@earendil-works/pi-ai 0.80.6 → 0.80.7

package/dist/providers/openrouter.models.js

@@ -189,6 +189,7 @@ export const OPENROUTER_MODELS = {
         baseUrl: "https://openrouter.ai/api/v1",
         compat: { "thinkingFormat": "openrouter", "cacheControlFormat": "anthropic" },
         reasoning: true,
+        thinkingLevelMap: { "off": null, "xhigh": "xhigh", "max": "max" },
         input: ["text", "image"],
         cost: {
             input: 10,
@@ -458,24 +459,6 @@ export const OPENROUTER_MODELS = {
         contextWindow: 262144,
         maxTokens: 80000,
     },
-    "arcee-ai/trinity-mini": {
-        id: "arcee-ai/trinity-mini",
-        name: "Arcee AI: Trinity Mini",
-        api: "openai-completions",
-        provider: "openrouter",
-        baseUrl: "https://openrouter.ai/api/v1",
-        compat: { "supportsDeveloperRole": false, "thinkingFormat": "openrouter" },
-        reasoning: true,
-        input: ["text"],
-        cost: {
-            input: 0.045,
-            output: 0.15,
-            cacheRead: 0,
-            cacheWrite: 0,
-        },
-        contextWindow: 131072,
-        maxTokens: 131072,
-    },
     "arcee-ai/virtuoso-large": {
         id: "arcee-ai/virtuoso-large",
         name: "Arcee AI: Virtuoso Large",
@@ -653,7 +636,7 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0,
             cacheWrite: 0,
         },
-        contextWindow: 131072,
+        contextWindow: 128000,
         maxTokens: 16000,
     },
     "deepseek/deepseek-chat-v3-0324": {
@@ -684,8 +667,8 @@ export const OPENROUTER_MODELS = {
         reasoning: true,
         input: ["text"],
         cost: {
-            input: 0.21,
-            output: 0.79,
+            input: 0.25,
+            output: 0.95,
             cacheRead: 0.13,
             cacheWrite: 0,
         },
@@ -707,7 +690,7 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0,
             cacheWrite: 0,
         },
-        contextWindow: 163840,
+        contextWindow: 64000,
         maxTokens: 16000,
     },
     "deepseek/deepseek-r1-0528": {
@@ -756,12 +739,12 @@ export const OPENROUTER_MODELS = {
         reasoning: true,
         input: ["text"],
         cost: {
-            input: 0.2288,
-            output: 0.3432,
-            cacheRead: 0.02288,
+            input: 0.2145,
+            output: 0.32175,
+            cacheRead: 0.02145,
             cacheWrite: 0,
         },
-        contextWindow: 131072,
+        contextWindow: 128000,
         maxTokens: 64000,
     },
     "deepseek/deepseek-v3.2-exp": {
@@ -1015,7 +998,7 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0.2,
             cacheWrite: 0.375,
         },
-        contextWindow: 1048756,
+        contextWindow: 1048576,
         maxTokens: 65536,
     },
     "google/gemini-3.5-flash": {
@@ -1105,7 +1088,7 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0,
             cacheWrite: 0,
         },
-        contextWindow: 262144,
+        contextWindow: 131072,
         maxTokens: 32768,
     },
     "google/gemma-4-31b-it": {
@@ -1118,13 +1101,13 @@ export const OPENROUTER_MODELS = {
         reasoning: true,
         input: ["text", "image"],
         cost: {
-            input: 0.12,
+            input: 0.06,
             output: 0.35,
-            cacheRead: 0.09,
+            cacheRead: 0,
             cacheWrite: 0,
         },
         contextWindow: 262144,
-        maxTokens: 262144,
+        maxTokens: 8192,
     },
     "google/gemma-4-31b-it:free": {
         id: "google/gemma-4-31b-it:free",
@@ -1142,7 +1125,7 @@ export const OPENROUTER_MODELS = {
             cacheWrite: 0,
         },
         contextWindow: 262144,
-        maxTokens: 8192,
+        maxTokens: 32768,
     },
     "ibm-granite/granite-4.1-8b": {
         id: "ibm-granite/granite-4.1-8b",
@@ -1235,6 +1218,24 @@ export const OPENROUTER_MODELS = {
         contextWindow: 262144,
         maxTokens: 65536,
     },
+    "kwaipilot/kat-coder-air-v2.5": {
+        id: "kwaipilot/kat-coder-air-v2.5",
+        name: "Kwaipilot: KAT-Coder-Air V2.5",
+        api: "openai-completions",
