For the complete documentation index, see llms.txt. Markdown versions of all docs pages are available by appending .md to any docs URL.

LLM playground

Send a test chat completion through the gateway in the agentgateway admin UI.

Use the built-in LLM playground in the agentgateway admin UI to send a chat completion request through your configured LLM provider. The playground sends a real request through the gateway, so you can confirm that your provider, model, and policies work before you point an application at agentgateway.

Before you begin

1. Install the agentgateway binary.
2. Configure at least one LLM provider. For an example, see OpenAI or any OpenAI-compatible provider.

Send a test request

1. Run agentgateway with your LLM configuration.

   agentgateway -f config.yaml

2. Open the LLM playground.

3. If you see a Browser access is not allowed notice, click Apply CORS so the playground can call the LLM listener from the UI.

4. In the Model list, select a model. If your configuration uses a wildcard (*) model, enter a specific model name in the Specific model field, such as gpt-4o-mini.

5. Optional: Expand System prompt to review or change the system prompt.

6. In the User message box, enter a prompt, such as Say hello to agentgateway, and click Send.

7. Verify that the gateway forwards the request to your provider and returns a response in the chat panel. Each response also shows the provider, model, latency, and token usage.

   

   

Next steps

• Observe LLM traffic with metrics, logs, and traces.
• Try out CEL expressions in the CEL playground.