> ## Documentation Index
> Fetch the complete documentation index at: https://arize-ax.mintlify.dev/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Together AI

> Trace Together AI inference calls with OpenInference and send spans to Arize AX for LLM observability.

[Together AI](https://www.together.ai/) hosts open-weight models (Llama 3.x, Qwen, Mistral, DeepSeek, and more) behind a fast OpenAI-compatible API. Arize AX captures every Together AI call — prompts, responses, model name, and token usage — by reusing the [`openinference-instrumentation-openai`](https://github.com/Arize-ai/openinference/tree/main/python/instrumentation/openinference-instrumentation-openai) package against the OpenAI client pointed at Together's endpoint.

## Prerequisites

* Python 3.9+
* An Arize AX account ([sign up](https://arize.com/sign-up/))
* A `TOGETHER_API_KEY` from the [Together AI console](https://api.together.ai/settings/api-keys)

## Launch Arize AX

1. Sign in to your [Arize AX account](https://app.arize.com/).
2. From **Space Settings**, copy your **Space ID** and **API Key**. You will set them as `ARIZE_SPACE_ID` and `ARIZE_API_KEY` below.

## Install

```bash theme={null}
pip install arize-otel openinference-instrumentation-openai openai
```

## Configure credentials

```bash theme={null}
export ARIZE_SPACE_ID="<your-space-id>"
export ARIZE_API_KEY="<your-api-key>"
export ARIZE_PROJECT_NAME="together-ai-tracing-example"
export TOGETHER_API_KEY="<your-together-api-key>"
```

## Setup tracing

```python theme={null}
# instrumentation.py
import os

from arize.otel import register
from openinference.instrumentation.openai import OpenAIInstrumentor

tracer_provider = register(
    space_id=os.environ["ARIZE_SPACE_ID"],
    api_key=os.environ["ARIZE_API_KEY"],
    project_name=os.environ["ARIZE_PROJECT_NAME"],
)

OpenAIInstrumentor().instrument(tracer_provider=tracer_provider)
print("Arize AX tracing initialized for Together AI.")
```

## Run Together AI

```python theme={null}
# example.py

# Importing instrumentation first ensures tracing is set up
# before `openai` is imported.
from instrumentation import tracer_provider

import os

from openai import OpenAI

# Together AI exposes an OpenAI-compatible endpoint. Point the OpenAI
# client at it and authenticate with TOGETHER_API_KEY.
client = OpenAI(
    api_key=os.environ["TOGETHER_API_KEY"],
    base_url="https://api.together.xyz/v1",
)

response = client.chat.completions.create(
    model="meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
    messages=[
        {
            "role": "user",
            "content": "Why is the ocean salty? Answer in two sentences.",
        }
    ],
)

print(response.choices[0].message.content)
```

### Expected output

```text wrap theme={null}
Arize AX tracing initialized for Together AI.
The ocean is salty because rivers continuously dissolve mineral salts from rocks and soil and carry them to the sea, where they accumulate over millions of years. Water leaves the ocean through evaporation but the salts remain, steadily concentrating until reaching today's roughly 3.5% salinity.
```

## Verify in Arize AX

1. Open your Arize AX space and select project **`together-ai-tracing-example`**.
2. You should see a new trace within \~30 seconds containing a `ChatCompletion` LLM span with the prompt, response, and token usage attached. The span's `llm.model_name` reflects the Together-hosted model (e.g. `meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo`).
3. If no traces appear, see [Troubleshooting](#troubleshooting).

## Troubleshooting

* **No traces in Arize AX.** Confirm `ARIZE_SPACE_ID` and `ARIZE_API_KEY` are set in the same shell that runs `example.py`. Enable OpenTelemetry debug logs with `export OTEL_LOG_LEVEL=debug` and re-run.
* **OpenAI spans missing.** `OpenAIInstrumentor().instrument(...)` must run before any `from openai import ...`. Make sure `instrumentation.py` is the first import in your entry point.
* **`401` from Together.** Verify `TOGETHER_API_KEY` is set and active. Generate a new key at [api.together.ai/settings/api-keys](https://api.together.ai/settings/api-keys) if needed.
* **`model_not_found`.** The exact model slug must match Together's catalog — see [Together's models page](https://www.together.ai/models). Swap the `model=` string for one your account can call.

## Resources

<CardGroup>
  <Card icon="book-open" href="https://docs.together.ai/docs/openai-api-compatibility" title="Together AI OpenAI Compatibility" horizontal />

  <Card icon="terminal" href="https://github.com/Arize-ai/openinference/tree/main/python/instrumentation/openinference-instrumentation-openai" title="OpenInference OpenAI Instrumentor" horizontal />

  <Card icon="github" href="https://github.com/togethercomputer/together-python" title="Together AI Python SDK" horizontal />
</CardGroup>