diff --git a/backend/src/index.ts b/backend/src/index.ts
index 050f706..95f111f 100644
--- a/backend/src/index.ts
+++ b/backend/src/index.ts
@@ -447,10 +447,11 @@ CRITICAL RULES:
     const baseUrl = providerConfig.baseUrl || settings?.aiBaseUrl;
     
     const aiProvider = createAIProvider({
-      provider: provider as 'openai' | 'anthropic' | 'ollama' | 'lmstudio' | 'groq',
+      provider,
       apiKey: apiKey,
       model: model || undefined,
-      baseUrl: (provider === 'ollama' || provider === 'lmstudio') ? baseUrl : undefined,
+      baseUrl: (provider === 'ollama' || provider === 'lmstudio' || provider === 'custom') ? baseUrl : undefined,
+      providerSettings: settings?.providerSettings,
     });
     
     console.log(`[Journal Generate] AI Provider created: ${aiProvider.provider}`);
@@ -657,7 +658,7 @@ app.post('/api/v1/ai/test', async (c) => {
   const userId = await getUserId(c);
   if (!userId) return c.json({ data: null, error: { code: 'UNAUTHORIZED', message: 'Invalid API key' } }, 401);
   
-  const { provider, apiKey, model, baseUrl } = await c.req.json();
+  const { provider, apiKey, model, baseUrl, headers, parameters } = await c.req.json();
   
   console.log(`[AI Test] Provider: ${provider}, Model: ${model || 'default'}, BaseURL: ${baseUrl || 'default'}`);
   console.log(`[AI Test] API Key set: ${!!apiKey}, Length: ${apiKey?.length || 0}`);
@@ -666,12 +667,18 @@ app.post('/api/v1/ai/test', async (c) => {
     return c.json({ data: null, error: { code: 'VALIDATION_ERROR', message: 'provider is required' } }, 400);
   }
   
+  let providerSettings: string | undefined;
+  if (headers || parameters) {
+    providerSettings = JSON.stringify({ headers, parameters });
+  }
+  
   try {
     const aiProvider = createAIProvider({
       provider,
       apiKey: apiKey || '',
       model: model || undefined,
       baseUrl: baseUrl || undefined,
+      providerSettings,
     });
     
     console.log(`[AI Test] Creating provider: ${aiProvider.provider}`);
diff --git a/backend/src/routes/journal.ts b/backend/src/routes/journal.ts
index 87ddac2..bc9cc0b 100644
--- a/backend/src/routes/journal.ts
+++ b/backend/src/routes/journal.ts
@@ -28,10 +28,11 @@ journalRoutes.post('/generate/:date', async (c) => {
   }
 
   const provider = createAIProvider({
-    provider: settings.aiProvider as AIProvider['provider'],
+    provider: settings.aiProvider,
     apiKey: settings.aiApiKey,
     model: settings.aiModel,
     baseUrl: settings.aiBaseUrl,
+    providerSettings: settings.providerSettings,
   });
 
   const eventsText = events.map(event => {
diff --git a/backend/src/routes/settings.ts b/backend/src/routes/settings.ts
index bfbd8bb..d60f87d 100644
--- a/backend/src/routes/settings.ts
+++ b/backend/src/routes/settings.ts
@@ -26,7 +26,7 @@ settingsRoutes.put('/', async (c) => {
   const prisma = c.get('prisma');
 
   const body = await c.req.json();
-  const { aiProvider, aiApiKey, aiModel, aiBaseUrl, journalPrompt, language } = body;
+  const { aiProvider, aiApiKey, aiModel, aiBaseUrl, journalPrompt, language, providerSettings } = body;
 
   const data: Record<string, unknown> = {};
   if (aiProvider !== undefined) data.aiProvider = aiProvider;
@@ -35,6 +35,7 @@ settingsRoutes.put('/', async (c) => {
   if (aiBaseUrl !== undefined) data.aiBaseUrl = aiBaseUrl;
   if (journalPrompt !== undefined) data.journalPrompt = journalPrompt;
   if (language !== undefined) data.language = language;
+  if (providerSettings !== undefined) data.providerSettings = typeof providerSettings === 'string' ? providerSettings : JSON.stringify(providerSettings);
 
