Quickstart

Get a key from the console, then hit chat completions.

1. Get an API key

Create a key in the console. It goes in the Authorization header as a bearer token.

2. List the lineup

curl https://api.refuseless.dev/v1/models \
  -H "Authorization: Bearer $REFUSELESS_API_KEY"

3. Send a chat completion

curl https://api.refuseless.dev/v1/chat/completions \
  -H "Authorization: Bearer $REFUSELESS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.3-refuseless",
    "messages": [{"role": "user", "content": "Write a tight system prompt."}]
  }'

4. Stream it

Add "stream": true and read Server-Sent Events. Each event is data: {...} followed by data: [DONE]. See Streaming.

Next steps

Authentication — keys and error codes
Models — the current lineup
Chat completions — full request/response reference
SDKs — OpenAI / Anthropic SDK drop-in