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

# Connect your application

> Create a Gateway key, connect your client, and verify a model request.

Use a Gateway API key to send model requests from your application through Edgee. Edgee-billed tokens consume your organization’s credits; add credits in **Org. Settings → Credits**. With [BYOK](/docs/features/byok), provider usage is billed by your provider.

<Steps>
  <Step title="Select your organization">
    [Sign in to the console](https://www.edgee.ai/login), or accept your team's invitation using the invited email. Select the organization that should own the application's keys and usage.
  </Step>

  <Step title="Create an API key">
    Follow [Create an API key](/docs/llm-router/quickstart/api-key). Store the key in your application's environment or secret manager. Keep it out of browser-side code.
  </Step>

  <Step title="Connect your client">
    Use the [OpenAI SDK](/docs/llm-router/integrations/openai), [Anthropic SDK](/docs/llm-router/integrations/anthropic), [LangChain](/docs/llm-router/integrations/langchain), or an [Edgee SDK](/docs/llm-router). Follow [Integrate your stack](/docs/llm-router/quickstart/integration) for code examples.
  </Step>

  <Step title="Verify the request">
    Send a short prompt. Confirm a model response, then find the request in **Logs** for the same organization and key. Check the model and provider served, since routing settings can change them.
  </Step>
</Steps>

If the request fails, inspect its [error](/docs/llm-router/api-reference/errors) and the organization's credit balance and [model access](/docs/features/model-access) settings.

Next, [restrict your key](/docs/llm-router/api-keys) and add [usage tracking and request tags](/docs/llm-router/observability).