   const settings = await prisma.settings.upsert({
     where: { userId },
@@ -70,12 +71,17 @@ settingsRoutes.post('/validate-key', async (c) => {
 
 settingsRoutes.post('/test', async (c) => {
   const body = await c.req.json();
-  const { provider, apiKey, model, baseUrl } = body;
+  const { provider, apiKey, model, baseUrl, headers, parameters } = body;
 
   if (!provider) {
     return c.json({ data: null, error: { code: 'VALIDATION_ERROR', message: 'provider is required' } }, 400);
   }
 
+  let providerSettings: string | undefined;
+  if (headers || parameters) {
+    providerSettings = JSON.stringify({ headers, parameters });
+  }
+
   const { createAIProvider } = await import('../services/ai/provider');
   
   try {
@@ -84,11 +90,12 @@ settingsRoutes.post('/test', async (c) => {
       apiKey: apiKey || '',
       model: model || undefined,
       baseUrl: baseUrl || undefined,
+      providerSettings,
     });
     
     const result = await aiProvider.generate('Say "OK" if you can read this.', 'You are a test assistant. Respond with just "OK".');
     
-    if (result.toLowerCase().includes('ok')) {
+    if (result.content.toLowerCase().includes('ok')) {
       return c.json({ data: { valid: true, message: 'Connection successful!' }, error: null });
     } else {
       return c.json({ data: { valid: false }, error: { code: 'TEST_FAILED', message: 'Model responded but with unexpected output' } });
diff --git a/backend/src/services/ai/anthropic.ts b/backend/src/services/ai/anthropic.ts
index 85a8df6..69555d8 100644
--- a/backend/src/services/ai/anthropic.ts
+++ b/backend/src/services/ai/anthropic.ts
@@ -1,15 +1,20 @@
 import type { AIProvider, AIProviderConfig, AIProviderResult } from './provider';
+import { ProviderSettings } from './openai';
 
 export class AnthropicProvider implements AIProvider {
   provider = 'anthropic' as const;
   private apiKey: string;
   private model: string;
   private baseUrl: string;
+  private customHeaders?: Record<string, string>;
+  private customParameters?: Record<string, unknown>;
 
-  constructor(config: AIProviderConfig) {
+  constructor(config: AIProviderConfig, settings?: ProviderSettings) {
     this.apiKey = config.apiKey;
     this.model = config.model || 'claude-3-sonnet-20240229';
     this.baseUrl = config.baseUrl || 'https://api.anthropic.com/v1';
+    this.customHeaders = settings?.headers;
+    this.customParameters = settings?.parameters;
   }
 
   async generate(prompt: string, systemPrompt?: string, options?: { jsonMode?: boolean }): Promise<AIProviderResult> {
@@ -20,20 +25,24 @@ export class AnthropicProvider implements AIProvider {
       messages: [
         { role: 'user', content: prompt }
       ],
+      ...this.customParameters,
     };
 
     if (options?.jsonMode) {
       requestBody.output = { format: { type: 'json_object' } };
     }
 
+    const headers: Record<string, string> = {
+      'Content-Type': 'application/json',
+      'x-api-key': this.apiKey,
+      'anthropic-version': '2023-06-01',
+      'anthropic-dangerous-direct-browser-access': 'true',
+      ...this.customHeaders,
+    };
+
     const response = await fetch(`${this.baseUrl}/messages`, {
       method: 'POST',
-      headers: {
-        'Content-Type': 'application/json',
-        'x-api-key': this.apiKey,
-        'anthropic-version': '2023-06-01',
-        'anthropic-dangerous-direct-browser-access': 'true',
-      },
+      headers,
       body: JSON.stringify(requestBody),
     });
 
