Package com.tnsai.llm.providers

Class MiniMaxClient

java.lang.Object

com.tnsai.llm.providers.AbstractLLMClient

com.tnsai.llm.providers.MiniMaxClient

All Implemented Interfaces:

JsonCapableLLMClient, com.tnsai.llm.LLMClient

public class MiniMaxClient
extends AbstractLLMClient
implements JsonCapableLLMClient

MiniMax LLM client implementation. Provides access to MiniMax's models via OpenAI-compatible API.

MiniMax is a Chinese AI company offering advanced language models with extensive context windows (up to 1M tokens) and multimodal capabilities.

Supported models:

• MiniMax-M2 - Latest flagship model with 1M context
• MiniMax-M2.1 - Enhanced multilingual capabilities
• MiniMax-Text-01 - Text-optimized model
• abab6.5s-chat - Balanced performance and speed
• abab6.5t-chat - Turbo version for faster responses
• abab5.5s-chat - Efficient model for simpler tasks

Configuration via environment variables:

• MINIMAX_API_KEY - Required API key for authentication
• MINIMAX_BASE_URL - Optional, defaults to https://api.minimax.io/v1
• MINIMAX_GROUP_ID - Optional group ID for some endpoints

See Also:

• MiniMax API Documentation

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	MiniMaxClient.Builder

Constructor Summary

Constructors

Constructor	Description
MiniMaxClient(String model)
MiniMaxClient(String model, float temperature)
MiniMaxClient(String model, float temperature, Float topP, Integer maxTokens)
MiniMaxClient(String model, float temperature, Integer maxTokens)
MiniMaxClient(String baseUrl, String model, float temperature, Float topP, Integer maxTokens, String apiKey, String groupId, boolean reasoningSplit)
MiniMaxClient(String baseUrl, String model, float temperature, Integer maxTokens, String apiKey, String groupId, boolean reasoningSplit)

Method Summary

Modifier and Type	Method	Description
static MiniMaxClient.Builder	builder()	Builder for MiniMaxClient.
com.tnsai.llm.ChatResponse	chat(String message, Optional<String> systemPrompt, Optional<List<Map<String,Object>>> history, Optional<List<Map<String,Object>>> tools)
com.tnsai.llm.ChatResponse	chatWithFormat(String message, Optional<String> systemPrompt, Optional<List<Map<String,Object>>> history, Optional<List<Map<String,Object>>> tools, ResponseFormat format)	Sends a chat message with the specified response format.
static MiniMaxClient	forChina(String model)	Creates a MiniMaxClient configured for China region.
Optional<String>	getGroupId()	Returns the configured group ID.
Stream<String>	streamChat(String message, Optional<String> systemPrompt, Optional<List<Map<String,Object>>> history, Optional<List<Map<String,Object>>> tools)
boolean	supportsExtendedContext()	Returns true if the current model supports extended context (1M tokens).
boolean	supportsFormat(ResponseFormat format)	Checks if this client supports the given response format.
boolean	supportsReasoningSplit()	Returns true if the current model supports reasoning split mode.

Methods inherited from class com.tnsai.llm.providers.AbstractLLMClient

getBaseUrl, getCallTimeoutMs, getMaxTokens, getModel, getTemperature, getTopP

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface com.tnsai.llm.format.JsonCapableLLMClient

chatJson, chatJson, chatWithSchema, chatWithSchema

Methods inherited from interface com.tnsai.llm.LLMClient

chat, chat, chat, chat, chat, getCapabilities, getMaxTokens, getModel, getProviderName, getTemperature, getTopP, listModels, streamChat, streamChat, streamChatWithHandler, streamChatWithHandler, streamChatWithSpec, streamChatWithSpec

Constructor Details

MiniMaxClient

public MiniMaxClient(String model)

MiniMaxClient

public MiniMaxClient(String model,
 float temperature)

MiniMaxClient

public MiniMaxClient(String model,
 float temperature,
 Integer maxTokens)

MiniMaxClient

public MiniMaxClient(String model,
 float temperature,
 Float topP,
 Integer maxTokens)

MiniMaxClient

public MiniMaxClient(String baseUrl,
 String model,
 float temperature,
 Integer maxTokens,
 String apiKey,
 String groupId,
 boolean reasoningSplit)

MiniMaxClient

public MiniMaxClient(String baseUrl,
 String model,
 float temperature,
 Float topP,
 Integer maxTokens,
 String apiKey,
 String groupId,
 boolean reasoningSplit)

Method Details

chat

public com.tnsai.llm.ChatResponse chat(String message,
 Optional<String> systemPrompt,
 Optional<List<Map<String,Object>>> history,
 Optional<List<Map<String,Object>>> tools)

Specified by:

chat in interface com.tnsai.llm.LLMClient

chatWithFormat

public com.tnsai.llm.ChatResponse chatWithFormat(String message,
 Optional<String> systemPrompt,
 Optional<List<Map<String,Object>>> history,
 Optional<List<Map<String,Object>>> tools,
 ResponseFormat format)

Description copied from interface: JsonCapableLLMClient

Sends a chat message with the specified response format.

Specified by:

chatWithFormat in interface JsonCapableLLMClient

Parameters:

message - The user message

systemPrompt - Optional system prompt

history - Optional conversation history

tools - Optional list of available tools

format - The desired response format

Returns:

The LLM response

streamChat

public Stream<String> streamChat(String message,
 Optional<String> systemPrompt,
 Optional<List<Map<String,Object>>> history,
 Optional<List<Map<String,Object>>> tools)

Specified by:

streamChat in interface com.tnsai.llm.LLMClient

supportsFormat

public boolean supportsFormat(ResponseFormat format)

Description copied from interface: JsonCapableLLMClient

Checks if this client supports the given response format.

Specified by:

supportsFormat in interface JsonCapableLLMClient

Parameters:

format - The format to check

Returns:

true if the format is supported

supportsExtendedContext

public boolean supportsExtendedContext()

Returns true if the current model supports extended context (1M tokens).

supportsReasoningSplit

public boolean supportsReasoningSplit()

Returns true if the current model supports reasoning split mode.

getGroupId

public Optional<String> getGroupId()

Returns the configured group ID.

forChina

public static MiniMaxClient forChina(String model)

Creates a MiniMaxClient configured for China region.

builder

public static MiniMaxClient.Builder builder()

Builder for MiniMaxClient.