Together AI

OverviewCopy Anchor Link

Together AI serves open models through an OpenAI-compatible API.

• TogetherLLMService: an OpenAILLMService subclass with Together AI's base URL and default model.

InstallationCopy Anchor Link

bun add @pipedog/together

It depends on @pipedog/openai, which is installed with it.

import { TogetherLLMService } from "@pipedog/together/llm";

PrerequisitesCopy Anchor Link

• A Together AI account and an API key from Together AI.
• Pass the key as apiKey. It is required, and the service never falls back to OPENAI_API_KEY. The examples read it from TOGETHER_API_KEY.

TogetherLLMServiceCopy Anchor Link

ConfigurationCopy Anchor Link

The other options (organization, project, defaultHeaders, serviceTier, retryOnTimeout, retryTimeoutSecs, function calling) are OpenAILLMService's. See OpenAI.

SettingsCopy Anchor Link

Runtime-updatable settings, passed as settings: new TogetherLLMService.Settings({...}) (TogetherLLMSettings). They are OpenAI's settings, with these defaults:

Every other setting keeps OpenAI's default. Unset sampling settings are left out of the request, so the provider's own defaults apply. extra carries provider-specific request fields.

UsageCopy Anchor Link

import { LLMUpdateSettingsFrame } from "@pipedog/core/frames/frames";
import { TogetherLLMService } from "@pipedog/together/llm";

const llm = new TogetherLLMService({
  apiKey: process.env.TOGETHER_API_KEY ?? "",
  settings: new TogetherLLMService.Settings({
    model: "zai-org/GLM-5.2",
    systemInstruction: "You are a helpful assistant in a voice conversation.",
    temperature: 0.7,
  }),
});

Turn off a reasoning model's thinking pass, which otherwise delays the first spoken token:

const noThinking = new TogetherLLMService({
  apiKey: process.env.TOGETHER_API_KEY ?? "",
  settings: new TogetherLLMService.Settings({ reasoning: { enabled: false } }),
});

Models that ignore the toggle, such as zai-org/GLM-5.3, still take a reasoning effort:

const lowEffort = new TogetherLLMService({
  apiKey: process.env.TOGETHER_API_KEY ?? "",
  settings: new TogetherLLMService.Settings({
    model: "zai-org/GLM-5.3",
    reasoningEffort: "low",
  }),
});

Change settings mid-call with an LLMUpdateSettingsFrame. The next completion uses them:

// Queue it on the worker, or push it from a processor upstream of the service.
const update = new LLMUpdateSettingsFrame({
  delta: new TogetherLLMService.Settings({ temperature: 0.2, maxTokens: 300 }),
});

NotesCopy Anchor Link

• Runs a completion for each LLMContextFrame, between an LLMFullResponseStartFrame and an LLMFullResponseEndFrame, and streams the reply as LLMTextFrames, as OpenAILLMService does. Function calls, token usage metrics and runInference work the same way.
• "developer" messages are sent as "user" messages, since the API doesn't support that role (supportsDeveloperRole is false).
• The same package has Together's speech-to-text and text-to-speech services.

Runtime notesCopy Anchor Link

Generated from pipecat.runtimes and pipecat.compat in packages/together/package.json: ✅ means the compat smoke test passes on that runtime.

• The client is the official openai JS SDK (through @pipedog/openai), which talks through fetch. It works on Bun, Node, Deno and Cloudflare Workers.
• The deprecated model constructor option is not ported. Use settings.
• Tested against a local OpenAI-compatible mock server, not against Together AI itself.