+        provider: "openrouter",
+        baseUrl: "https://openrouter.ai/api/v1",
+        compat: { "supportsDeveloperRole": false, "thinkingFormat": "openrouter" },
+        reasoning: false,
+        input: ["text"],
+        cost: {
+            input: 0.15,
+            output: 0.6,
+            cacheRead: 0.03,
+            cacheWrite: 0,
+        },
+        contextWindow: 256000,
+        maxTokens: 80000,
+    },
     "kwaipilot/kat-coder-pro-v2": {
         id: "kwaipilot/kat-coder-pro-v2",
         name: "Kwaipilot: KAT-Coder-Pro V2",
@@ -1253,23 +1254,23 @@ export const OPENROUTER_MODELS = {
         contextWindow: 256000,
         maxTokens: 80000,
     },
-    "liquid/lfm-2.5-1.2b-thinking:free": {
-        id: "liquid/lfm-2.5-1.2b-thinking:free",
-        name: "LiquidAI: LFM2.5-1.2B-Thinking (free)",
+    "kwaipilot/kat-coder-pro-v2.5": {
+        id: "kwaipilot/kat-coder-pro-v2.5",
+        name: "Kwaipilot: KAT-Coder-Pro V2.5",
         api: "openai-completions",
         provider: "openrouter",
         baseUrl: "https://openrouter.ai/api/v1",
         compat: { "supportsDeveloperRole": false, "thinkingFormat": "openrouter" },
-        reasoning: true,
+        reasoning: false,
         input: ["text"],
         cost: {
-            input: 0,
-            output: 0,
-            cacheRead: 0,
+            input: 0.74,
+            output: 2.96,
+            cacheRead: 0.15,
             cacheWrite: 0,
         },
-        contextWindow: 32768,
-        maxTokens: 4096,
+        contextWindow: 256000,
+        maxTokens: 80000,
     },
     "meta-llama/llama-3.1-70b-instruct": {
         id: "meta-llama/llama-3.1-70b-instruct",
@@ -1340,7 +1341,7 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0,
             cacheWrite: 0,
         },
-        contextWindow: 131072,
+        contextWindow: 65536,
         maxTokens: 4096,
     },
     "meta-llama/llama-4-maverick": {
@@ -1353,8 +1354,8 @@ export const OPENROUTER_MODELS = {
         reasoning: false,
         input: ["text", "image"],
         cost: {
-            input: 0.15,
-            output: 0.6,
+            input: 0.2,
+            output: 0.8,
             cacheRead: 0,
             cacheWrite: 0,
         },
@@ -1376,7 +1377,7 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0,
             cacheWrite: 0,
         },
-        contextWindow: 10000000,
+        contextWindow: 327680,
         maxTokens: 16384,
     },
     "minimax/minimax-m1": {
@@ -1448,7 +1449,7 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0.05,
             cacheWrite: 0,
         },
-        contextWindow: 204800,
+        contextWindow: 196608,
         maxTokens: 196608,
     },
     "minimax/minimax-m2.7": {
@@ -1466,7 +1467,7 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0,
             cacheWrite: 0,
         },
-        contextWindow: 204800,
+        contextWindow: 196608,
         maxTokens: 196608,
     },
     "minimax/minimax-m3": {
@@ -1484,7 +1485,7 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0.06,
             cacheWrite: 0,
         },
-        contextWindow: 1048576,
+        contextWindow: 1000000,
         maxTokens: 131072,
     },
     "mistralai/codestral-2508": {
@@ -1893,9 +1894,9 @@ export const OPENROUTER_MODELS = {
         reasoning: true,
         input: ["text", "image"],
         cost: {
-            input: 0.72,
+            input: 0.719,
             output: 3.49,
-            cacheRead: 0.159,
+            cacheRead: 0.149,
             cacheWrite: 0,
         },
         contextWindow: 262144,
@@ -2024,7 +2025,7 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0,
             cacheWrite: 0,
         },
-        contextWindow: 1000000,
+        contextWindow: 262144,
         maxTokens: 4096,
     },
     "nvidia/nemotron-3-super-120b-a12b:free": {
@@ -2042,7 +2043,7 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0,
             cacheWrite: 0,
         },
-        contextWindow: 1000000,
+        contextWindow: 262144,
         maxTokens: 262144,
     },
     "nvidia/nemotron-3-ultra-550b-a55b": {
