@caupulican/pi-ai 0.80.7 → 0.80.9

package/dist/models.generated.js

@@ -1086,6 +1086,59 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 131072,
         },
+        "openai.gpt-5.4": {
+            id: "openai.gpt-5.4",
+            name: "GPT-5.4",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 2.75,
+                output: 16.5,
+                cacheRead: 0.275,
+                cacheWrite: 0,
+            },
+            contextWindow: 272000,
+            maxTokens: 128000,
+        },
+        "openai.gpt-5.5": {
+            id: "openai.gpt-5.5",
+            name: "GPT-5.5",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: true,
+            thinkingLevelMap: { "xhigh": "xhigh" },
+            input: ["text", "image"],
+            cost: {
+                input: 5.5,
+                output: 33,
+                cacheRead: 0.55,
+                cacheWrite: 0,
+            },
+            contextWindow: 272000,
+            maxTokens: 128000,
+        },
+        "openai.gpt-oss-120b": {
+            id: "openai.gpt-oss-120b",
+            name: "gpt-oss-120b",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.15,
+                output: 0.6,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
         "openai.gpt-oss-120b-1:0": {
             id: "openai.gpt-oss-120b-1:0",
             name: "gpt-oss-120b",
@@ -1103,6 +1156,23 @@ export const MODELS = {
             contextWindow: 128000,
             maxTokens: 16384,
         },
+        "openai.gpt-oss-20b": {
+            id: "openai.gpt-oss-20b",
+            name: "gpt-oss-20b",
+            api: "bedrock-converse-stream",
+            provider: "amazon-bedrock",
+            baseUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
+            reasoning: false,
+            input: ["text"],
+            cost: {
+                input: 0.07,
+                output: 0.3,
+                cacheRead: 0,
+                cacheWrite: 0,
+            },
+            contextWindow: 128000,
+            maxTokens: 16384,
+        },
         "openai.gpt-oss-20b-1:0": {
             id: "openai.gpt-oss-20b-1:0",
             name: "gpt-oss-20b",
@@ -3809,8 +3879,8 @@ export const MODELS = {
                 cacheRead: 0.1,
                 cacheWrite: 0,
             },
-            contextWindow: 128000,
-            maxTokens: 8192,
+            contextWindow: 262144,
+            maxTokens: 65536,
         },
         "accounts/fireworks/routers/glm-5p1-fast": {
             id: "accounts/fireworks/routers/glm-5p1-fast",
@@ -3830,6 +3900,24 @@ export const MODELS = {
             contextWindow: 202800,
             maxTokens: 131072,
         },
+        "accounts/fireworks/routers/kimi-k2p6-fast": {
+            id: "accounts/fireworks/routers/kimi-k2p6-fast",
+            name: "Kimi K2.6 Fast",
+            api: "anthropic-messages",
+            provider: "fireworks",
+            baseUrl: "https://api.fireworks.ai/inference",
+            compat: { "sendSessionAffinityHeaders": true, "supportsEagerToolInputStreaming": false, "supportsCacheControlOnTools": false, "supportsLongCacheRetention": false },
+            reasoning: true,
+            input: ["text", "image"],
+            cost: {
+                input: 2,
+                output: 8,
+                cacheRead: 0.3,
+                cacheWrite: 0,
+            },
+            contextWindow: 262000,
+            maxTokens: 262000,
+        },
         "accounts/fireworks/routers/kimi-k2p6-turbo": {
             id: "accounts/fireworks/routers/kimi-k2p6-turbo",
             name: "Kimi K2.6 Turbo",
@@ -5948,11 +6036,11 @@ export const MODELS = {
             api: "mistral-conversations",
             provider: "mistral",
             baseUrl: "https://api.mistral.ai",
-            reasoning: true,
+            reasoning: false,
             input: ["text", "image"],
             cost: {
-                input: 1.5,
-                output: 7.5,
+                input: 0.4,
+                output: 2,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -7950,9 +8038,9 @@ export const MODELS = {
             contextWindow: 200000,
