diff --git a/packages/ai-providers/server-ai-openai/__tests__/OpenAIProvider.test.ts b/packages/ai-providers/server-ai-openai/__tests__/OpenAIProvider.test.ts
index d94326d01..0abfef7f9 100644
--- a/packages/ai-providers/server-ai-openai/__tests__/OpenAIProvider.test.ts
+++ b/packages/ai-providers/server-ai-openai/__tests__/OpenAIProvider.test.ts
@@ -199,6 +199,157 @@ describe('OpenAIProvider', () => {
     });
   });
 
+  describe('invokeStructuredModel', () => {
+    it('invokes OpenAI with structured output and returns parsed response', async () => {
+      const mockResponse = {
+        choices: [
+          {
+            message: {
+              content: '{"name": "John", "age": 30, "city": "New York"}',
+            },
+          },
+        ],
+        usage: {
+          prompt_tokens: 20,
+          completion_tokens: 10,
+          total_tokens: 30,
+        },
+      };
+
+      (mockOpenAI.chat.completions.create as jest.Mock).mockResolvedValue(mockResponse as any);
+
+      const messages = [{ role: 'user' as const, content: 'Tell me about a person' }];
+      const responseStructure = {
+        type: 'object',
+        properties: {
+          name: { type: 'string' },
+          age: { type: 'number' },
+          city: { type: 'string' },
+        },
+        required: ['name', 'age', 'city'],
+      };
+
+      const result = await provider.invokeStructuredModel(messages, responseStructure);
+
+      expect(mockOpenAI.chat.completions.create).toHaveBeenCalledWith({
+        model: 'gpt-3.5-turbo',
+        messages: [{ role: 'user', content: 'Tell me about a person' }],
+        response_format: {
+          type: 'json_schema',
+          json_schema: {
+            name: 'structured_output',
+            schema: responseStructure,
+            strict: true,
+          },
+        },
+      });
+
+      expect(result).toEqual({
+        data: {
+          name: 'John',
+          age: 30,
+          city: 'New York',
+        },
+        rawResponse: '{"name": "John", "age": 30, "city": "New York"}',
+        metrics: {
+          success: true,
+          usage: {
+            total: 30,
+            input: 20,
+            output: 10,
+          },
+        },
+      });
+    });
+
+    it('returns unsuccessful response when no content in structured response', async () => {
+      const mockResponse = {
+        choices: [
+          {
+            message: {
+              // content is missing
+            },
+          },
+        ],
+      };
+
+      (mockOpenAI.chat.completions.create as jest.Mock).mockResolvedValue(mockResponse as any);
+
+      const messages = [{ role: 'user' as const, content: 'Tell me about a person' }];
+      const responseStructure = { type: 'object' };
+
+      const result = await provider.invokeStructuredModel(messages, responseStructure);
+
+      expect(result).toEqual({
+        data: {},
+        rawResponse: '',
+        metrics: {
+          success: false,
+          usage: undefined,
+        },
+      });
+    });
+
+    it('handles JSON parsing errors gracefully', async () => {
+      const mockResponse = {
+        choices: [
+          {
+            message: {
+              content: 'invalid json content',
+            },
+          },
+        ],
+        usage: {
+          prompt_tokens: 10,
+          completion_tokens: 5,
+          total_tokens: 15,
+        },
+      };
+
+      (mockOpenAI.chat.completions.create as jest.Mock).mockResolvedValue(mockResponse as any);
+
+      const messages = [{ role: 'user' as const, content: 'Tell me about a person' }];
+      const responseStructure = { type: 'object' };
+
+      const result = await provider.invokeStructuredModel(messages, responseStructure);
+
+      expect(result).toEqual({
+        data: {},
+        rawResponse: 'invalid json content',
+        metrics: {
+          success: false,
+          usage: {
+            total: 15,
+            input: 10,
+            output: 5,
+          },
+        },
+      });
+    });
+
+    it('handles empty choices array in structured response', async () => {
+      const mockResponse = {
+        choices: [],
+      };
+
+      (mockOpenAI.chat.completions.create as jest.Mock).mockResolvedValue(mockResponse as any);
+
+      const messages = [{ role: 'user' as const, content: 'Tell me about a person' }];
+      const responseStructure = { type: 'object' };
+
+      const result = await provider.invokeStructuredModel(messages, responseStructure);
+
+      expect(result).toEqual({
+        data: {},
+        rawResponse: '',
+        metrics: {
+          success: false,
+          usage: undefined,
+        },
+      });
+    });
+  });
+
   describe('getClient', () => {
     it('returns the underlying OpenAI client', () => {
       const client = provider.getClient();
diff --git a/packages/ai-providers/server-ai-openai/src/OpenAIProvider.ts b/packages/ai-providers/server-ai-openai/src/OpenAIProvider.ts
index 7b30012b8..7376bce09 100644
--- a/packages/ai-providers/server-ai-openai/src/OpenAIProvider.ts
+++ b/packages/ai-providers/server-ai-openai/src/OpenAIProvider.ts
@@ -8,6 +8,7 @@ import type {
   LDLogger,
   LDMessage,
   LDTokenUsage,
+  StructuredResponse,
 } from '@launchdarkly/server-sdk-ai';
 
