API ReferenceCopy MarkdownDecisionsCreate a decisionclient.decisions.create(DecisionCreateParams { input, model, questions, 3 more } body, RequestOptionsoptions?): Decision { answers, model, usage } POST/decisionsModelsExpand Collapse Decision { answers, model, usage } View schema detailsDecisionInputImage { image_url, type, detail, prompt_cache_breakpoint } An image provided as a base64 data URL or a publicly accessible HTTP(S) URL. File IDs are not supported. View schema detailsDecisionInputMessage = DecisionInputUserMessage { content, role, type } | DecisionInputDeveloperMessage { content, role, type } | DecisionInputSystemMessage { content, role, type } | DecisionInputAssistantMessage { content, role, phase, type } A user message containing input text, images, or JSON. View schema detailsDecisionInputPart = DecisionInputText { text, type, prompt_cache_breakpoint } | DecisionInputImage { image_url, type, detail, prompt_cache_breakpoint } | DecisionInputJSON { data, type } An image provided as a base64 data URL or a publicly accessible HTTP(S) URL. File IDs are not supported. View schema detailsDecisionInputText { text, type, prompt_cache_breakpoint } View schema detailsDecisionPromptCacheBreakpoint { mode } Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request’s prompt_cache_options.ttl; the boundary is not rounded to a token block. View schema details