For the complete documentation index, see llms.txt. Markdown versions of all docs pages are available by appending .md to any docs URL.
Perplexity
Route agentgateway LLM traffic to models available through Perplexity.
Configure Perplexity as an LLM provider in agentgateway.
Note
Send requests to /v1/responses or /v1/messages. Messages requests are converted to the OpenAI Responses format, which is the only format that the perplexity provider sends to Perplexity. Requests to /v1/chat/completions fail. To send Chat Completions requests to Perplexity, use a custom provider with the completions format and baseUrl: https://api.perplexity.ai/v1.
Configuration
Review the following example configuration.# yaml-language-server: $schema=https://agentgateway.dev/schema/config
llm:
models:
- name: "*"
provider: perplexity
params:
apiKey: "$PERPLEXITY_API_KEY"Review the following table to understand this configuration.
| Setting | Description |
|---|---|
name | The model name to match in incoming requests. When a client sends "model": "<name>", the request is routed to this provider. Use * to match any model name. |
provider | The LLM provider, set to perplexity. |
params.model | Optional. If you set this field, this model is used for all requests. If you omit this field, the request must include the model to use. |
params.apiKey | Your Perplexity API key. You can reference environment variables using the $VAR_NAME syntax. |
params.baseUrl | Optional. Overrides the provider base URL. Default: https://api.perplexity.ai/v1. |
Example request
After you run agentgateway with the Perplexity configuration, send an OpenAI Responses request to the /v1/responses endpoint:
curl -X POST http://localhost:4000/v1/responses \
-H "Content-Type: application/json" \
-d '{
"model": "perplexity/sonar",
"input": "Hello from Perplexity!"
}'