Skip to main content
Use the Context Router as the model in an OpenAI-compatible client or supported agent integration. You can configure it in an agent framework or a voice platform with a custom LLM field.
For platform-specific steps, use an agent integration such as ElevenLabs, Vapi, Deepgram, LiveKit, or Pipecat.

​
Prerequisites

  • A supported agent integration that accepts a custom OpenAI-compatible LLM.
  • An SLNG API key from your project’s Project Vault > SLNG API key page. A key from Call TTS/STT models API cannot call the Context Router. See Set up a project for your own code.
  • A model chosen in your project’s Think section: an SLNG model, or an LLM key you registered under Bring your own key.

​
Configuration

Use these three values:

​
Configure your agent integration

In your agent integration, enter the base URL and model from the table above. Store your API key in the platform’s secret manager or environment, then send it as an Authorization: Bearer <SLNG API key> header. The router also requires two headers that tie each turn to an SLNG agent and call: X-Slng-Agent-Id and X-Slng-Session-Id. Map them to your platform’s agent and session identifiers. Your platform guide lists the exact values to use. Follow your framework or platform guide for its exact configuration steps.
Read the key from the environment. Do not paste the literal value into your code or a shared config.

​
Next steps