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

# Simple Setup

> Set up Prisma AIRS AI Gateway in Strata Cloud Manager and make your first LLM request.

This guide takes you from an empty gateway to a working LLM request. It uses OpenAI as the
provider because it is the shortest path; every step works the same way for Anthropic, Vertex
AI, Bedrock, Azure OpenAI and the rest of the [supported providers](/docs/aigw/integrations/llms).

<Note>
  **Before you start.** AI Gateway must be enabled on your Strata Cloud Manager tenant.
</Note>

<Tip>
  This is the minimal path. To scan requests with Prisma AIRS, enable the plugin and attach a
  guardrail — see the [Prisma AIRS guardrail
  reference](/docs/aigw/integrations/guardrails/palo-alto-panw-prisma) — then bind it to your key with
  a [config](/docs/aigw/product/ai-gateway/configs).
</Tip>

## Overview

<Steps>
  <Step title="Set up a workspace" />

  <Step title="Add an LLM integration" />

  <Step title="Create an API key" />

  <Step title="Make your first request" />

  <Step title="Check the logs" />
</Steps>

***

## 1. Set up a workspace

Workspaces are managed under **Workspace Control**. A workspace is the unit that owns
integrations, configs and API keys, and it is the boundary your access scopes are evaluated
against.

Use the default workspace to get started, or create one for this exercise. Everything below is
created inside a workspace, so make a note of which one you are in.

<Note>
  The tenancy model is **Organisation → Workspace → User/Machine**. Your organisation is your
  Strata Cloud Manager tenant; workspaces divide it; users and machine identities act within a
  workspace.
</Note>

## 2. Add an LLM integration

Go to **Integrations → Add LLM Integration**.

<Steps>
  <Step title="Select the provider">
    Choose **OpenAI**.
  </Step>

  <Step title="Supply the credential">
    Paste your OpenAI API key. Other providers take different credential shapes — Vertex AI takes
    a service account JSON file, Bedrock takes an IAM role or access keys.
  </Step>

  <Step title="Assign the integration to your workspace">
    Only workspaces you assign here can route through this integration.
  </Step>

  <Step title="Select models">
    Pick the models you want exposed, then click **Create Integration**.
  </Step>
</Steps>

The integration gets a **provider slug** — something like `@openai-prod`. You will use it in the
`model` parameter of every request.

## 3. Create an API key

Go to **Security Keys → Create New**.

Create the key inside the workspace from step 1. You can attach default metadata here, which
then shows up on every log line, and a [config](/docs/aigw/product/ai-gateway/configs) if you have
one — any request made with the key then picks it up without the caller passing anything extra.

Copy the key. It is shown once.

<Card title="API keys, authentication and authorisation" href="/docs/aigw/product/enterprise-offering/org-management/api-keys-authn-and-authz">
  Scopes, metadata enforcement, expiry and rotation.
</Card>

## 4. Make your first request

The gateway speaks the OpenAI API. Point your existing client at
`https://aigw.portkey.ai/v1`, authenticate with your gateway API key, and prefix the model with
your provider slug.

<CodeGroup>
  ```sh cURL theme={"system"}
  curl https://aigw.portkey.ai/v1/chat/completions \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer $PORTKEY_API_KEY" \
    -d '{
      "model": "@openai-prod/gpt-4o",
      "messages": [
        { "role": "user", "content": "Say hello in one sentence." }
      ]
    }'
  ```

  ```py OpenAI Python theme={"system"}
  from openai import OpenAI

  client = OpenAI(
      api_key="YOUR_PORTKEY_API_KEY",
      base_url="https://aigw.portkey.ai/v1",
  )

  completion = client.chat.completions.create(
      model="@openai-prod/gpt-4o",
      messages=[{"role": "user", "content": "Say hello in one sentence."}],
  )

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

  ```js OpenAI Node theme={"system"}
  import OpenAI from "openai";

  const client = new OpenAI({
    apiKey: "YOUR_PORTKEY_API_KEY",
    baseURL: "https://aigw.portkey.ai/v1",
  });

  const completion = await client.chat.completions.create({
    model: "@openai-prod/gpt-4o",
    messages: [{ role: "user", content: "Say hello in one sentence." }],
  });

  console.log(completion.choices[0].message.content);
  ```
</CodeGroup>

Three things to note:

* **`Authorization` carries the gateway key**, not the provider key. The gateway holds the OpenAI
  credential from step 2 and attaches it upstream.
* **The provider slug lives in `model`.** `@openai-prod/gpt-4o` means "the `gpt-4o` model, via the
  `@openai-prod` integration". You do not need a provider header.
* **Policy rides on the key.** Anything attached to the config on your API key — guardrails,
  fallbacks, retries, caching — applies without the caller opting in.

<Tip>
  To scope a config to a single request rather than to the whole API key, pass
  `-H "x-portkey-config: pc-xxxxxx"`. The header overrides the key's default.
</Tip>

## 5. Check the logs

Go to **Observability → Logs**. Your request is there with the model, provider, token counts,
cost and latency. If a guardrail is attached to the key, its verdict shows here too.

To correlate a set of calls, pass a trace ID on the request:

```sh theme={"system"}
-H "x-portkey-trace-id: my-first-session"
```

Requests sharing a trace ID are grouped as one session in the log view.

Once Prisma AIRS scanning is enabled, the same trace ID resolves on the Prisma AIRS side under
**AI Runtime → AI Sessions**, where you can see the scan results for that session.

## Next steps

<CardGroup cols={2}>
  <Card title="Model Catalog" href="/docs/aigw/product/model-catalog" icon="microchip-ai">
    Add more providers, set budget and rate limits per workspace.
  </Card>

  <Card title="Guardrails" href="/docs/aigw/product/guardrails" icon="shield-halved">
    Guardrail actions, PII redaction, and the full check list.
  </Card>

  <Card title="AI Gateway" href="/docs/aigw/product/ai-gateway" icon="network-wired">
    Fallbacks, retries, load balancing, caching and conditional routing.
  </Card>

  <Card title="Observability" href="/docs/aigw/product/observability" icon="chart-line">
    Analytics, traces, metadata and OpenTelemetry export.
  </Card>

  <Card title="Coding agents" href="/docs/aigw/integrations/libraries/claude-code" icon="terminal">
    Route Claude Code, Cursor, Cline and Codex through the gateway.
  </Card>

  <Card title="Integrations" href="/docs/aigw/integrations/overview" icon="puzzle-piece">
    Agent frameworks, libraries, tracing providers and MCP.
  </Card>
</CardGroup>


## Related topics

- [OpenAI Agents SDK (Python)](/docs/aigw/integrations/agents/openai-agents.md)
- [OpenAI Agents SDK (TypeScript)](/docs/aigw/integrations/agents/openai-agents-ts.md)
- [LangGraph](/docs/aigw/integrations/agents/langgraph.md)
- [Setup Assumed Role for Claude Platform on AWS](/docs/aigw/integrations/llms/claude-platform-aws/setup-assumed-role.md)
- [CrewAI](/docs/aigw/integrations/agents/crewai.md)