@earendil-works/pi-ai 0.80.6 → 0.80.8

package/dist/providers/vercel-ai-gateway.models.js

@@ -494,23 +494,6 @@ export const VERCEL_AI_GATEWAY_MODELS = {
         contextWindow: 200000,
         maxTokens: 4096,
     },
-    "anthropic/claude-3.5-haiku": {
-        id: "anthropic/claude-3.5-haiku",
-        name: "Claude 3.5 Haiku",
-        api: "anthropic-messages",
-        provider: "vercel-ai-gateway",
-        baseUrl: "https://ai-gateway.vercel.sh",
-        reasoning: false,
-        input: ["text", "image"],
-        cost: {
-            input: 0.8,
-            output: 4,
-            cacheRead: 0.08,
-            cacheWrite: 1,
-        },
-        contextWindow: 200000,
-        maxTokens: 8192,
-    },
     "anthropic/claude-fable-5": {
         id: "anthropic/claude-fable-5",
         name: "Claude Fable 5",
@@ -562,7 +545,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
             cacheWrite: 18.75,
         },
         contextWindow: 200000,
-        maxTokens: 32000,
+        maxTokens: 8192,
     },
     "anthropic/claude-opus-4.1": {
         id: "anthropic/claude-opus-4.1",
@@ -636,6 +619,25 @@ export const VERCEL_AI_GATEWAY_MODELS = {
         contextWindow: 1000000,
         maxTokens: 128000,
     },
+    "anthropic/claude-opus-4.7-fast": {
+        id: "anthropic/claude-opus-4.7-fast",
+        name: "Claude Opus 4.7 (Fast)",
+        api: "anthropic-messages",
+        provider: "vercel-ai-gateway",
+        baseUrl: "https://ai-gateway.vercel.sh",
+        compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
+        reasoning: true,
+        thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
+        input: ["text", "image"],
+        cost: {
+            input: 30,
+            output: 150,
+            cacheRead: 3,
+            cacheWrite: 37.5,
+        },
+        contextWindow: 1000000,
+        maxTokens: 128000,
+    },
     "anthropic/claude-opus-4.8": {
         id: "anthropic/claude-opus-4.8",
         name: "Claude Opus 4.8",
@@ -655,6 +657,25 @@ export const VERCEL_AI_GATEWAY_MODELS = {
         contextWindow: 1000000,
         maxTokens: 128000,
     },
+    "anthropic/claude-opus-4.8-fast": {
+        id: "anthropic/claude-opus-4.8-fast",
+        name: "Claude Opus 4.8 (Fast)",
+        api: "anthropic-messages",
+        provider: "vercel-ai-gateway",
+        baseUrl: "https://ai-gateway.vercel.sh",
+        compat: { "forceAdaptiveThinking": true, "supportsTemperature": false },
+        reasoning: true,
+        thinkingLevelMap: { "xhigh": "xhigh", "max": "max" },
+        input: ["text", "image"],
+        cost: {
+            input: 10,
+            output: 50,
+            cacheRead: 1,
+            cacheWrite: 12.5,
+        },
+        contextWindow: 1000000,
+        maxTokens: 128000,
+    },
     "anthropic/claude-sonnet-4": {
         id: "anthropic/claude-sonnet-4",
         name: "Claude Sonnet 4",
@@ -670,7 +691,7 @@ export const VERCEL_AI_GATEWAY_MODELS = {
             cacheWrite: 3.75,
         },
         contextWindow: 1000000,
-        maxTokens: 64000,
+        maxTokens: 8192,
     },
     "anthropic/claude-sonnet-4.5": {
         id: "anthropic/claude-sonnet-4.5",
@@ -727,23 +748,6 @@ export const VERCEL_AI_GATEWAY_MODELS = {
         contextWindow: 1000000,
         maxTokens: 128000,
     },
-    "arcee-ai/trinity-large-preview": {
-        id: "arcee-ai/trinity-large-preview",
-        name: "Trinity Large Preview",
