diff --git a/packages/__tests__/cost/__snapshots__/registrySnapshots.test.ts.snap b/packages/__tests__/cost/__snapshots__/registrySnapshots.test.ts.snap
index a55441b574..0ad950ace1 100644
--- a/packages/__tests__/cost/__snapshots__/registrySnapshots.test.ts.snap
+++ b/packages/__tests__/cost/__snapshots__/registrySnapshots.test.ts.snap
@@ -3128,14 +3128,38 @@ exports[`Registry Snapshots endpoint configurations snapshot 1`] = `
         "*",
       ],
     },
+    "grok-4-fast-non-reasoning:xai": {
+      "context": 2000000,
+      "crossRegion": false,
+      "maxTokens": 2000000,
+      "modelId": "grok-4-fast-non-reasoning",
+      "parameters": [
+        "logprobs",
+        "max_tokens",
+        "response_format",
+        "seed",
+        "structured_outputs",
+        "temperature",
+        "tool_choice",
+        "tools",
+        "top_logprobs",
+        "top_p",
+      ],
+      "provider": "xai",
+      "ptbEnabled": true,
+      "regions": [
+        "*",
+      ],
+    },
     "grok-4-fast-reasoning:xai": {
       "context": 2000000,
       "crossRegion": false,
-      "maxTokens": 30000,
+      "maxTokens": 2000000,
       "modelId": "grok-4-fast",
       "parameters": [
         "logprobs",
         "max_tokens",
+        "reasoning",
         "response_format",
         "seed",
         "structured_outputs",
@@ -3483,6 +3507,7 @@ exports[`Registry Snapshots model coverage snapshot 1`] = `
     "xai",
     "xai",
     "xai",
+    "xai",
   ],
   "zai/glm-4": [
     "novita",
@@ -4673,6 +4698,12 @@ exports[`Registry Snapshots verify registry state 1`] = `
         "xai",
       ],
     },
+    {
+      "model": "grok-4-fast-non-reasoning",
+      "providers": [
+        "xai",
+      ],
+    },
     {
       "model": "grok-4-fast-reasoning",
       "providers": [
@@ -4897,7 +4928,7 @@ exports[`Registry Snapshots verify registry state 1`] = `
       "provider": "vertex",
     },
     {
-      "modelCount": 5,
+      "modelCount": 6,
       "provider": "xai",
     },
   ],
@@ -4935,6 +4966,7 @@ exports[`Registry Snapshots verify registry state 1`] = `
     "grok-3",
     "grok-3-mini",
     "grok-4",
+    "grok-4-fast-non-reasoning",
     "grok-4-fast-reasoning",
     "grok-code-fast-1",
     "kimi-k2",
@@ -4970,9 +5002,9 @@ exports[`Registry Snapshots verify registry state 1`] = `
     "claude-3.5-haiku:openrouter:*",
   ],
   "totalArchivedConfigs": 0,
-  "totalEndpoints": 138,
-  "totalModelProviderConfigs": 138,
-  "totalModelsWithPtb": 58,
+  "totalEndpoints": 139,
+  "totalModelProviderConfigs": 139,
+  "totalModelsWithPtb": 59,
   "totalProviders": 13,
 }
 `;
diff --git a/packages/cost/models/authors/xai/endpoints.ts b/packages/cost/models/authors/xai/endpoints.ts
index b9a832203a..4a343729ec 100644
--- a/packages/cost/models/authors/xai/endpoints.ts
+++ b/packages/cost/models/authors/xai/endpoints.ts
@@ -120,7 +120,7 @@ export const endpoints = {
       },
     ],
     contextLength: 2_000_000,
-    maxCompletionTokens: 30_000,
+    maxCompletionTokens: 2_000_000,
     supportedParameters: [
       "tools",
       "tool_choice",
@@ -131,7 +131,51 @@ export const endpoints = {
       "top_p",
       "seed",
       "logprobs",
-      "top_logprobs"
+      "top_logprobs",
+      "reasoning",
+    ],
+    ptbEnabled: true,
+    endpointConfigs: {
+      "*": {},
+    },
+  },
+  "grok-4-fast-non-reasoning:xai": {
+    providerModelId: "grok-4-fast-non-reasoning",
+    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: 2_000_000,
+    supportedParameters: [
+      "tools",
+      "tool_choice",
+      "structured_outputs",
+      "response_format",
+      "max_tokens",
+      "temperature",
+      "top_p",
+      "seed",
+      "logprobs",
+      "top_logprobs",
     ],
     ptbEnabled: true,
     endpointConfigs: {
diff --git a/packages/cost/models/authors/xai/models.ts b/packages/cost/models/authors/xai/models.ts
index f7024b988f..3d2a4530b5 100644
--- a/packages/cost/models/authors/xai/models.ts
+++ b/packages/cost/models/authors/xai/models.ts
@@ -28,12 +28,23 @@ export const models = {
     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,
+    contextLength: 2000000,
+    maxOutputTokens: 2000000,
     created: "2025-09-01T00:00:00.000Z",
     modality: { inputs: ["text", "image"], outputs: ["text"] },
     tokenizer: "Grok",
   },
+  "grok-4-fast-non-reasoning": {
+    name: "xAI Grok 4 Fast Non-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. This non-reasoning model specifically excludes reasoning capabilities.",
+    contextLength: 2000000,
+    maxOutputTokens: 2000000,
+    created: "2025-09-19T00:00:00.000Z",
+    modality: { inputs: ["text", "image", "audio"], outputs: ["text"] },
+    tokenizer: "Grok",
+  },
   "grok-3": {
     name: "xAI: Grok 3",
