT_ID}/{CLOUDFLARE_GATEWAY_ID}/openai",
+            reasoning: true,
+            thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 10,
+                output: 50,
+                cacheRead: 1,
+                cacheWrite: 12,
+            },
+            contextWindow: 1050000,
+            maxTokens: 128000,
+        },
         "o3": {
             id: "o3",
             name: "o3",
@@ -7966,80 +7984,6 @@ export const MODELS = {
             maxTokens: 131072,
         },
     },
-    "kimi-coding": {
-        "k3": {
-            id: "k3",
-            name: "Kimi K3",
-            api: "anthropic-messages",
-            provider: "kimi-coding",
-            baseUrl: "https://api.kimi.com/coding",
-            headers: { "User-Agent": "KimiCLI/1.5" },
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 131072,
-        },
-        "k3-256k": {
-            id: "k3-256k",
-            name: "Kimi K3-256K",
-            api: "anthropic-messages",
-            provider: "kimi-coding",
-            baseUrl: "https://api.kimi.com/coding",
-            headers: { "User-Agent": "KimiCLI/1.5" },
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 131072,
-        },
-        "kimi-for-coding": {
-            id: "kimi-for-coding",
-            name: "kimi-for-coding",
-            api: "anthropic-messages",
-            provider: "kimi-coding",
-            baseUrl: "https://api.kimi.com/coding",
-            headers: { "User-Agent": "KimiCLI/1.5" },
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 1048576,
-            maxTokens: 32768,
-        },
-        "kimi-for-coding-highspeed": {
-            id: "kimi-for-coding-highspeed",
-            name: "Kimi For Coding HighSpeed",
-            api: "anthropic-messages",
-            provider: "kimi-coding",
-            baseUrl: "https://api.kimi.com/coding",
-            headers: { "User-Agent": "KimiCLI/1.5" },
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 32768,
-        },
-    },
     "minimax": {
         "MiniMax-M2.7": {
             id: "MiniMax-M2.7",
@@ -8657,6 +8601,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 131072,
         },
+        "zai-glm-5-3": {
+            id: "zai-glm-5-3",
+            name: "GLM-5.3",
+            api: "mistral-conversations",
+            provider: "mistral",
+            baseUrl: "https://api.mistral.ai",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 1.4,
+                output: 4.4,
+                cacheRead: 0.14,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
     },
     "moonshotai": {
         "kimi-k2.6": {
@@ -10032,6 +9993,25 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 384000,
         },
+        "deepseek-v4.1-flash": {
+            id: "deepseek-v4.1-flash",
+            name: "DeepSeek V4.1 Flash",
+            api: "openai-completions",
+            provider: "opencode",
+            baseUrl: "https://opencode.ai/zen/v1",
+            compat: { "requiresReasoningContentOnAssistantMessages": true, "thinkingFormat": "deepseek" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "max" },
+            input: ["text", "image"],
+            cost: {
+                input: 0.3,
+                output: 1.2,
+                cacheRead: 0.006,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 384000,
+        },
         "gemini-3-flash": {
             id: "gemini-3-flash",
             name: "Gemini 3 Flash",
@@ -10551,7 +10531,7 @@ export const MODELS = {
         },
         "gpt-5.6-sol": {
             id: "gpt-5.6-sol",
-            name: "GPT-5.6 Sol (50% Off)",
+            name: "GPT-5.6 Sol",
             api: "openai-responses",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
@@ -10559,10 +10539,10 @@ export const MODELS = {
             thinkingLevelMap: { "off": null, "xhigh": "xhigh" },
             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,
@@ -10946,21 +10926,21 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 65536,
         },
-        "union-alpha": {
-            id: "union-alpha",
-            name: "Union Alpha Free",
+        "qwen3.8-flash": {
+            id: "qwen3.8-flash",
+            name: "Qwen3.8 Flash",
             api: "anthropic-messages",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen",
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
+                input: 0.15,
+                output: 0.47,
+                cacheRead: 0.016,
+                cacheWrite: 0.2,
             },
-            contextWindow: 262144,
+            contextWindow: 1000000,
             maxTokens: 131072,
         },
     },
@@ -11436,23 +11416,6 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 131072,
         },
