Package com.tnsai.llm.providers

Class TogetherAIClient

java.lang.Object

com.tnsai.llm.providers.AbstractLLMClient

com.tnsai.llm.providers.AbstractOpenAICompatibleClient

com.tnsai.llm.providers.TogetherAIClient

All Implemented Interfaces:

com.tnsai.llm.LLMClient

public class TogetherAIClient
extends AbstractOpenAICompatibleClient

Together.ai LLM client.

Together hosts open models (Llama 3.x, Mixtral, Qwen, DeepSeek, Nemotron, and many more) behind an OpenAI-compatible API at https://api.together.xyz/v1. The wire format matches every other OpenAI-shape provider in this module (GroqClient, OpenRouterClient, NvidiaNIMClient, XAIGrokClient, CerebrasClient), so this client is a thin same-shape addition.

Supported models (at time of writing — the serverless catalogue evolves quickly, check the live list at docs.together.ai/docs/serverless-models):

• meta-llama/Llama-3.3-70B-Instruct-Turbo — Llama 3.3 70B (recommended general-purpose)
• meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo — Llama 3.1 405B (frontier)
• meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo — Llama 3.1 70B
• meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo — Llama 3.1 8B (fast / cheap)
• mistralai/Mixtral-8x7B-Instruct-v0.1 — Mixtral 8x7B
• mistralai/Mistral-7B-Instruct-v0.3 — Mistral 7B
• Qwen/Qwen2.5-72B-Instruct-Turbo — Qwen 2.5 72B
• deepseek-ai/DeepSeek-V3 — DeepSeek V3
• nvidia/Llama-3.1-Nemotron-70B-Instruct-HF — Nemotron-tuned Llama

Function calling is supported on most chat models — verify per model against the live docs if a tool-call payload comes back empty.

Configuration via environment variables:

• TOGETHER_API_KEY — Required.
• TOGETHER_BASE_URL — Optional override, defaults to https://api.together.xyz/v1.

See Also:

• Together.ai Chat Completions API

Constructor Summary

Constructors

Constructor	Description
TogetherAIClient(String model)
TogetherAIClient(String model, float temperature)
TogetherAIClient(String model, float temperature, Float topP, Integer maxTokens)
TogetherAIClient(String model, float temperature, Integer maxTokens)
TogetherAIClient(String baseUrl, String model, float temperature, Float topP, Integer maxTokens, String apiKey)
TogetherAIClient(String baseUrl, String model, float temperature, Integer maxTokens, String apiKey)

Method Summary

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

chat, streamChat

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.LLMClient

chat, chat, chat, chat, chat, getCapabilities, getProviderName, listModels, streamChat, streamChat, streamChatWithHandler, streamChatWithHandler, streamChatWithSpec, streamChatWithSpec

Constructor Details

TogetherAIClient

public TogetherAIClient(String model)

TogetherAIClient

public TogetherAIClient(String model,
 float temperature)

TogetherAIClient

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

TogetherAIClient

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

TogetherAIClient

public TogetherAIClient(String baseUrl,
 String model,
 float temperature,
 Integer maxTokens,
 String apiKey)

TogetherAIClient

public TogetherAIClient(String baseUrl,
 String model,
 float temperature,
 Float topP,
 Integer maxTokens,
 String apiKey)