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

# Portkey

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

[Portkey](https://portkey.ai/) is an AI gateway and control panel that puts a single OpenAI-compatible endpoint in front of 250+ LLMs, with retries, fallbacks, caching, and cost controls. Arize AX captures every Portkey-routed call — the gateway request and the underlying LLM completion — via the [`openinference-instrumentation-portkey`](https://github.com/Arize-ai/openinference/tree/main/python/instrumentation/openinference-instrumentation-portkey) package.

## Prerequisites

* Python 3.10+
* An Arize AX account ([sign up](https://arize.com/sign-up/))
* A `PORTKEY_API_KEY` from the [Portkey dashboard](https://app.portkey.ai/)
* An `OPENAI_API_KEY` from the [OpenAI Platform](https://platform.openai.com/api-keys) (the example routes Portkey → OpenAI; swap in any other provider Portkey supports)

## 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-portkey portkey-ai openai
```

## Configure credentials

```bash theme={null}
export ARIZE_SPACE_ID="<your-space-id>"
export ARIZE_API_KEY="<your-api-key>"
export ARIZE_PROJECT_NAME="portkey-tracing-example"
export PORTKEY_API_KEY="<your-portkey-api-key>"
export OPENAI_API_KEY="<your-openai-api-key>"
```

## Setup tracing

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

from arize.otel import register
from openinference.instrumentation.portkey import PortkeyInstrumentor

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

PortkeyInstrumentor().instrument(tracer_provider=tracer_provider)
print("Arize AX tracing initialized for Portkey.")
```

## Run Portkey

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

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

import os

from portkey_ai import Portkey

# The Portkey SDK forwards the request to the named provider using the
# Authorization header you pass. The instrumentor only wraps calls made
# through this client — using the OpenAI SDK pointed at Portkey's URL
# would bypass the instrumentation.
portkey = Portkey(
    api_key=os.environ["PORTKEY_API_KEY"],
    provider="openai",
    Authorization=f"Bearer {os.environ['OPENAI_API_KEY']}",
)

response = portkey.chat.completions.create(
    model="gpt-5.4-mini",
    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 Portkey.
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 **`portkey-tracing-example`**.
2. You should see a new trace within \~30 seconds containing a `Completions` LLM span with the prompt, response, and token usage attached. The span's `llm.model_name` reflects the resolved provider model (e.g. `gpt-5.4-mini`).
3. If no traces appear, see [Troubleshooting](#troubleshooting).

### Check from the skill, CLI, or SDK

Confirm spans are actually reaching your Arize AX project. Use whichever fits your workflow — the skill and CLI work for any framework; the SDK check is shown for each language.

<Tabs>
  <Tab title="Arize skill (agent)">
    Install the [Arize Skills](https://github.com/Arize-ai/arize-skills) plugin and let your coding agent check for you:

    ```bash theme={null}
    npx skills add Arize-ai/arize-skills
    ```

    Then prompt your agent:

    > Use the `arize-trace` skill to export and analyze recent traces from my project. Confirm spans are arriving, and summarize any errors or latency issues.
  </Tab>

  <Tab title="AX CLI">
    Export recent spans for your project — any rows mean traces are landing:

    ```bash theme={null}
    ax spans export "$ARIZE_PROJECT_NAME" --space "$ARIZE_SPACE_ID" \
      --limit 5 --stdout | jq 'length'
    ```

    A non-zero count confirms spans reached Arize AX. Run `ax auth login` first if you have not authenticated. See the [`ax spans` reference](/docs/api-clients/cli/spans).
  </Tab>

  <Tab title="SDK">
    Query the project's spans and check that at least one came back.

    <CodeGroup>
      ```python Python theme={null}
      import os
      from arize import ArizeClient

      client = ArizeClient(api_key=os.environ["ARIZE_API_KEY"])
      resp = client.spans.list(
          project=os.environ["ARIZE_PROJECT_NAME"],
          space=os.environ["ARIZE_SPACE_ID"],
          limit=5,
      )
      count = len(resp.spans)
      print(
          f"{count} span(s) found" if count else "No spans yet — recheck setup"
      )
      ```

      ```typescript TypeScript theme={null}
      // Reads ARIZE_API_KEY from the environment.
      import { listSpans } from "@arizeai/ax-client";

      const { data: spans } = await listSpans({
        project: process.env.ARIZE_PROJECT_NAME!,
        space: process.env.ARIZE_SPACE_ID!,
        limit: 5,
      });
      const count = spans.length;
      console.log(
        count ? `${count} span(s) found` : "No spans yet — recheck setup",
      );
      ```

      ```go Go theme={null}
      client, err := arize.NewClient(
          arize.Config{APIKey: os.Getenv("ARIZE_API_KEY")},
      )
      if err != nil {
          log.Fatal(err)
      }
      resp, err := client.Spans.List(ctx, spans.ListRequest{
          Project: os.Getenv("ARIZE_PROJECT_NAME"),
          Space:   os.Getenv("ARIZE_SPACE_ID"),
          Limit:   5,
      })
      if err != nil {
          log.Fatal(err)
      }
      fmt.Printf("%d span(s) found\n", len(resp.Spans))
      ```
    </CodeGroup>

    SDK span references: [Python](/docs/api-clients/python/version-8/client-resources/spans) · [TypeScript](/docs/api-clients/typescript/version-1/client-resources/spans) · [Go](/docs/api-clients/go/version-2/client-resources/spans).
  </Tab>
</Tabs>

## 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.
* **Portkey spans missing but other spans present.** `PortkeyInstrumentor().instrument(...)` must run before any `from portkey_ai import ...`. Make sure `instrumentation.py` is the first import in your entry point.
* **`401` from the gateway.** A `401` with an OpenAI body means `OPENAI_API_KEY` is invalid; a `401` with a Portkey body means `PORTKEY_API_KEY` is invalid. Check both in the [Portkey logs](https://app.portkey.ai/).
* **Routing to a different provider.** Set `provider=` in `createHeaders(...)` (e.g. `"anthropic"`, `"google"`) and pass the matching provider key. Portkey also supports virtual keys — see the [Portkey docs](https://docs.portkey.ai/) for setup.

## Resources

<CardGroup>
  <Card icon="book-open" href="https://docs.portkey.ai/" title="Portkey Documentation" horizontal />

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

  <Card icon="github" href="https://github.com/Portkey-AI/portkey-python-sdk" title="Portkey Python SDK" horizontal />
</CardGroup>