Clawrouter

POSThttps://your-instance.com/v1/completions

Takes a bare prompt instead of a message list. Kept for older integrations; new code should use chat completions, which every current model is tuned for.

modelstringrequired
Model to use.
promptstring | string[]required
The prompt to complete.
streambooleandefault: false
Stream the completion as it is produced.
temperaturenumberdefault: 1
Sampling temperature between 0 and 2. Lower is more deterministic.
top_pnumberdefault: 1
Nucleus sampling. Consider setting this or temperature, not both.
max_tokensinteger
Upper bound on generated tokens. The request fails if the prompt plus this exceeds the model's context window.
stopstring | string[]
Up to four sequences that end generation when produced.

curl

curl https://your-instance.com/v1/completions \
  -H "Authorization: Bearer $CLAWROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-3.5-turbo-instruct",
    "prompt": "Once upon a time",
    "max_tokens": 64
  }'