/completions

Create text completions for provided prompts. This is a legacy endpoint; prefer /chat/completions for new applications.

POST

/v1/completions

Creates a completion for the provided prompt.

Request Body

modelID of the model to use (required)

promptThe prompt to generate completions for (required)

max_tokensMaximum tokens to generate

temperatureSampling temperature 0-2 (default: 1)

Request Body

{
  "model": "your-model",
  "prompt": "Say hello in Japanese:",
  "max_tokens": 100,
  "temperature": 0.7
}