Preise und Kosten
Output Price
The per-million-token cost charged for tokens the model generates.
Output price covers every token the model writes in its completion. Generation is more compute-intensive than reading (prefill), so output tokens are priced 2–5× higher than input tokens. Controlling output length — through concise instructions or max_tokens limits — is one of the most effective cost-reduction levers.
Verwandte Begriffe
Input Price
The per-million-token cost charged for tokens in your prompt.
Token
The basic unit of text that language models process and are billed by.
Completion
The text output generated by a language model in response to a prompt.
Context Window
The maximum number of tokens a model can process in a single request.