Together AI cost tracking

Price every Together AI call at Together AI's own rates through the OpenAI client, attribute it to customers and features, and check it against the invoice.

By Keyveve, Inc. · Updated 2026-10-23

Together AI serves open models through an OpenAI-compatible API. Wrap the OpenAI client pointed at it and every call is priced at Together AI's published rate for that model, not another host's.

Wrap the client

import veqen
from openai import OpenAI

veqen.init()  # reads VEQEN_API_KEY, an ingest key
client = veqen.wrap(OpenAI(base_url="https://api.together.xyz/v1", api_key=API_KEY), feature="extraction")

with veqen.tags(customer=org.id):
    client.chat.completions.create(model="meta-llama/Llama-3.3-70B-Instruct-Turbo", messages=messages)

import OpenAI from "openai";
import { wrap } from "@veqen/sdk";

const client = wrap(new OpenAI({ baseURL: "https://api.together.xyz/v1", apiKey: process.env.API_KEY }), { feature: "extraction" });

The host is read from the base URL, and the model id Together AI reports is looked up in its own price list first. Use the OpenAI client: Together AI's own SDK isn't wrapped. Through LiteLLM, together_ai/ models are priced the same way.

Reconcile to the bill

Together AI has no cost API, so enter each month's invoice under Bills entered by hand on the Bill check page. Veqen compares it with what you tracked for Together AI that month, and the monthly close books the invoice amount.

Next

• Together AI model prices.
• Self-hosted models: when you move a model onto your own GPUs.