 /**
@@ -55,12 +56,81 @@ export class OpenAIProvider extends AIProvider {
    * Invoke the OpenAI model with an array of messages.
    */
   async invokeModel(messages: LDMessage[]): Promise<ChatResponse> {
-    // Call OpenAI chat completions API
-    const response = await this._client.chat.completions.create({
-      model: this._modelName,
-      messages,
-      ...this._parameters,
-    });
+    try {
+      const response = await this._client.chat.completions.create({
+        ...this._parameters,
+        model: this._modelName,
+        messages,
+      });
+
+      // Generate metrics early (assumes success by default)
+      const metrics = OpenAIProvider.getAIMetricsFromResponse(response);
+
+      // Safely extract the first choice content using optional chaining
+      const content = response?.choices?.[0]?.message?.content || '';
+
+      if (!content) {
+        this.logger?.warn('OpenAI response has no content available');
+        metrics.success = false;
+      }
+
+      const assistantMessage: LDMessage = {
+        role: 'assistant',
+        content,
+      };
+
+      return {
+        message: assistantMessage,
+        metrics,
+      };
+    } catch (error) {
+      this.logger?.warn('OpenAI model invocation failed:', error);
+
+      return {
+        message: {
+          role: 'assistant',
+          content: '',
+        },
+        metrics: {
+          success: false,
+        },
+      };
+    }
+  }
+
+  /**
+   * Invoke the OpenAI model with structured output support.
+   */
+  async invokeStructuredModel(
+    messages: LDMessage[],
+    responseStructure: Record<string, unknown>,
+  ): Promise<StructuredResponse> {
+    let response;
+    try {
+      response = await this._client.chat.completions.create({
+        ...this._parameters,
+        model: this._modelName,
+        messages,
+        response_format: {
+          type: 'json_schema',
+          json_schema: {
+            name: 'structured_output',
+            schema: responseStructure,
+            strict: true,
+          },
+        },
+      });
+    } catch (error) {
+      this.logger?.warn('OpenAI structured model invocation failed:', error);
+
+      return {
+        data: {},
+        rawResponse: '',
+        metrics: {
+          success: false,
+        },
+      };
+    }
 
     // Generate metrics early (assumes success by default)
     const metrics = OpenAIProvider.getAIMetricsFromResponse(response);
@@ -69,20 +139,32 @@ export class OpenAIProvider extends AIProvider {
     const content = response?.choices?.[0]?.message?.content || '';
 
     if (!content) {
-      this.logger?.warn('OpenAI response has no content available');
+      this.logger?.warn('OpenAI structured response has no content available');
       metrics.success = false;
+      return {
+        data: {},
+        rawResponse: '',
+        metrics,
+      };
     }
 
-    // Create the assistant message
-    const assistantMessage: LDMessage = {
-      role: 'assistant',
-      content,
-    };
+    try {
+      const data = JSON.parse(content) as Record<string, unknown>;
 
-    return {
-      message: assistantMessage,
-      metrics,
-    };
+      return {
+        data,
+        rawResponse: content,
+        metrics,
+      };
+    } catch (parseError) {
+      this.logger?.warn('OpenAI structured response contains invalid JSON:', parseError);
+      metrics.success = false;
+      return {
+        data: {},
+        rawResponse: content,
+        metrics,
+      };
+    }
   }
 
   /**