Together

together

YAML config

providers:
  - id: together:meta-llama/Llama-3-70b-chat-hf
    config:
      apiKey: ${TOGETHER_API_KEY}

TypeScript usage

import { createProvider } from "@evalguard/core";

const provider = createProvider("together", process.env.TOGETHER_API_KEY);
const response = await provider.complete({
  model: "meta-llama/Llama-3-70b-chat-hf",
  messages: [{ role: "user", content: "Hello" }],
});

Authentication

Set TOGETHER_API_KEY in your environment. EvalGuard validates the key on first call and surfaces typed errors for 401 / 403 / rate-limit responses (with Retry-After parsing).

Setup walkthrough

  1. 1. Sign up for an account on the Together platform.
  2. 2. Obtain your API key from the account dashboard.
  3. 3. Install the Together SDK using your preferred package manager.
  4. 4. Initialize the SDK in your application with the provided API key.
  5. 5. Test the connection by making a simple API call to fetch model information.

Gotchas

  • Rate limits are enforced per API key, so monitor usage to avoid hitting limits.
  • Some models may have regional availability restrictions, check the documentation for details.
  • Ensure you handle authentication errors gracefully, as they can occur if the API key is invalid.

Cost note

Pricing starts at $0.002 per 1,000 tokens for the cheapest model and $0.020 per 1,000 tokens for the flagship model.

Recommended models

Eval / judge
gpt-3.5-turbo
Agent / tool-use
gpt-4
Code
code-davinci-002
Vision
dall-e-2

LLM-generated (llm-gpt-4o) · 2026-05-23