diff --git a/README.md b/README.md
index 9c11a47d7..2a823f566 100644
--- a/README.md
+++ b/README.md
@@ -16,7 +16,7 @@ Want to know more about its architecture and how it works? You can read it [here
 
 ## ✨ Features
 
-🤖 **Support for all major AI providers** - Use local LLMs through Ollama or connect to OpenAI, Anthropic Claude, Google Gemini, Groq, and more. Mix and match models based on your needs.
+🤖 **Support for all major AI providers** - Use local LLMs through Ollama or connect to OpenAI, Anthropic Claude, Google Gemini, Groq, MiniMax, and more. Mix and match models based on your needs.
 
 ⚡ **Smart search modes** - Choose Speed Mode when you need quick answers, Balanced Mode for everyday searches, or Quality Mode for deep research.
 
diff --git a/src/lib/models/providers/index.ts b/src/lib/models/providers/index.ts
index cabfaa96f..007eaa221 100644
--- a/src/lib/models/providers/index.ts
+++ b/src/lib/models/providers/index.ts
@@ -8,6 +8,7 @@ import GroqProvider from './groq';
 import LemonadeProvider from './lemonade';
 import AnthropicProvider from './anthropic';
 import LMStudioProvider from './lmstudio';
+import MiniMaxProvider from './minimax';
 
 export const providers: Record<string, ProviderConstructor<any>> = {
   openai: OpenAIProvider,
@@ -18,6 +19,7 @@ export const providers: Record<string, ProviderConstructor<any>> = {
   lemonade: LemonadeProvider,
   anthropic: AnthropicProvider,
   lmstudio: LMStudioProvider,
+  minimax: MiniMaxProvider,
 };
 