@@ -2060,7 +2061,7 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0.1,
             cacheWrite: 0,
         },
-        contextWindow: 1000000,
+        contextWindow: 262144,
         maxTokens: 16384,
     },
     "nvidia/nemotron-3-ultra-550b-a55b:free": {
@@ -2453,11 +2454,11 @@ export const OPENROUTER_MODELS = {
         cost: {
             input: 0.05,
             output: 0.4,
-            cacheRead: 0.01,
+            cacheRead: 0.005,
             cacheWrite: 0,
         },
         contextWindow: 400000,
-        maxTokens: 4096,
+        maxTokens: 128000,
     },
     "openai/gpt-5-pro": {
         id: "openai/gpt-5-pro",
@@ -2489,7 +2490,7 @@ export const OPENROUTER_MODELS = {
         cost: {
             input: 1.25,
             output: 10,
-            cacheRead: 0.13,
+            cacheRead: 0.125,
             cacheWrite: 0,
         },
         contextWindow: 400000,
@@ -2973,26 +2974,8 @@ export const OPENROUTER_MODELS = {
         reasoning: true,
         input: ["text"],
         cost: {
-            input: 0.036,
-            output: 0.18,
-            cacheRead: 0,
-            cacheWrite: 0,
-        },
-        contextWindow: 131072,
-        maxTokens: 4096,
-    },
-    "openai/gpt-oss-120b:free": {
-        id: "openai/gpt-oss-120b:free",
-        name: "OpenAI: gpt-oss-120b (free)",
-        api: "openai-completions",
-        provider: "openrouter",
-        baseUrl: "https://openrouter.ai/api/v1",
-        compat: { "thinkingFormat": "openrouter" },
-        reasoning: true,
-        input: ["text"],
-        cost: {
-            input: 0,
-            output: 0,
+            input: 0.03,
+            output: 0.15,
             cacheRead: 0,
             cacheWrite: 0,
         },
@@ -3356,7 +3339,7 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0,
             cacheWrite: 0,
         },
-        contextWindow: 131072,
+        contextWindow: 32768,
         maxTokens: 16384,
     },
     "qwen/qwen-2.5-7b-instruct": {
@@ -3374,7 +3357,7 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0,
             cacheWrite: 0,
         },
-        contextWindow: 131072,
+        contextWindow: 32768,
         maxTokens: 32768,
     },
     "qwen/qwen-plus": {
@@ -3446,7 +3429,7 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0,
             cacheWrite: 0,
         },
-        contextWindow: 131702,
+        contextWindow: 40960,
         maxTokens: 40960,
     },
     "qwen/qwen3-235b-a22b": {
@@ -3478,7 +3461,7 @@ export const OPENROUTER_MODELS = {
         input: ["text"],
         cost: {
             input: 0.09,
-            output: 0.1,
+            output: 0.55,
             cacheRead: 0,
             cacheWrite: 0,
         },
@@ -3500,7 +3483,7 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0,
             cacheWrite: 0,
         },
-        contextWindow: 262144,
+        contextWindow: 131072,
         maxTokens: 4096,
     },
     "qwen/qwen3-30b-a3b": {
@@ -3518,7 +3501,7 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0,
             cacheWrite: 0,
         },
-        contextWindow: 131072,
+        contextWindow: 40960,
         maxTokens: 16384,
     },
     "qwen/qwen3-30b-a3b-instruct-2507": {
@@ -3536,7 +3519,7 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0,
             cacheWrite: 0,
         },
-        contextWindow: 131072,
+        contextWindow: 128000,
         maxTokens: 32000,
     },
     "qwen/qwen3-30b-a3b-thinking-2507": {
@@ -3554,7 +3537,7 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0,
             cacheWrite: 0,
         },
-        contextWindow: 131072,
+        contextWindow: 81920,
         maxTokens: 32768,
     },
     "qwen/qwen3-32b": {
@@ -3572,7 +3555,7 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0,
             cacheWrite: 0,
         },
-        contextWindow: 131072,
+        contextWindow: 40960,
         maxTokens: 16384,
     },
     "qwen/qwen3-8b": {
@@ -3608,7 +3591,7 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0,
             cacheWrite: 0,
         },
-        contextWindow: 1048576,
+        contextWindow: 262144,
