XPNCORE API quick start

Top up your wallet, then open the setup wizard to create an API key. Store the key in an environment variable; you can view it again on the API keys page.

Call GET /v1/models to get the models you can use instead of hard-coding a model ID.

Key points

Keep the API key in an environment variable, never in source code.
Use the base URL shown in the setup wizard.
Call GET /v1/models and choose a model ID.
Use stream=false for JSON, or stream=true to receive the answer in parts until [DONE].
Keep the x-routing-request-id header (your request ID) to include with support requests.

Example request

POST /v1/chat/completions

curl --request POST 'https://api.xpncore.com/v1/chat/completions' \
  --max-time 35 \
  --header "Authorization: Bearer $API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "MODEL_ID_FROM_GET_V1_MODELS",
  "messages": [
    {
      "role": "user",
      "content": "Hello from the gateway"
    }
  ],
  "temperature": 0.7,
  "max_tokens": 512,
  "stream": false
}'

Open the setup wizard Playground