@@ -66,18 +75,21 @@ export class AnthropicProvider implements AIProvider {
 
   async validate(): Promise<boolean> {
     try {
+      const headers: Record<string, string> = {
+        'Content-Type': 'application/json',
+        'x-api-key': this.apiKey,
+        'anthropic-version': '2023-06-01',
+        'anthropic-dangerous-direct-browser-access': 'true',
+        ...this.customHeaders,
+      };
       const response = await fetch(`${this.baseUrl}/messages`, {
         method: 'POST',
-        headers: {
-          'Content-Type': 'application/json',
-          'x-api-key': this.apiKey,
-          'anthropic-version': '2023-06-01',
-          'anthropic-dangerous-direct-browser-access': 'true',
-        },
+        headers,
         body: JSON.stringify({
           model: this.model,
           max_tokens: 1,
           messages: [{ role: 'user', content: 'hi' }],
+          ...this.customParameters,
         }),
       });
       return response.ok;
diff --git a/backend/src/services/ai/custom.ts b/backend/src/services/ai/custom.ts
new file mode 100644
index 0000000..8f7dd41
--- /dev/null
+++ b/backend/src/services/ai/custom.ts
@@ -0,0 +1,94 @@
+import type { AIProvider, AIProviderConfig, AIProviderResult } from './provider';
+import { ProviderSettings } from './openai';
+
+export class CustomProvider implements AIProvider {
+  provider = 'custom' as const;
+  private apiKey: string;
+  private model: string;
+  private baseUrl: string;
+  private customHeaders?: Record<string, string>;
+  private customParameters?: Record<string, unknown>;
+
+  constructor(config: AIProviderConfig, settings?: ProviderSettings) {
+    this.apiKey = config.apiKey || '';
+    this.model = config.model || 'unknown';
+    this.baseUrl = config.baseUrl || '';
+    this.customHeaders = settings?.headers;
+    this.customParameters = settings?.parameters;
+  }
+
+  async generate(prompt: string, systemPrompt?: string, options?: { jsonMode?: boolean }): Promise<AIProviderResult> {
+    const messages: Array<{ role: string; content: string }> = [];
+    
+    if (systemPrompt) {
+      messages.push({ role: 'system', content: systemPrompt });
+    }
+    
+    messages.push({ role: 'user', content: prompt });
+
+    const requestBody: Record<string, unknown> = {
+      model: this.model,
+      messages,
+      temperature: 0.7,
+      max_tokens: 2000,
+      ...this.customParameters,
+    };
+
+    if (options?.jsonMode) {
+      requestBody.response_format = { type: 'json_object' };
+    }
+
+    const headers: Record<string, string> = {
+      'Content-Type': 'application/json',
+      ...(this.apiKey ? { 'Authorization': `Bearer ${this.apiKey}` } : {}),
+      ...this.customHeaders,
+    };
+
+    const response = await fetch(`${this.baseUrl}/chat/completions`, {
+      method: 'POST',
+      headers,
+      body: JSON.stringify(requestBody),
+    });
+
+    const responseData = await response.json();
+
+    if (!response.ok) {
+      throw new Error(`Custom API error: ${response.status} ${JSON.stringify(responseData)}`);
+    }
+
+    let content = responseData.choices?.[0]?.message?.content || '';
+    let title: string | undefined;
+    
+    if (options?.jsonMode) {
+      try {
+        const parsed = JSON.parse(content);
+        title = parsed.title;
+        content = parsed.content || content;
+      } catch {
+        // If JSON parsing fails, use content as-is
+      }
+    }
+    
+    return {
+      content,
+      title,
+      request: requestBody,
+      response: responseData,
+    };
+  }
+
+  async validate(): Promise<boolean> {
+    try {
+      if (!this.baseUrl) return false;
+      const response = await fetch(`${this.baseUrl}/models`, {
+        headers: {
+          ...(this.apiKey ? { 'Authorization': `Bearer ${this.apiKey}` } : {}),
+          ...this.customHeaders,
+        },
+      });
+      return response.ok;
+    } catch {
+      return false;
+    }
+  }
+}
diff --git a/backend/src/services/ai/groq.ts b/backend/src/services/ai/groq.ts
index 9b7a38a..933d066 100644
--- a/backend/src/services/ai/groq.ts
+++ b/backend/src/services/ai/groq.ts
@@ -1,15 +1,20 @@
 import type { AIProvider, AIProviderConfig, AIProviderResult } from './provider';
+import { ProviderSettings } from './openai';
 
 export class GroqProvider implements AIProvider {
   provider = 'groq' as const;
   private apiKey: string;
   private model: string;
   private baseUrl: string;
+  private customHeaders?: Record<string, string>;
+  private customParameters?: Record<string, unknown>;
 