         maxTokens: 65536,
     },
     "qwen/qwen3-coder-30b-a3b-instruct": {
@@ -3698,7 +3681,7 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0,
             cacheWrite: 0,
         },
-        contextWindow: 1048576,
+        contextWindow: 262000,
         maxTokens: 262000,
     },
     "qwen/qwen3-max": {
@@ -3788,7 +3771,7 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0,
             cacheWrite: 0,
         },
-        contextWindow: 262144,
+        contextWindow: 131072,
         maxTokens: 32768,
     },
     "qwen/qwen3-vl-235b-a22b-instruct": {
@@ -3842,7 +3825,7 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0,
             cacheWrite: 0,
         },
-        contextWindow: 262144,
+        contextWindow: 131072,
         maxTokens: 32768,
     },
     "qwen/qwen3-vl-30b-a3b-thinking": {
@@ -3878,7 +3861,7 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0,
             cacheWrite: 0,
         },
-        contextWindow: 262144,
+        contextWindow: 131072,
         maxTokens: 32768,
     },
     "qwen/qwen3-vl-8b-instruct": {
@@ -3896,7 +3879,7 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0,
             cacheWrite: 0,
         },
-        contextWindow: 256000,
+        contextWindow: 131072,
         maxTokens: 32768,
     },
     "qwen/qwen3-vl-8b-thinking": {
@@ -3914,7 +3897,7 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0,
             cacheWrite: 0,
         },
-        contextWindow: 256000,
+        contextWindow: 131072,
         maxTokens: 32768,
     },
     "qwen/qwen3.5-122b-a10b": {
@@ -3986,7 +3969,7 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0.111,
             cacheWrite: 0,
         },
-        contextWindow: 256000,
+        contextWindow: 131072,
         maxTokens: 4096,
     },
     "qwen/qwen3.5-9b": {
@@ -4071,13 +4054,13 @@ export const OPENROUTER_MODELS = {
         reasoning: true,
         input: ["text", "image"],
         cost: {
-            input: 0.285,
+            input: 0.289,
             output: 2.4,
-            cacheRead: 0.15,
+            cacheRead: 0,
             cacheWrite: 0,
         },
-        contextWindow: 262144,
-        maxTokens: 262140,
+        contextWindow: 131072,
+        maxTokens: 131072,
     },
     "qwen/qwen3.6-35b-a3b": {
         id: "qwen/qwen3.6-35b-a3b",
@@ -4472,7 +4455,7 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0.028,
             cacheWrite: 0,
         },
-        contextWindow: 1048576,
+        contextWindow: 262144,
         maxTokens: 4096,
     },
     "xiaomi/mimo-v2.5-pro": {
@@ -4558,12 +4541,12 @@ export const OPENROUTER_MODELS = {
         input: ["text"],
         cost: {
             input: 0.43,
-            output: 1.74,
+            output: 1.75,
             cacheRead: 0.08,
             cacheWrite: 0,
         },
-        contextWindow: 202752,
-        maxTokens: 131072,
+        contextWindow: 198000,
+        maxTokens: 16384,
     },
     "z-ai/glm-4.6v": {
         id: "z-ai/glm-4.6v",
@@ -4634,8 +4617,8 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0.119,
             cacheWrite: 0,
         },
-        contextWindow: 202752,
-        maxTokens: 4096,
+        contextWindow: 198000,
+        maxTokens: 128000,
     },
     "z-ai/glm-5-turbo": {
         id: "z-ai/glm-5-turbo",
@@ -4670,7 +4653,7 @@ export const OPENROUTER_MODELS = {
             cacheRead: 0.1794,
             cacheWrite: 0,
         },
-        contextWindow: 202752,
+        contextWindow: 200000,
         maxTokens: 128000,
     },
     "z-ai/glm-5.2": {
@@ -4684,13 +4667,13 @@ export const OPENROUTER_MODELS = {
         thinkingLevelMap: { "xhigh": "xhigh" },
         input: ["text"],
         cost: {
-            input: 0.532,
-            output: 1.672,
-            cacheRead: 0.0988,
+            input: 0.924,
+            output: 2.904,
+            cacheRead: 0.1716,
             cacheWrite: 0,
         },
-        contextWindow: 1048576,
-        maxTokens: 131072,
+        contextWindow: 1024000,
+        maxTokens: 128000,
     },
     "z-ai/glm-5v-turbo": {
         id: "z-ai/glm-5v-turbo",