-        api: "anthropic-messages",
-        provider: "vercel-ai-gateway",
-        baseUrl: "https://ai-gateway.vercel.sh",
-        reasoning: false,
-        input: ["text"],
-        cost: {
-            input: 0.25,
-            output: 1,
-            cacheRead: 0,
-            cacheWrite: 0,
-        },
-        contextWindow: 131000,
-        maxTokens: 131000,
-    },
     "arcee-ai/trinity-large-thinking": {
         id: "arcee-ai/trinity-large-thinking",
         name: "Trinity Large Thinking",
@@ -872,12 +876,12 @@ export const VERCEL_AI_GATEWAY_MODELS = {
         reasoning: true,
         input: ["text"],
         cost: {
-            input: 0.6,
-            output: 1.7,
-            cacheRead: 0,
+            input: 0.25,
+            output: 0.95,
+            cacheRead: 0.13,
             cacheWrite: 0,
         },
-        contextWindow: 128000,
+        contextWindow: 163840,
         maxTokens: 128000,
     },
     "deepseek/deepseek-v3.1-terminus": {
@@ -1203,6 +1207,23 @@ export const VERCEL_AI_GATEWAY_MODELS = {
         contextWindow: 1000000,
         maxTokens: 32000,
     },
+    "kwaipilot/kat-coder-air-v2.5": {
+        id: "kwaipilot/kat-coder-air-v2.5",
+        name: "Kat Coder Air V2.5",
+        api: "anthropic-messages",
+        provider: "vercel-ai-gateway",
+        baseUrl: "https://ai-gateway.vercel.sh",
+        reasoning: true,
+        input: ["text"],
+        cost: {
+            input: 0.15,
+            output: 0.6,
+            cacheRead: 0.03,
+            cacheWrite: 0,
+        },
+        contextWindow: 256000,
+        maxTokens: 80000,
+    },
     "kwaipilot/kat-coder-pro-v1": {
         id: "kwaipilot/kat-coder-pro-v1",
         name: "KAT-Coder-Pro V1",
@@ -1237,39 +1258,22 @@ export const VERCEL_AI_GATEWAY_MODELS = {
         contextWindow: 256000,
         maxTokens: 256000,
     },
-    "meituan/longcat-flash-chat": {
-        id: "meituan/longcat-flash-chat",
-        name: "LongCat Flash Chat",
-        api: "anthropic-messages",
-        provider: "vercel-ai-gateway",
-        baseUrl: "https://ai-gateway.vercel.sh",
-        reasoning: false,
-        input: ["text"],
-        cost: {
-            input: 0,
-            output: 0,
-            cacheRead: 0,
-            cacheWrite: 0,
-        },
-        contextWindow: 128000,
-        maxTokens: 100000,
-    },
-    "meituan/longcat-flash-thinking-2601": {
-        id: "meituan/longcat-flash-thinking-2601",
-        name: "LongCat Flash Thinking 2601",
+    "kwaipilot/kat-coder-pro-v2.5": {
+        id: "kwaipilot/kat-coder-pro-v2.5",
+        name: "Kat Coder Pro V2.5",
         api: "anthropic-messages",
         provider: "vercel-ai-gateway",
         baseUrl: "https://ai-gateway.vercel.sh",
         reasoning: true,
         input: ["text"],
         cost: {
-            input: 0,
-            output: 0,
-            cacheRead: 0,
+            input: 0.74,
+            output: 2.96,
+            cacheRead: 0.15,
             cacheWrite: 0,
         },
-        contextWindow: 32768,
-        maxTokens: 32768,
+        contextWindow: 256000,
+        maxTokens: 80000,
     },
     "meta/llama-3.1-70b": {
         id: "meta/llama-3.1-70b",
@@ -1577,23 +1581,6 @@ export const VERCEL_AI_GATEWAY_MODELS = {
         contextWindow: 256000,
         maxTokens: 256000,
     },
-    "mistral/devstral-small": {
-        id: "mistral/devstral-small",
-        name: "Devstral Small 1.1",
-        api: "anthropic-messages",
