xAI/grok-4-fast (#5006)

* integrate grok 4 fast with zai

* test

* fix release date;

* update model name

* update tests

Author: juliettech13

packages/__tests__/cost/__snapshots__/registrySnapshots.test.ts.snap

@@ -3099,6 +3099,29 @@ exports[`Registry Snapshots endpoint configurations snapshot 1`] = `
         "*",
       ],
     },
+    "grok-4-fast-reasoning:xai": {
+      "context": 2000000,
+      "crossRegion": false,
+      "maxTokens": 30000,
+      "modelId": "grok-4-fast",
+      "parameters": [
+        "logprobs",
+        "max_tokens",
+        "response_format",
+        "seed",
+        "structured_outputs",
+        "temperature",
+        "tool_choice",
+        "tools",
+        "top_logprobs",
+        "top_p",
+      ],
+      "provider": "xai",
+      "ptbEnabled": true,
+      "regions": [
+        "*",
+      ],
+    },
     "grok-4:openrouter": {
       "context": 256000,
       "crossRegion": false,
@@ -3429,6 +3452,7 @@ exports[`Registry Snapshots model coverage snapshot 1`] = `
     "xai",
     "xai",
     "xai",
+    "xai",
   ],
   "zai/glm-4": [
     "novita",
@@ -4612,6 +4636,12 @@ exports[`Registry Snapshots verify registry state 1`] = `
         "xai",
       ],
     },
+    {
+      "model": "grok-4-fast-reasoning",
+      "providers": [
+        "xai",
+      ],
+    },
     {
       "model": "grok-code-fast-1",
       "providers": [
@@ -4825,7 +4855,7 @@ exports[`Registry Snapshots verify registry state 1`] = `
       "provider": "vertex",
     },
     {
-      "modelCount": 4,
+      "modelCount": 5,
       "provider": "xai",
     },
   ],
@@ -4863,6 +4893,7 @@ exports[`Registry Snapshots verify registry state 1`] = `
     "grok-3",
     "grok-3-mini",
     "grok-4",
+    "grok-4-fast-reasoning",
     "grok-code-fast-1",
     "kimi-k2",
     "kimi-k2-0905",
@@ -4897,9 +4928,9 @@ exports[`Registry Snapshots verify registry state 1`] = `
     "claude-3.5-haiku:openrouter:*",
   ],
   "totalArchivedConfigs": 0,
-  "totalEndpoints": 136,
-  "totalModelProviderConfigs": 136,
-  "totalModelsWithPtb": 57,
+  "totalEndpoints": 137,
+  "totalModelProviderConfigs": 137,
+  "totalModelsWithPtb": 58,
   "totalProviders": 12,
 }
 `;

packages/cost/models/authors/xai/endpoints.ts

@@ -95,6 +95,49 @@ export const endpoints = {
       "*": {},
     },
   },
+  "grok-4-fast-reasoning:xai": {
+    providerModelId: "grok-4-fast",
+    provider: "xai",
+    author: "xai",
+    pricing: [
+      {
+        threshold: 0,
+        input: 0.0000002, // $0.20 per 1M tokens (up to 128K context)
+        output: 0.0000005, // $0.50 per 1M tokens (up to 128K context)
+        web_search: 0.025, // $25.00 per 1K sources
+        cacheMultipliers: {
+          cachedInput: 0.25, // $0.05 / $0.20 = 0.25
+        },
+      },
+      {
+        threshold: 128000, // Above 128K context window
+        input: 0.0000004, // $0.40 per 1M tokens (over 128K context)
+        output: 0.000001, // $1.00 per 1M tokens (over 128K context)
+        web_search: 0.025, // $25.00 per 1K sources
+        cacheMultipliers: {
+          cachedInput: 0.125, // $0.05 / $0.40 = 0.125
+        },
+      },
+    ],
+    contextLength: 2_000_000,
+    maxCompletionTokens: 30_000,
+    supportedParameters: [
+      "tools",
+      "tool_choice",
+      "structured_outputs",
+      "response_format",
+      "max_tokens",
+      "temperature",
+      "top_p",
+      "seed",
+      "logprobs",
+      "top_logprobs"
+    ],
+    ptbEnabled: true,
+    endpointConfigs: {
+      "*": {},
+    },
+  },
   "grok-3:xai": {
     providerModelId: "grok-3",
     provider: "xai",

packages/cost/models/authors/xai/models.ts

@@ -23,6 +23,17 @@ export const models = {
     modality: { inputs: ["text"], outputs: ["text"] },
     tokenizer: "Grok",
   },
+  "grok-4-fast-reasoning": {
+    name: "xAI: Grok 4 Fast Reasoning",
+    author: "xai",
+    description:
+      "Grok 4 Fast is xAI's latest advancement in cost-efficient reasoning models. Built on xAI’s learnings from Grok 4, Grok 4 Fast delivers frontier-level performance across Enterprise and Consumer domains—with exceptional token efficiency. This model pushes the boundaries for smaller and faster AI, making high-quality reasoning accessible to more users and developers. Grok 4 Fast features state-of-the-art (SOTA) cost-efficiency, cutting-edge web and X search capabilities, a 2M token context window, and a unified architecture that blends reasoning and non-reasoning modes in one model.",
+    contextLength: 2_000_000,
+    maxOutputTokens: 30_000,
+    created: "2025-09-01T00:00:00.000Z",
+    modality: { inputs: ["text", "image"], outputs: ["text"] },
+    tokenizer: "Grok",
+  },
   "grok-3": {
     name: "xAI: Grok 3",
     author: "xai",
@@ -47,4 +58,4 @@ export const models = {
   },
 } satisfies Record<string, ModelConfig>;
 
-export type GrokModelName = keyof typeof models;
+export type GrokModelName = keyof typeof models;