@fleetagent/pi-ai 0.0.7 → 0.0.8

package/dist/models.generated.js

@@ -1081,6 +1081,59 @@ 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",
@@ -1098,6 +1151,23 @@ 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",
@@ -5919,11 +5989,11 @@ 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,
             },
@@ -8181,7 +8251,7 @@ export const MODELS = {
                 cacheRead: 0.05,
                 cacheWrite: 0.625,
             },
-            contextWindow: 262144,
+            contextWindow: 1000000,
             maxTokens: 65536,
         },
         "qwen3.7-max": {
@@ -8215,7 +8285,7 @@ export const MODELS = {
                 cacheRead: 0.04,
                 cacheWrite: 0.5,
             },
-            contextWindow: 262144,
+            contextWindow: 1000000,
             maxTokens: 65536,
         },
     },
@@ -9395,7 +9465,7 @@ export const MODELS = {
             input: ["text"],
             cost: {
                 input: 0.02,
-                output: 0.049999999999999996,
+                output: 0.03,
                 cacheRead: 0,
                 cacheWrite: 0,
             },
@@ -11369,7 +11439,7 @@ export const MODELS = {
                 cacheWrite: 0,
             },
             contextWindow: 131072,
-            maxTokens: 20000,
+            maxTokens: 16384,
         },
         "qwen/qwen3-30b-a3b-instruct-2507": {
             id: "qwen/qwen3-30b-a3b-instruct-2507",
@@ -12784,7 +12854,7 @@ 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",
@@ -12932,6 +13002,25 @@ 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",
@@ -14636,12 +14725,12 @@ export const MODELS = {
             reasoning: true,
             input: ["text"],
             cost: {
-                input: 0.5,
-                output: 2.5,
-                cacheRead: 0.15,
+                input: 0.6,
+                output: 2.4,
+                cacheRead: 0.12,
                 cacheWrite: 0,
             },
-            contextWindow: 262144,
+            contextWindow: 1000000,
             maxTokens: 65000,
         },
         "nvidia/nemotron-nano-12b-v2-vl": {