 export const getModelProvidersUIConfigSection =
diff --git a/src/lib/models/providers/minimax/index.ts b/src/lib/models/providers/minimax/index.ts
new file mode 100644
index 000000000..3e3be5ce2
--- /dev/null
+++ b/src/lib/models/providers/minimax/index.ts
@@ -0,0 +1,111 @@
+import { UIConfigField } from '@/lib/config/types';
+import { getConfiguredModelProviderById } from '@/lib/config/serverRegistry';
+import { Model, ModelList, ProviderMetadata } from '../../types';
+import BaseEmbedding from '../../base/embedding';
+import BaseModelProvider from '../../base/provider';
+import BaseLLM from '../../base/llm';
+import MiniMaxLLM from './miniMaxLLM';
+
+interface MiniMaxConfig {
+  apiKey: string;
+  baseURL?: string;
+}
+
+const DEFAULT_CHAT_MODELS: Model[] = [
+  { key: 'MiniMax-M2.7', name: 'MiniMax M2.7' },
+  { key: 'MiniMax-M2.5', name: 'MiniMax M2.5' },
+  { key: 'MiniMax-M2.5-highspeed', name: 'MiniMax M2.5 High Speed' },
+];
+
+const providerConfigFields: UIConfigField[] = [
+  {
+    type: 'password',
+    name: 'API Key',
+    key: 'apiKey',
+    description: 'Your MiniMax API key',
+    required: true,
+    placeholder: 'MiniMax API Key',
+    env: 'MINIMAX_API_KEY',
+    scope: 'server',
+  },
+  {
+    type: 'string',
+    name: 'Base URL',
+    key: 'baseURL',
+    description: 'MiniMax API base URL (default: https://api.minimax.io/v1)',
+    required: false,
+    placeholder: 'https://api.minimax.io/v1',
+    env: 'MINIMAX_BASE_URL',
+    scope: 'server',
+  },
+];
+
+class MiniMaxProvider extends BaseModelProvider<MiniMaxConfig> {
+  constructor(id: string, name: string, config: MiniMaxConfig) {
+    super(id, name, config);
+  }
+
+  async getDefaultModels(): Promise<ModelList> {
+    return {
+      embedding: [],
+      chat: DEFAULT_CHAT_MODELS,
+    };
+  }
+
+  async getModelList(): Promise<ModelList> {
+    const defaultModels = await this.getDefaultModels();
+    const configProvider = getConfiguredModelProviderById(this.id)!;
+
+    return {
+      embedding: [],
+      chat: [...defaultModels.chat, ...configProvider.chatModels],
+    };
+  }
+
+  async loadChatModel(key: string): Promise<BaseLLM<any>> {
+    const modelList = await this.getModelList();
+
+    const exists = modelList.chat.find((m) => m.key === key);
+
+    if (!exists) {
+      throw new Error(
+        'Error Loading MiniMax Chat Model. Invalid Model Selected',
+      );
+    }
+
+    return new MiniMaxLLM({
+      apiKey: this.config.apiKey,
+      model: key,
+      baseURL: this.config.baseURL || 'https://api.minimax.io/v1',
+    });
+  }
+
+  async loadEmbeddingModel(key: string): Promise<BaseEmbedding<any>> {
+    throw new Error('MiniMax provider does not support embedding models.');
+  }
+
+  static parseAndValidate(raw: any): MiniMaxConfig {
+    if (!raw || typeof raw !== 'object')
+      throw new Error('Invalid config provided. Expected object');
+    if (!raw.apiKey)
+      throw new Error('Invalid config provided. API key must be provided');
+
+    return {
+      apiKey: String(raw.apiKey),
+      ...(raw.baseURL && { baseURL: String(raw.baseURL) }),
+    };
+  }
+
+  static getProviderConfigFields(): UIConfigField[] {
+    return providerConfigFields;
+  }
+
+  static getProviderMetadata(): ProviderMetadata {
+    return {
+      key: 'minimax',
+      name: 'MiniMax',
+    };
+  }
+}
+
+export default MiniMaxProvider;
diff --git a/src/lib/models/providers/minimax/miniMaxLLM.ts b/src/lib/models/providers/minimax/miniMaxLLM.ts
new file mode 100644
index 000000000..094cf280e
--- /dev/null
+++ b/src/lib/models/providers/minimax/miniMaxLLM.ts
@@ -0,0 +1,131 @@
+import OpenAILLM from '../openai/openaiLLM';
+import {
+  GenerateObjectInput,
+  GenerateOptions,
+  GenerateTextInput,
+  GenerateTextOutput,
+  StreamTextOutput,
+} from '../../types';
+import z from 'zod';
+import { parse } from 'partial-json';
+import { repairJson } from '@toolsycc/json-repair';
+
+class MiniMaxLLM extends OpenAILLM {
+  async generateText(input: GenerateTextInput): Promise<GenerateTextOutput> {
+    const clampedInput = {
+      ...input,
+      options: this.clampTemperature(input.options),
+    };
+    return super.generateText(clampedInput);
+  }
+
+  async *streamText(
+    input: GenerateTextInput,
+  ): AsyncGenerator<StreamTextOutput> {
+    const clampedInput = {
+      ...input,
+      options: this.clampTemperature(input.options),
+    };
+    yield* super.streamText(clampedInput);
+  }
+
+  async generateObject<T>(input: GenerateObjectInput): Promise<T> {
+    const jsonSchema = z.toJSONSchema(input.schema);
+    const jsonPrompt = `You must respond with valid JSON only, no other text. The JSON must conform to this schema:\n${JSON.stringify(jsonSchema, null, 2)}`;
+
+    const systemMessage = { role: 'system' as const, content: jsonPrompt };
+    const messages = [systemMessage, ...input.messages];
+
+    const response = await this.openAIClient.chat.completions.create({
+      model: this.config.model,
+      messages: this.convertToOpenAIMessages(messages),
+      temperature:
+        this.clampTemperature(input.options)?.temperature ??
+        this.clampTemperature(this.config.options)?.temperature ??
+        1.0,
+      top_p: input.options?.topP ?? this.config.options?.topP,
+      max_completion_tokens:
+        input.options?.maxTokens ?? this.config.options?.maxTokens,
+      stop: input.options?.stopSequences ?? this.config.options?.stopSequences,
+      frequency_penalty:
+        input.options?.frequencyPenalty ??
+        this.config.options?.frequencyPenalty,
+      presence_penalty:
+        input.options?.presencePenalty ?? this.config.options?.presencePenalty,
+    });
+
+    if (response.choices && response.choices.length > 0) {
+      try {
+        return input.schema.parse(
+          JSON.parse(
+            repairJson(response.choices[0].message.content!, {
+              extractJson: true,
+            }) as string,
+          ),
+        ) as T;
+      } catch (err) {
+        throw new Error(`Error parsing response from MiniMax: ${err}`);
+      }
+    }
+
+    throw new Error('No response from MiniMax');
+  }
+
+  async *streamObject<T>(input: GenerateObjectInput): AsyncGenerator<T> {
+    const jsonSchema = z.toJSONSchema(input.schema);
+    const jsonPrompt = `You must respond with valid JSON only, no other text. The JSON must conform to this schema:\n${JSON.stringify(jsonSchema, null, 2)}`;
+
+    const systemMessage = { role: 'system' as const, content: jsonPrompt };
+    const messages = [systemMessage, ...input.messages];
+
+    let receivedObj = '';
+
+    const stream = await this.openAIClient.chat.completions.create({
+      model: this.config.model,
+      messages: this.convertToOpenAIMessages(messages),
+      temperature:
+        this.clampTemperature(input.options)?.temperature ??
+        this.clampTemperature(this.config.options)?.temperature ??
+        1.0,
+      top_p: input.options?.topP ?? this.config.options?.topP,
+      max_completion_tokens:
+        input.options?.maxTokens ?? this.config.options?.maxTokens,
+      stop: input.options?.stopSequences ?? this.config.options?.stopSequences,
+      frequency_penalty:
+        input.options?.frequencyPenalty ??
+        this.config.options?.frequencyPenalty,
+      presence_penalty:
+        input.options?.presencePenalty ?? this.config.options?.presencePenalty,
+      stream: true,
+    });
+
+    for await (const chunk of stream) {
+      if (chunk.choices && chunk.choices.length > 0) {
+        const content = chunk.choices[0].delta.content || '';
+        receivedObj += content;
+
+        try {
+          yield parse(receivedObj) as T;
+        } catch {
+          yield {} as T;
+        }
+      }
+    }
+  }
+
+  private clampTemperature(
+    options?: GenerateOptions,
+  ): GenerateOptions | undefined {
+    if (!options) return options;
+    if (
+      options.temperature !== undefined &&
+      options.temperature !== null &&
+      options.temperature <= 0
+    ) {
+      return { ...options, temperature: 0.01 };
+    }
+    return options;
+  }
+}
+
+export default MiniMaxLLM;