# Together AI cost tracking

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

```python [Python]
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)
```

```ts [TypeScript]
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](/providers/together).
- [Self-hosted models](/integrations/self-hosted): when you move a model onto your own GPUs.