RIrilldata

Complete sends the messages of a chat to the AI and asks it to generate a new message.

Changed on
post/v1/ai/complete

Request

  • The document declares no server URL.
  • Auth
    none declared

Request body

includeReasoningboolean

Whether the response may include reasoning blocks. Older clients don't support them, so they are removed from the response unless this is set.

outputJsonSchemastring

Response

A successful response.

cacheWriteInputTokensinteger

Number of input tokens written to the prompt cache, which some providers (e.g. Claude) bill at a premium.

cachedInputTokensinteger

Number of cache-read (discounted) input tokens; a subset of input_tokens.

inputTokensinteger

Number of full-rate (non-cached) tokens in the input.

outputTokensinteger

Number of tokens in the output.

providerstring

The LLM provider that served the completion (e.g. "claude", "openai", "gemini").

Changes

  • v12f4cda73bc26Revision changes
    • info

      added the new optional request property

    • info

      added the new optional request property ////

    • info

      added the optional property to the response with the status

    • info

      added the optional property /// to the response with the status

  • v1e47705c6c629Revision changes
    • info

      added the optional property to the response with the status

    • info

      added the optional property to the response with the status