-  constructor(config: AIProviderConfig) {
+  constructor(config: AIProviderConfig, settings?: ProviderSettings) {
     this.apiKey = config.apiKey;
     this.model = config.model || 'llama-3.3-70b-versatile';
     this.baseUrl = config.baseUrl || 'https://api.groq.com/openai/v1';
+    this.customHeaders = settings?.headers;
+    this.customParameters = settings?.parameters;
   }
 
   async generate(prompt: string, systemPrompt?: string, options?: { jsonMode?: boolean }): Promise<AIProviderResult> {
@@ -26,18 +31,22 @@ export class GroqProvider implements AIProvider {
       messages,
       temperature: 0.7,
       max_tokens: 2000,
+      ...this.customParameters,
     };
 
     if (options?.jsonMode) {
       requestBody.response_format = { type: 'json_object' };
     }
 
+    const headers: Record<string, string> = {
+      'Content-Type': 'application/json',
+      'Authorization': `Bearer ${this.apiKey}`,
+      ...this.customHeaders,
+    };
+
     const response = await fetch(`${this.baseUrl}/chat/completions`, {
       method: 'POST',
-      headers: {
-        'Content-Type': 'application/json',
-        'Authorization': `Bearer ${this.apiKey}`,
-      },
+      headers,
       body: JSON.stringify(requestBody),
     });
 
@@ -71,16 +80,19 @@ export class GroqProvider implements AIProvider {
 
   async validate(): Promise<boolean> {
     try {
+      const headers: Record<string, string> = {
+        'Content-Type': 'application/json',
+        'Authorization': `Bearer ${this.apiKey}`,
+        ...this.customHeaders,
+      };
       const response = await fetch(`${this.baseUrl}/chat/completions`, {
         method: 'POST',
-        headers: {
-          'Content-Type': 'application/json',
-          'Authorization': `Bearer ${this.apiKey}`,
-        },
+        headers,
         body: JSON.stringify({
           model: this.model,
           messages: [{ role: 'user', content: 'test' }],
           max_tokens: 5,
+          ...this.customParameters,
         }),
       });
       return response.ok || response.status === 400;
diff --git a/backend/src/services/ai/lmstudio.ts b/backend/src/services/ai/lmstudio.ts
index fa143fa..f345f18 100644
--- a/backend/src/services/ai/lmstudio.ts
+++ b/backend/src/services/ai/lmstudio.ts
@@ -1,13 +1,18 @@
 import type { AIProvider, AIProviderConfig, AIProviderResult } from './provider';
+import { ProviderSettings } from './openai';
 
 export class LMStudioProvider implements AIProvider {
   provider = 'lmstudio' as const;
   private baseUrl: string;
   private model: string;
+  private customHeaders?: Record<string, string>;
+  private customParameters?: Record<string, unknown>;
 
-  constructor(config: AIProviderConfig) {
+  constructor(config: AIProviderConfig, settings?: ProviderSettings) {
     this.baseUrl = config.baseUrl || 'http://localhost:1234/v1';
     this.model = config.model || 'local-model';
+    this.customHeaders = settings?.headers;
+    this.customParameters = settings?.parameters;
   }
 
   async generate(prompt: string, systemPrompt?: string, options?: { jsonMode?: boolean }): Promise<AIProviderResult> {
@@ -19,18 +24,26 @@ export class LMStudioProvider implements AIProvider {
     
     messages.push({ role: 'user', content: prompt });
 
