Start here

Quickstart

From your first API key to your first completion.

On this page

1. Set up your account 2. Create a model key 3. Choose a model 4. Send your first request 5. Inspect the result

1. Set up your account

Create an account at 17.wtf, sign in, and open the console. Complete account verification to access free models. Paid models require available package credits. Check Credits for your balance and available packages.

2. Create a model key

Open API Keys, create and name a key, and copy the secret. Store it as an environment variable in your server environment. The tools API requires a separate tool key created in Tools Studio.

export LM0_API_KEY="YOUR_MODEL_API_KEY"

3. Choose a model

Find a text model in the Models page or list models with the API. Copy its exact ID, including any pool prefix. Replace MODEL_ID in all examples with that ID. Model availability and capabilities depend on your account and the selected model.

curl https://api.17.wtf/v1/models \
  -H "Authorization: Bearer $LM0_API_KEY"

4. Send your first request

Use cURL directly, or install an SDK with pip install openai or npm install openai. Run SDK examples on your server. The OpenAI SDK base URL includes /v1.

curl https://api.17.wtf/v1/chat/completions \
  -H "Authorization: Bearer $LM0_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "MODEL_ID",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "max_tokens": 512
}'

5. Inspect the result

Read the assistant text from choices[0].message.content and token counts from usage. Review requests in Usage. If a request fails, keep the response status, error message, and x-request-id for troubleshooting.