             maxTokens: 32000,
         },
-        "nemotron-3-super-free": {
-            id: "nemotron-3-super-free",
-            name: "Nemotron 3 Super Free",
+        "nemotron-3-ultra-free": {
+            id: "nemotron-3-ultra-free",
+            name: "Nemotron 3 Ultra Free",
             api: "openai-completions",
             provider: "opencode",
             baseUrl: "https://opencode.ai/zen/v1",
@@ -7964,7 +8052,7 @@ export const MODELS = {
                 cacheRead: 0,
                 cacheWrite: 0,
             },
-            contextWindow: 204800,
+            contextWindow: 1000000,
             maxTokens: 128000,
         },
         "qwen3.5-plus": {
@@ -8211,7 +8299,7 @@ export const MODELS = {
                 cacheRead: 0.05,
                 cacheWrite: 0.625,
             },
-            contextWindow: 262144,
+            contextWindow: 1000000,
             maxTokens: 65536,
         },
         "qwen3.7-max": {
@@ -8245,7 +8333,7 @@ export const MODELS = {
                 cacheRead: 0.04,
                 cacheWrite: 0.5,
             },
-            contextWindow: 262144,
+            contextWindow: 1000000,
             maxTokens: 65536,
         },
     },
@@ -9273,12 +9361,12 @@ export const MODELS = {
             input: ["text", "image"],
             cost: {
                 input: 0.12,
-                output: 0.37,
-                cacheRead: 0,
+                output: 0.36,
+                cacheRead: 0.09,
                 cacheWrite: 0,
             },
             contextWindow: 262144,
-            maxTokens: 16384,
+            maxTokens: 8192,
         },
         "google/gemma-4-31b-it:free": {
             id: "google/gemma-4-31b-it:free",
@@ -9427,7 +9515,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.02,
-                output: 0.049999999999999996,
+                output: 0.03,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -9585,7 +9673,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 204800,
-            maxTokens: 131072,
+            maxTokens: 196608,
         },
         "minimax/minimax-m3": {
             id: "minimax/minimax-m3",
@@ -10116,6 +10204,40 @@ export const MODELS = {
             contextWindow: 1000000,
             maxTokens: 262144,
         },
+        "nvidia/nemotron-3-ultra-550b-a55b": {
+            id: "nvidia/nemotron-3-ultra-550b-a55b",
+            name: "NVIDIA: Nemotron 3 Ultra",
+            api: "openai-completions",
+            provider: "openrouter",
+            baseUrl: "https://openrouter.ai/api/v1",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.5,
+                output: 2.5,
+                cacheRead: 0.15,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 16384,
+        },
+        "nvidia/nemotron-3-ultra-550b-a55b:free": {
+            id: "nvidia/nemotron-3-ultra-550b-a55b:free",
+            name: "NVIDIA: Nemotron 3 Ultra (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: 1000000,
+            maxTokens: 65536,
+        },
         "nvidia/nemotron-nano-12b-v2-vl:free": {
             id: "nvidia/nemotron-nano-12b-v2-vl:free",
             name: "NVIDIA: Nemotron Nano 12B 2 VL (free)",
@@ -10235,23 +10357,6 @@ export const MODELS = {
             contextWindow: 8191,
             maxTokens: 4096,
         },
-        "openai/gpt-4-0314": {
-            id: "openai/gpt-4-0314",
-            name: "OpenAI: GPT-4 (older v0314)",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 30,
-                output: 60,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 8191,
-            maxTokens: 4096,
-        },
         "openai/gpt-4-1106-preview": {
             id: "openai/gpt-4-1106-preview",
             name: "OpenAI: GPT-4 Turbo (older v1106)",
@@ -11384,7 +11489,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 20000,
+            maxTokens: 16384,
         },
         "qwen/qwen3-30b-a3b-instruct-2507": {
             id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -11395,8 +11500,8 @@ export const MODELS = {
             reasoning: false,
             input: ["text"],
             cost: {
-                input: 0.0428,
