Together AI LLM

Overview

TogetherLLMService provides access to Together AI’s language models, including Meta’s Llama 3.1 and 3.2 models, through an OpenAI-compatible interface. It inherits from OpenAILLMService and supports streaming responses, function calling, and context management with optimized open-source model hosting.

Together AI LLM API Reference

Pipecat’s API methods for Together AI integration

Example Implementation

Complete example with function calling

Together AI Documentation

Official Together AI API documentation and features

Together AI Platform

Access open-source models and manage API keys

Installation

To use Together AI services, install the required dependencies:

uv add "pipecat-ai[together]"

Prerequisites

Together AI Account Setup

Before using Together AI LLM services, you need:

Together AI Account: Sign up at Together AI
API Key: Generate an API key from your account dashboard
Model Selection: Choose from available open-source models (Llama, Mistral, etc.)

Required Environment Variables

TOGETHER_API_KEY: Your Together AI API key for authentication

Configuration

str

required

Together AI API key for authentication.

str

default:"https://api.together.xyz/v1"

Base URL for Together AI API endpoint.

str

default:"None"

deprecated

Deprecated in v0.0.105. Use settings=TogetherLLMService.Settings(model=...) instead.

TogetherLLMService.Settings

default:"None"

Runtime-configurable settings. See Settings below.

Settings

Runtime-configurable settings passed via the settings constructor argument using TogetherLLMService.Settings(...). These can be updated mid-conversation with LLMUpdateSettingsFrame. See Service Settings for details.

dict[str, Any] | None

default:"None"

Together’s reasoning toggle, for the models that support one, e.g. {"enabled": False}. A reasoning model such as GLM runs a reasoning pass before every answer, which delays the first spoken token. None leaves the choice to the model’s own default.

This service also inherits settings from OpenAILLMService. See OpenAI LLM Settings for the full parameter reference.

Usage

Basic Setup

import os
from pipecat.services.together.llm import TogetherLLMService

llm = TogetherLLMService(
    api_key=os.getenv("TOGETHER_API_KEY"),
    model="zai-org/GLM-5.2",
)

With Custom Settings

from pipecat.services.together.llm import TogetherLLMService

llm = TogetherLLMService(
    api_key=os.getenv("TOGETHER_API_KEY"),
    settings=TogetherLLMService.Settings(
        model="zai-org/GLM-5.2",
        temperature=0.7,
        top_p=0.9,
        max_completion_tokens=1024,
    ),
)

With Reasoning Disabled

For reasoning models like GLM, disable the reasoning pass to reduce latency in real-time voice applications:

from pipecat.services.together.llm import TogetherLLMService

llm = TogetherLLMService(
    api_key=os.getenv("TOGETHER_API_KEY"),
    settings=TogetherLLMService.Settings(
        model="zai-org/GLM-5.2",
        reasoning={"enabled": False},
    ),
)

Notes

Together AI hosts a wide variety of open-source models. Model identifiers use the organization/model-name format.
Together AI fully supports the OpenAI-compatible parameter set inherited from OpenAILLMService.

The InputParams / params= pattern is deprecated as of v0.0.105. Use Settings / settings= instead. See the Service Settings guide for migration details.

Get Started

Pipecat Server

Client SDKs

Pipecat Flows

Pipecat Cloud

CLI

Pipecat Context Hub

Together AI LLM

Overview

Together AI LLM API Reference

Example Implementation

Together AI Documentation

Together AI Platform

Installation

Prerequisites

Together AI Account Setup

Required Environment Variables

Configuration

Settings

Usage

Basic Setup

With Custom Settings

With Reasoning Disabled

Notes

​Overview

Together AI LLM API Reference

Example Implementation

Together AI Documentation

Together AI Platform

​Installation

​Prerequisites

​Together AI Account Setup

​Required Environment Variables

​Configuration

​Settings

​Usage

​Basic Setup

​With Custom Settings

​With Reasoning Disabled

​Notes

Overview

Installation

Prerequisites

Together AI Account Setup

Required Environment Variables

Configuration

Settings

Usage

Basic Setup

With Custom Settings

With Reasoning Disabled

Notes