-        "union-alpha": {
-            id: "union-alpha",
-            name: "Union Alpha Free",
-            api: "anthropic-messages",
-            provider: "opencode-go",
-            baseUrl: "https://opencode.ai/zen/go",
-            reasoning: true,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 131072,
-        },
     },
     "openrouter": {
         "aion-labs/aion-2.0": {
@@ -12250,13 +12213,13 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.2574,
-                output: 1.0287,
+                input: 0.32,
+                output: 0.8899999999999999,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
             contextWindow: 163840,
-            maxTokens: 16000,
+            maxTokens: 16384,
         },
         "deepseek/deepseek-chat-v3-0324": {
             id: "deepseek/deepseek-chat-v3-0324",
@@ -12388,9 +12351,9 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 0.07,
-                output: 0.14,
-                cacheRead: 0.014,
+                input: 0.04396,
+                output: 0.08792,
+                cacheRead: 0.008792,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -12407,9 +12370,9 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 0.06,
-                output: 0.12,
-                cacheRead: 0.012,
+                input: 0.04,
+                output: 0.08,
+                cacheRead: 0.016,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
@@ -12434,6 +12397,25 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 943718,
         },
+        "deepseek/deepseek-v4-flash-0731:free": {
+            id: "deepseek/deepseek-v4-flash-0731:free",
+            name: "DeepSeek: DeepSeek V4 Flash 0731 (free)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            compat: { "requiresReasoningContentOnAssistantMessages": true },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
+            input: ["text"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 393216,
+        },
         "deepseek/deepseek-v4-flash-vision-exp": {
             id: "deepseek/deepseek-v4-flash-vision-exp",
             name: "DeepSeek: DeepSeek V4 Flash Vision Exp",
@@ -12445,13 +12427,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
-                input: 0.22,
-                output: 0.66,
-                cacheRead: 0.007,
+                input: 0.21559999999999999,
+                output: 0.6468,
+                cacheRead: 0.00686,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 943718,
+            maxTokens: 262144,
         },
         "deepseek/deepseek-v4-flash-vision-exp:batch": {
             id: "deepseek/deepseek-v4-flash-vision-exp:batch",
@@ -12483,13 +12465,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 1.5999999999999999,
-                output: 3.1999999999999997,
-                cacheRead: 0.135,
+                input: 0.45274800000000004,
+                output: 0.9054960000000001,
+                cacheRead: 0.037729,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 393216,
+            maxTokens: 384000,
         },
         "deepseek/deepseek-v4-pro-0813": {
             id: "deepseek/deepseek-v4-pro-0813",
@@ -12502,9 +12484,9 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 0.57948,
-                output: 1.73844,
-                cacheRead: 0.018438,
+                input: 0.57816,
+                output: 1.73448,
+                cacheRead: 0.018396000000000003,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -13426,8 +13408,8 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.3,
-                output: 1.1,
+                input: 0.35,
+                output: 1.5,
                 cacheRead: 0.04,
                 cacheWrite: 0,
             },
@@ -13808,23 +13790,6 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 104857,
         },
-        "mistralai/mistral-large-2512": {
-            id: "mistralai/mistral-large-2512",
-            name: "Mistral: Mistral Large 3 2512",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0.5,
-                output: 1.5,
-                cacheRead: 0.049999999999999996,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 209715,
-        },
         "mistralai/mistral-large-2512:batch": {
             id: "mistralai/mistral-large-2512:batch",
             name: "Mistral: Mistral Large 3 2512 (batch)",
@@ -14158,9 +14123,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 3,
-                output: 15,
-                cacheRead: 0.3,
+                input: 1.7,
+                output: 8.5,
+                cacheRead: 0.16999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -14294,13 +14259,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.625,