-        provider: "vercel-ai-gateway",
-        baseUrl: "https://ai-gateway.vercel.sh",
-        reasoning: false,
-        input: ["text"],
-        cost: {
-            input: 0.1,
-            output: 0.3,
-            cacheRead: 0,
-            cacheWrite: 0,
-        },
-        contextWindow: 128000,
-        maxTokens: 64000,
-    },
     "mistral/devstral-small-2": {
         id: "mistral/devstral-small-2",
         name: "Devstral Small 2",
@@ -1798,23 +1785,6 @@ export const VERCEL_AI_GATEWAY_MODELS = {
         contextWindow: 128000,
         maxTokens: 4000,
     },
-    "mistral/pixtral-large": {
-        id: "mistral/pixtral-large",
-        name: "Pixtral Large",
-        api: "anthropic-messages",
-        provider: "vercel-ai-gateway",
-        baseUrl: "https://ai-gateway.vercel.sh",
-        reasoning: false,
-        input: ["text", "image"],
-        cost: {
-            input: 2,
-            output: 6,
-            cacheRead: 0,
-            cacheWrite: 0,
-        },
-        contextWindow: 128000,
-        maxTokens: 4000,
-    },
     "moonshotai/kimi-k2": {
         id: "moonshotai/kimi-k2",
         name: "Kimi K2 Instruct",
@@ -2782,6 +2752,23 @@ export const VERCEL_AI_GATEWAY_MODELS = {
         contextWindow: 256000,
         maxTokens: 256000,
     },
+    "thinkingmachines/inkling": {
+        id: "thinkingmachines/inkling",
+        name: "Inkling",
+        api: "anthropic-messages",
+        provider: "vercel-ai-gateway",
+        baseUrl: "https://ai-gateway.vercel.sh",
+        reasoning: true,
+        input: ["text", "image"],
+        cost: {
+            input: 1,
+            output: 4.05,
+            cacheRead: 0.17,
+            cacheWrite: 0,
+        },
+        contextWindow: 256000,
+        maxTokens: 256000,
+    },
     "xai/grok-4.1-fast-non-reasoning": {
         id: "xai/grok-4.1-fast-non-reasoning",
         name: "Grok 4.1 Fast Non-Reasoning",
@@ -2969,40 +2956,6 @@ export const VERCEL_AI_GATEWAY_MODELS = {
         contextWindow: 256000,
         maxTokens: 256000,
     },
-    "xiaomi/mimo-v2-flash": {
-        id: "xiaomi/mimo-v2-flash",
-        name: "MiMo V2 Flash",
-        api: "anthropic-messages",
-        provider: "vercel-ai-gateway",
-        baseUrl: "https://ai-gateway.vercel.sh",
-        reasoning: true,
-        input: ["text"],
-        cost: {
-            input: 0.1,
-            output: 0.3,
-            cacheRead: 0.01,
-            cacheWrite: 0,
-        },
-        contextWindow: 262144,
-        maxTokens: 32000,
-    },
-    "xiaomi/mimo-v2-pro": {
-        id: "xiaomi/mimo-v2-pro",
-        name: "MiMo V2 Pro",
-        api: "anthropic-messages",
-        provider: "vercel-ai-gateway",
-        baseUrl: "https://ai-gateway.vercel.sh",
-        reasoning: true,
-        input: ["text"],
-        cost: {
-            input: 1,
-            output: 3,
-            cacheRead: 0.2,
-            cacheWrite: 0,
-        },
-        contextWindow: 1000000,
-        maxTokens: 128000,
-    },
     "xiaomi/mimo-v2.5": {
         id: "xiaomi/mimo-v2.5",
         name: "MiMo M2.5",
@@ -3267,9 +3220,9 @@ export const VERCEL_AI_GATEWAY_MODELS = {
         reasoning: true,
         input: ["text"],
         cost: {
-            input: 3,
-            output: 10.25,
-            cacheRead: 0.5,
+            input: 2.1,
+            output: 6.6,
+            cacheRead: 0.21,
             cacheWrite: 0,
         },
         contextWindow: 1000000,