-    const requestBody = {
+    const requestBody: Record<string, unknown> = {
       model: this.model,
       messages,
       temperature: 0.7,
       max_tokens: 2000,
+      ...this.customParameters,
+    };
+
+    if (options?.jsonMode) {
+      requestBody.response_format = { type: 'json_object' };
+    }
+
+    const headers: Record<string, string> = {
+      'Content-Type': 'application/json',
+      ...this.customHeaders,
     };
 
     const response = await fetch(`${this.baseUrl}/chat/completions`, {
       method: 'POST',
-      headers: {
-        'Content-Type': 'application/json',
-      },
+      headers,
       body: JSON.stringify(requestBody),
     });
 
@@ -63,7 +76,9 @@ export class LMStudioProvider implements AIProvider {
 
   async validate(): Promise<boolean> {
     try {
-      const response = await fetch(`${this.baseUrl}/models`);
+      const response = await fetch(`${this.baseUrl}/models`, {
+        headers: this.customHeaders,
+      });
       return response.ok;
     } catch {
       return false;
diff --git a/backend/src/services/ai/ollama.ts b/backend/src/services/ai/ollama.ts
index 58817db..ebf60cb 100644
--- a/backend/src/services/ai/ollama.ts
+++ b/backend/src/services/ai/ollama.ts
@@ -1,30 +1,39 @@
 import type { AIProvider, AIProviderConfig, AIProviderResult } from './provider';
+import { ProviderSettings } from './openai';
 
 export class OllamaProvider implements AIProvider {
   provider = 'ollama' as const;
   private baseUrl: string;
   private model: string;
+  private customHeaders?: Record<string, string>;
+  private customParameters?: Record<string, unknown>;
 
-  constructor(config: AIProviderConfig) {
+  constructor(config: AIProviderConfig, settings?: ProviderSettings) {
     this.baseUrl = config.baseUrl || 'http://localhost:11434';
     this.model = config.model || 'llama3.2';
+    this.customHeaders = settings?.headers;
+    this.customParameters = settings?.parameters;
   }
 
   async generate(prompt: string, systemPrompt?: string, options?: { jsonMode?: boolean }): Promise<AIProviderResult> {
-    const requestBody = {
+    const requestBody: Record<string, unknown> = {
       model: this.model,
       stream: false,
       messages: [
         ...(systemPrompt ? [{ role: 'system', content: systemPrompt }] : []),
         { role: 'user', content: prompt },
       ],
+      ...this.customParameters,
+    };
+
+    const headers: Record<string, string> = {
+      'Content-Type': 'application/json',
+      ...this.customHeaders,
     };
 
     const response = await fetch(`${this.baseUrl}/api/chat`, {
       method: 'POST',
-      headers: {
-        'Content-Type': 'application/json',
-      },
+      headers,
       body: JSON.stringify(requestBody),
     });
 
@@ -57,7 +66,9 @@ export class OllamaProvider implements AIProvider {
 
   async validate(): Promise<boolean> {
     try {
-      const response = await fetch(`${this.baseUrl}/api/tags`);
+      const response = await fetch(`${this.baseUrl}/api/tags`, {
+        headers: this.customHeaders,
+      });
       return response.ok;
     } catch {
       return false;
diff --git a/backend/src/services/ai/openai.ts b/backend/src/services/ai/openai.ts
index 1c63a64..7db3827 100644
--- a/backend/src/services/ai/openai.ts
+++ b/backend/src/services/ai/openai.ts
@@ -1,15 +1,24 @@
 import type { AIProvider, AIProviderConfig, AIProviderResult } from './provider';
 
+export interface ProviderSettings {
+  headers?: Record<string, string>;
+  parameters?: Record<string, unknown>;
+}
+
 export class OpenAIProvider implements AIProvider {
   provider = 'openai' as const;
   private apiKey: string;
   private model: string;
   private baseUrl: string;
+  private customHeaders?: Record<string, string>;
+  private customParameters?: Record<string, unknown>;
 