-                output: 3.125,
-                cacheRead: 0.1875,
+                input: 0.6,
+                output: 2.4,
+                cacheRead: 0.12,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 32768,
+            maxTokens: 182520,
         },
         "nvidia/nemotron-3-ultra-550b-a55b:free": {
             id: "nvidia/nemotron-3-ultra-550b-a55b:free",
@@ -14328,13 +14293,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.08,
+                input: 0.07,
                 output: 0.19999999999999998,
                 cacheRead: 0.04,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 131072,
+            maxTokens: 235929,
         },
         "nvidia/nemotron-3.5-lightning:free": {
             id: "nvidia/nemotron-3.5-lightning:free",
@@ -15621,13 +15586,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.037,
-                output: 0.16999999999999998,
-                cacheRead: 0,
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0.075,
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 117964,
+            maxTokens: 65536,
         },
         "openai/gpt-oss-120b:batch": {
             id: "openai/gpt-oss-120b:batch",
@@ -15969,6 +15934,23 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 32768,
         },
+        "prism-ml/ternary-bonsai-2-27b": {
+            id: "prism-ml/ternary-bonsai-2-27b",
+            name: "PrismML: Ternary Bonsai 2 27B",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.075,
+                output: 0.5,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 32768,
+        },
         "qwen/qwen-2.5-72b-instruct": {
             id: "qwen/qwen-2.5-72b-instruct",
             name: "Qwen2.5 72B Instruct",
@@ -16386,8 +16368,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 0.13,
-                output: 0.52,
+                input: 0.19999999999999998,
+                output: 0.7,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -16802,6 +16784,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 131072,
         },
+        "qwen/qwen3.8-27b:free": {
+            id: "qwen/qwen3.8-27b:free",
+            name: "Qwen: Qwen3.8 27B (free)",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0,
+                output: 0,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 235929,
+        },
         "qwen/qwen3.8-flash": {
             id: "qwen/qwen3.8-flash",
             name: "Qwen: Qwen3.8 Flash",
@@ -16955,23 +16954,6 @@ export const MODELS = {
             contextWindow: 131072,
             maxTokens: 16384,
         },
-        "stealth/union-alpha": {
-            id: "stealth/union-alpha",
-            name: "Union Alpha",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text", "image"],
-            cost: {
-                input: 0,
-                output: 0,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 262144,
-            maxTokens: 131072,
-        },
         "stepfun/step-3.5-flash": {
             id: "stepfun/step-3.5-flash",
             name: "StepFun: Step 3.5 Flash",
@@ -17142,6 +17124,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 262144,
         },
+        "unbiased/pareto": {
+            id: "unbiased/pareto",
+            name: "Pareto",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: false,
+            input: ["text", "image"],
+            cost: {
+                input: 2.5,
+                output: 7.5,
+                cacheRead: 0.25,
+                cacheWrite: 0,
+            },
+            contextWindow: 262144,
+            maxTokens: 131072,
+        },
         "upstage/solar-pro-3": {
             id: "upstage/solar-pro-3",
             name: "Upstage: Solar Pro 3",
@@ -17491,9 +17490,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.4,
-                output: 4.4,
-                cacheRead: 0.14,
+                input: 0.5544,
+                output: 1.7424,
+                cacheRead: 0.10296000000000001,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -17525,13 +17524,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 1.4,
-                output: 4.4,
-                cacheRead: 0.26,
+                input: 0.9099999999999999,
+                output: 2.8600000000000003,
+                cacheRead: 0.16899999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
-            maxTokens: 943717,
+            maxTokens: 131072,
         },
         "z-ai/glm-5.3-flash": {
             id: "z-ai/glm-5.3-flash",
@@ -17567,6 +17566,23 @@ export const MODELS = {
             contextWindow: 1048576,
             maxTokens: 943718,
         },
+        "z-ai/glm-5.3-flashx": {
+            id: "z-ai/glm-5.3-flashx",