     author: "xai",
diff --git a/worker/test/ai-gateway/registry-xai.spec.ts b/worker/test/ai-gateway/registry-xai.spec.ts
index 8efeb56a63..9132b3b5c1 100644
--- a/worker/test/ai-gateway/registry-xai.spec.ts
+++ b/worker/test/ai-gateway/registry-xai.spec.ts
@@ -281,6 +281,204 @@ describe("xAI Registry Tests", () => {
         }));
     });
 
+    describe("grok-4-fast-non-reasoning", () => {
+      it("should handle xai provider", () =>
+        runGatewayTest({
+          model: "grok-4-fast-non-reasoning/xai",
+          expected: {
+            providers: [
+              {
+                url: "https://api.x.ai/v1/chat/completions",
+                response: "success",
+                model: "grok-4-fast-non-reasoning",
+                expects: xaiAuthExpectations,
+              },
+            ],
+            finalStatus: 200,
+          },
+        }));
+
+      it("should auto-select xai provider when none specified", () =>
+        runGatewayTest({
+          model: "grok-4-fast-non-reasoning",
+          expected: {
+            providers: [
+              {
+                url: "https://api.x.ai/v1/chat/completions",
+                response: "success",
+                model: "grok-4-fast-non-reasoning",
+                expects: xaiAuthExpectations,
+              },
+            ],
+            finalStatus: 200,
+          },
+        }));
+
+      it("should handle tool calls with xai provider", () =>
+        runGatewayTest({
+          model: "grok-4-fast-non-reasoning/xai",
+          request: {
+            body: {
+              messages: [{ role: "user", content: "What's the weather?" }],
+              tools: [
+                {
+                  type: "function",
+                  function: {
+                    name: "get_weather",
+                    description: "Get current weather",
+                    parameters: {
+                      type: "object",
+                      properties: {
+                        location: { type: "string" }
+                      },
+                      required: ["location"]
+                    }
+                  }
+                }
+              ],
+              tool_choice: "auto",
+              temperature: 0.7,
+              max_tokens: 1000
+            }
+          },
+          expected: {
+            providers: [
+              {
+                url: "https://api.x.ai/v1/chat/completions",
+                response: "success",
+                model: "grok-4-fast-non-reasoning",
+                expects: {
+                  ...xaiAuthExpectations,
+                  bodyContains: [
+                    "tools",
+                    "tool_choice",
+                    "get_weather",
+                    "temperature",
+                    "max_tokens"
+                  ]
+                }
+              }
+            ],
+            finalStatus: 200
+          }
+        }));
+
+      it("should handle response format with xai provider", () =>
+        runGatewayTest({
+          model: "grok-4-fast-non-reasoning/xai",
+          request: {
+            body: {
+              messages: [{ role: "user", content: "Generate JSON data" }],
+              response_format: { type: "json_object" },
+              temperature: 0.1,
+              top_p: 0.9
+            }
+          },
+          expected: {
+            providers: [
+              {
+                url: "https://api.x.ai/v1/chat/completions",
+                response: "success",
+                model: "grok-4-fast-non-reasoning",
+                expects: {
+                  ...xaiAuthExpectations,
+                  bodyContains: [
+                    "response_format",
+                    "json_object",
+                    "temperature",
+                    "top_p"
+                  ]
+                }
+              }
+            ],
+            finalStatus: 200
+          }
+        }));
+
+      it("should handle all supported parameters", () =>
+        runGatewayTest({
+          model: "grok-4-fast-non-reasoning/xai",
+          request: {
+            body: {
+              messages: [
+                { role: "user", content: "Test comprehensive parameters" }
+              ],
+              max_tokens: 1000,
+              temperature: 0.8,
+              top_p: 0.95,
+              seed: 12345,
+              logprobs: true,
+              top_logprobs: 5
+            }
+          },
+          expected: {
+            providers: [
+              {
+                url: "https://api.x.ai/v1/chat/completions",
+                response: "success",
+                model: "grok-4-fast-non-reasoning",
+                expects: {
+                  ...xaiAuthExpectations,
+                  bodyContains: [