-  constructor(config: AIProviderConfig) {
+  constructor(config: AIProviderConfig, settings?: ProviderSettings) {
     this.apiKey = config.apiKey;
     this.model = config.model || 'gpt-4';
     this.baseUrl = config.baseUrl || 'https://api.openai.com/v1';
+    this.customHeaders = settings?.headers;
+    this.customParameters = settings?.parameters;
   }
 
   async generate(prompt: string, systemPrompt?: string, options?: { jsonMode?: boolean }): Promise<AIProviderResult> {
@@ -26,18 +35,22 @@ export class OpenAIProvider implements AIProvider {
       messages,
       temperature: 0.7,
       max_tokens: 2000,
+      ...this.customParameters,
     };
 
     if (options?.jsonMode) {
       requestBody.response_format = { type: 'json_object' };
     }
 
+    const headers: Record<string, string> = {
+      'Content-Type': 'application/json',
+      'Authorization': `Bearer ${this.apiKey}`,
+      ...this.customHeaders,
+    };
+
     const response = await fetch(`${this.baseUrl}/chat/completions`, {
       method: 'POST',
-      headers: {
-        'Content-Type': 'application/json',
-        'Authorization': `Bearer ${this.apiKey}`,
-      },
+      headers,
       body: JSON.stringify(requestBody),
     });
 
@@ -70,11 +83,11 @@ export class OpenAIProvider implements AIProvider {
 
   async validate(): Promise<boolean> {
     try {
-      const response = await fetch(`${this.baseUrl}/models`, {
-        headers: {
-          'Authorization': `Bearer ${this.apiKey}`,
-        },
-      });
+      const headers: Record<string, string> = {
+        'Authorization': `Bearer ${this.apiKey}`,
+        ...this.customHeaders,
+      };
+      const response = await fetch(`${this.baseUrl}/models`, { headers });
       return response.ok;
     } catch {
       return false;
diff --git a/backend/src/services/ai/provider.ts b/backend/src/services/ai/provider.ts
index bbb2724..b7e2402 100644
--- a/backend/src/services/ai/provider.ts
+++ b/backend/src/services/ai/provider.ts
@@ -6,16 +6,33 @@ export interface AIProviderResult {
 }
 
 export interface AIProvider {
-  provider: 'openai' | 'anthropic' | 'ollama' | 'lmstudio' | 'groq';
+  provider: string;
   generate(prompt: string, systemPrompt?: string, options?: { jsonMode?: boolean }): Promise<AIProviderResult>;
   validate?(): Promise<boolean>;
 }
 
 export interface AIProviderConfig {
-  provider: 'openai' | 'anthropic' | 'ollama' | 'lmstudio' | 'groq';
-  apiKey: string;
+  provider: string;
+  apiKey?: string;
   model?: string;
   baseUrl?: string;
+  providerSettings?: string;
+}
+
+function parseProviderSettings(settingsJson?: string): {
+  headers?: Record<string, string>;
+  parameters?: Record<string, unknown>;
+} {
+  if (!settingsJson) return {};
+  try {
+    const parsed = JSON.parse(settingsJson);
+    return {
+      headers: parsed.headers,
+      parameters: parsed.parameters,
+    };
+  } catch {
+    return {};
+  }
 }
 
 import { OpenAIProvider } from './openai';
@@ -23,19 +40,24 @@ import { AnthropicProvider } from './anthropic';
 import { OllamaProvider } from './ollama';
 import { LMStudioProvider } from './lmstudio';
 import { GroqProvider } from './groq';
+import { CustomProvider } from './custom';
 
 export function createAIProvider(config: AIProviderConfig): AIProvider {
+  const settings = parseProviderSettings(config.providerSettings);
+  
   switch (config.provider) {
     case 'openai':
-      return new OpenAIProvider(config);
+      return new OpenAIProvider(config, settings);
     case 'anthropic':
-      return new AnthropicProvider(config);
+      return new AnthropicProvider(config, settings);
     case 'ollama':
-      return new OllamaProvider(config);
+      return new OllamaProvider(config, settings);
     case 'lmstudio':
-      return new LMStudioProvider(config);
+      return new LMStudioProvider(config, settings);
     case 'groq':
-      return new GroqProvider(config);
+      return new GroqProvider(config, settings);
+    case 'custom':
+      return new CustomProvider(config, settings);
     default:
       throw new Error(`Unknown AI provider: ${config.provider}`);
   }