+            name: "Z.ai: GLM 5.3 FlashX",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.37,
+                output: 1.25,
+                cacheRead: 0.075,
+                cacheWrite: 0,
+            },
+            contextWindow: 1048576,
+            maxTokens: 131072,
+        },
         "z-ai/glm-5.3:batch": {
             id: "z-ai/glm-5.3:batch",
             name: "Z.ai: GLM 5.3 (batch)",
@@ -17678,13 +17694,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 0.15,
-                output: 0.6,
-                cacheRead: 0.015,
+                input: 0.13,
+                output: 0.52,
+                cacheRead: 0.0026000000000000003,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
-            maxTokens: 393216,
+            maxTokens: 943718,
         },
         "~deepseek/deepseek-pro-latest": {
             id: "~deepseek/deepseek-pro-latest",
@@ -17695,9 +17711,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.57948,
-                output: 1.73844,
-                cacheRead: 0.018438,
+                input: 0.57816,
+                output: 1.73448,
+                cacheRead: 0.018396000000000003,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -17714,13 +17730,13 @@ export const MODELS = {
             thinkingLevelMap: { "minimal": null, "low": null, "medium": null, "high": "high", "xhigh": "xhigh" },
             input: ["text"],
             cost: {
-                input: 0.03,
-                output: 0.13,
-                cacheRead: 0.01,
+                input: 0.04,
+                output: 0.08,
+                cacheRead: 0.016,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
-            maxTokens: 393216,
+            maxTokens: 943718,
         },
         "~google/gemini-flash-latest": {
             id: "~google/gemini-flash-latest",
@@ -17765,9 +17781,9 @@ export const MODELS = {
             reasoning: true,
             input: ["text", "image"],
             cost: {
-                input: 2.0999999999999996,
-                output: 10.950000000000001,
-                cacheRead: 0.22999999999999998,
+                input: 1.7,
+                output: 8.5,
+                cacheRead: 0.16999999999999998,
                 cacheWrite: 0,
             },
             contextWindow: 1048576,
@@ -17901,13 +17917,13 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.8775,
-                output: 2.9699999999999998,
-                cacheRead: 0.1755,
+                input: 0.8917999999999999,
+                output: 2.8028,
+                cacheRead: 0.16562,
                 cacheWrite: 0,
             },
             contextWindow: 1310720,
-            maxTokens: 235929,
+            maxTokens: 131072,
         },
     },
     "together": {
@@ -18838,6 +18854,23 @@ export const MODELS = {
             contextWindow: 991000,
             maxTokens: 128000,
         },
+        "alibaba/qwen3.8-omni-flash": {
+            id: "alibaba/qwen3.8-omni-flash",
+            name: "Qwen 3.8 Omni Flash",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.15,
+                output: 0.47,
+                cacheRead: 0.016,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
         "amazon/nova-2-lite": {
             id: "amazon/nova-2-lite",
             name: "Nova 2 Lite",
@@ -21286,10 +21319,10 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
-                input: 2,
-                output: 10,
-                cacheRead: 0.19999999999999998,
-                cacheWrite: 2.5,
+                input: 4,
+                output: 20,
+                cacheRead: 0.39999999999999997,
+                cacheWrite: 5,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -21304,10 +21337,10 @@ export const MODELS = {
             thinkingLevelMap: { "xhigh": "xhigh" },
             input: ["text", "image"],
             cost: {
-                input: 4,
-                output: 20,
-                cacheRead: 0.39999999999999997,
-                cacheWrite: 5,
+                input: 8,
+                output: 40,
+                cacheRead: 0.7999999999999999,
+                cacheWrite: 10,
             },
             contextWindow: 1050000,
             maxTokens: 128000,
@@ -22268,6 +22301,23 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 131000,
         },
+        "zai/glm-5.3-flashx": {
+            id: "zai/glm-5.3-flashx",
+            name: "GLM 5.3 FlashX",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 0.37,
+                output: 1.25,
+                cacheRead: 0.075,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 131072,
+        },
         "zai/glm-5v-turbo": {
             id: "zai/glm-5v-turbo",
             name: "GLM 5V Turbo",