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

# Prompt flow

> Use TokenLab through Prompt flow OpenAI connections

## Overview

Prompt flow's OpenAI connection supports a custom `base_url`. Set it to TokenLab's `/v1` endpoint and use TokenLab model IDs in your flow.

<Note>
  **Type**: Flow builder and evaluation platform

  **Primary Path**: OpenAI-compatible Chat Completions

  **Support Confidence**: Supported OpenAI-compatible path
</Note>

## Create A Connection

```bash theme={null}
pf connection create \
  --file ./my_chatbot/openai.yaml \
  --set api_key=sk-your-tokenlab-key base_url=https://api.tokenlab.sh/v1 \
  --name open_ai_connection
```

## Flow Notes

In your `flow.dag.yaml`, keep the connection name aligned with the command above:

```yaml theme={null}
connection: open_ai_connection
deployment_name: claude-sonnet-5
```

Some Prompt flow templates call this value `deployment_name` because the same templates also support Azure OpenAI deployments. With TokenLab, use the TokenLab model ID.

## Endpoint Notes

This integration uses Prompt flow's OpenAI-compatible connection. Native TokenLab Responses, Anthropic Messages, and Gemini routes require Prompt flow tools or custom Python nodes that call those endpoints directly.