-                output: 0.1716,
+                input: 0.04815,
+                output: 0.19305,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -12049,23 +12154,6 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 128000,
         },
-        "sao10k/l3-euryale-70b": {
-            id: "sao10k/l3-euryale-70b",
-            name: "Sao10k: Llama 3 Euryale 70B v2.1",
-            api: "openai-completions",
-            provider: "openrouter",
-            baseUrl: "https://openrouter.ai/api/v1",
-            reasoning: false,
-            input: ["text"],
-            cost: {
-                input: 1.48,
-                output: 1.48,
-                cacheRead: 0,
-                cacheWrite: 0,
-            },
-            contextWindow: 8192,
-            maxTokens: 8192,
-        },
         "sao10k/l3.1-euryale-70b": {
             id: "sao10k/l3.1-euryale-70b",
             name: "Sao10K: Llama 3.1 Euryale 70B v2.2",
@@ -12799,7 +12887,7 @@ export const MODELS = {
         },
         "deepseek-ai/DeepSeek-V3": {
             id: "deepseek-ai/DeepSeek-V3",
-            name: "DeepSeek V3",
+            name: "DeepSeek-V3",
             api: "openai-completions",
             provider: "together",
             baseUrl: "https://api.together.ai/v1",
@@ -12947,6 +13035,25 @@ export const MODELS = {
             contextWindow: 262144,
             maxTokens: 131000,
         },
+        "nvidia/nemotron-3-ultra-550b-a55b": {
+            id: "nvidia/nemotron-3-ultra-550b-a55b",
+            name: "Nemotron 3 Ultra 550B A55B",
+            api: "openai-completions",
+            provider: "together",
+            baseUrl: "https://api.together.ai/v1",
+            compat: { "supportsStore": false, "supportsDeveloperRole": false, "supportsReasoningEffort": false, "maxTokensField": "max_tokens", "supportsStrictMode": false, "supportsLongCacheRetention": false, "thinkingFormat": "together" },
+            reasoning: true,
+            thinkingLevelMap: { "minimal": null, "low": null, "medium": null },
+            input: ["text"],
+            cost: {
+                input: 0.6,
+                output: 3.6,
+                cacheRead: 0.2,
+                cacheWrite: 0,
+            },
+            contextWindow: 512300,
+            maxTokens: 512300,
+        },
         "openai/gpt-oss-120b": {
             id: "openai/gpt-oss-120b",
             name: "GPT OSS 120B",
@@ -13062,7 +13169,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
                 input: 1.3,
                 output: 7.8,
@@ -13334,7 +13441,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
                 input: 1.25,
                 output: 3.75,
@@ -14259,7 +14366,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
                 input: 0.6,
                 output: 2.4,
@@ -14276,7 +14383,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
                 input: 0.3,
                 output: 1.2,
@@ -14293,7 +14400,7 @@ export const MODELS = {
             provider: "vercel-ai-gateway",
             baseUrl: "https://ai-gateway.vercel.sh",
             reasoning: true,
-            input: ["text", "image"],
+            input: ["text"],
             cost: {
                 input: 0.6,
                 output: 2.4,
@@ -14643,6 +14750,23 @@ export const MODELS = {
             contextWindow: 256000,
             maxTokens: 32000,
         },
+        "nvidia/nemotron-3-ultra-550b-a55b": {
+            id: "nvidia/nemotron-3-ultra-550b-a55b",
+            name: "Nemotron 3 Ultra",
+            api: "anthropic-messages",
+            provider: "vercel-ai-gateway",
+            baseUrl: "https://ai-gateway.vercel.sh",
+            reasoning: true,
+            input: ["text"],
+            cost: {
+                input: 0.6,
+                output: 2.4,
+                cacheRead: 0.12,
+                cacheWrite: 0,
+            },
+            contextWindow: 1000000,
+            maxTokens: 65000,
+        },
         "nvidia/nemotron-nano-12b-v2-vl": {
             id: "nvidia/nemotron-nano-12b-v2-vl",
             name: "Nvidia Nemotron Nano 12B V2 VL",