+                    "max_tokens",
+                    "temperature",
+                    "top_p",
+                    "seed",
+                    "logprobs",
+                    "top_logprobs"
+                  ]
+                }
+              }
+            ],
+            finalStatus: 200
+          }
+        }));
+
+      it("should handle structured outputs", () =>
+        runGatewayTest({
+          model: "grok-4-fast-non-reasoning/xai",
+          request: {
+            body: {
+              messages: [
+                { role: "user", content: "Generate structured data" }
+              ],
+              response_format: {
+                type: "json_schema",
+                json_schema: {
+                  name: "user_data",
+                  schema: {
+                    type: "object",
+                    properties: {
+                      name: { type: "string" },
+                      age: { type: "number" }
+                    },
+                    required: ["name", "age"]
+                  }
+                }
+              }
+            }
+          },
+          expected: {
+            providers: [
+              {
+                url: "https://api.x.ai/v1/chat/completions",
+                response: "success",
+                model: "grok-4-fast-non-reasoning",
+                expects: {
+                  ...xaiAuthExpectations,
+                  bodyContains: [
+                    "response_format",
+                    "json_schema",
+                    "user_data"
+                  ]
+                }
+              }
+            ],
+            finalStatus: 200
+          }
+        }));
+    });
+
     describe("grok-3", () => {
       it("should handle xai provider", () =>
         runGatewayTest({
@@ -497,4 +695,102 @@ describe("xAI Registry Tests", () => {
         }
       }));
   });
+
+  describe("Error scenarios - grok-4-fast-non-reasoning", () => {
+    it("should handle xAI provider failure for grok-4-fast-non-reasoning", () =>
+      runGatewayTest({
+        model: "grok-4-fast-non-reasoning/xai",
+        expected: {
+          providers: [
+            {
+              url: "https://api.x.ai/v1/chat/completions",
+              response: "failure",
+              statusCode: 500,
+              errorMessage: "xAI service unavailable"
+            }
+          ],
+          finalStatus: 500
+        }
+      }));
+
+    it("should handle rate limiting from xAI for grok-4-fast-non-reasoning", () =>
+      runGatewayTest({
+        model: "grok-4-fast-non-reasoning/xai",
+        expected: {
+          providers: [
+            {
+              url: "https://api.x.ai/v1/chat/completions",
+              response: "failure",
+              statusCode: 429,
+              errorMessage: "Rate limit exceeded"
+            }
+          ],
+          finalStatus: 429
+        }
+      }));
+
+    it("should handle authentication failure for grok-4-fast-non-reasoning", () =>
+      runGatewayTest({
+        model: "grok-4-fast-non-reasoning/xai",
+        expected: {
+          providers: [
+            {
+              url: "https://api.x.ai/v1/chat/completions",
+              response: "failure",
+              statusCode: 401,
+              errorMessage: "Invalid API key"
+            }
+          ],
+          finalStatus: 401
+        }
+      }));
+
+    it("should handle model not found error for grok-4-fast-non-reasoning", () =>
+      runGatewayTest({
+        model: "grok-4-fast-non-reasoning/xai",
+        expected: {
+          providers: [
+            {
+              url: "https://api.x.ai/v1/chat/completions",
+              response: "failure",
+              statusCode: 404,
+              errorMessage: "Model not found"
+            }
+          ],
+          finalStatus: 500
+        }
+      }));
+
+    it("should handle timeout for grok-4-fast-non-reasoning", () =>
+      runGatewayTest({
+        model: "grok-4-fast-non-reasoning/xai",
+        expected: {
+          providers: [
+            {
+              url: "https://api.x.ai/v1/chat/completions",
+              response: "failure",
+              statusCode: 408,
+              errorMessage: "Request timeout"
+            }
+          ],
+          finalStatus: 500
+        }
+      }));
+
+    it("should handle bad request error for grok-4-fast-non-reasoning", () =>
+      runGatewayTest({
+        model: "grok-4-fast-non-reasoning/xai",
+        expected: {
+          providers: [
+            {
+              url: "https://api.x.ai/v1/chat/completions",
+              response: "failure",
+              statusCode: 400,
+              errorMessage: "Bad request"
+            }
+          ],
+          finalStatus: 500
+        }
+      }));
+  });
 });