## Create a decision `client.Decisions.New(ctx, body) (*Decision, error)` **post** `/decisions` Use this endpoint to quickly answer classification or scoring questions about some input. You can ask multiple questions in one request. ### Parameters - `body DecisionNewParams` - `Input param.Field[DecisionNewParamsInputUnion]` The input to evaluate for every question. Provide a text string or an ordered array of messages, function calls and outputs, or custom tool calls and outputs. Each tool output must identify a matching call by call ID. - `string` - `type DecisionNewParamsInputArray []DecisionNewParamsInputArrayItemUnion` - `type DecisionNewParamsInputArrayItemDecisionInputUserMessage struct{…}` A user message containing input text, images, or JSON. - `Content DecisionNewParamsInputArrayItemDecisionInputUserMessageContentUnion` A text string or an ordered list of text, image, and JSON parts. - `string` - `type DecisionNewParamsInputArrayItemDecisionInputUserMessageContentParts []DecisionInputPartUnion` - `type DecisionInputText struct{…}` - `Text string` - `Type InputText` - `const InputTextInputText InputText = "input_text"` - `PromptCacheBreakpoint DecisionPromptCacheBreakpoint` 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. - `Mode Explicit` The breakpoint mode. Always `explicit`. - `const ExplicitExplicit Explicit = "explicit"` - `type DecisionInputImage struct{…}` An image provided as a base64 data URL or a publicly accessible HTTP(S) URL. File IDs are not supported. - `ImageURL string` A base64-encoded image in a data URL or a publicly accessible HTTP(S) image URL. - `Type InputImage` - `const InputImageInputImage InputImage = "input_image"` - `Detail DecisionInputImageDetail` The image detail level, using the selected model's image profile. Defaults to auto. - `const DecisionInputImageDetailLow DecisionInputImageDetail = "low"` - `const DecisionInputImageDetailHigh DecisionInputImageDetail = "high"` - `const DecisionInputImageDetailAuto DecisionInputImageDetail = "auto"` - `const DecisionInputImageDetailOriginal DecisionInputImageDetail = "original"` - `PromptCacheBreakpoint DecisionPromptCacheBreakpoint` 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. - `type DecisionInputJSON struct{…}` A JSON object or an array of objects rendered as text. Nested values may be any JSON value. Limited to 32 container levels, 10,000 values, and 256 KiB of compact UTF-8 JSON. - `Data DecisionInputJSONDataUnion` - `map[string, any]` - `[]map[string, any]` - `Type InputJSON` - `const InputJSONInputJSON InputJSON = "input_json"` - `Role User` - `const UserUser User = "user"` - `Type string` - `const DecisionNewParamsInputArrayItemDecisionInputUserMessageTypeMessage DecisionNewParamsInputArrayItemDecisionInputUserMessageType = "message"` - `type DecisionNewParamsInputArrayItemDecisionInputDeveloperMessage struct{…}` A developer message containing input text. - `Content DecisionNewParamsInputArrayItemDecisionInputDeveloperMessageContentUnion` A text string or an ordered list of input text parts. - `string` - `DecisionNewParamsInputArrayItemDecisionInputDeveloperMessageContentParts` - `Text string` - `Type InputText` - `PromptCacheBreakpoint DecisionPromptCacheBreakpoint` 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. - `Role Developer` - `const DeveloperDeveloper Developer = "developer"` - `Type string` - `const DecisionNewParamsInputArrayItemDecisionInputDeveloperMessageTypeMessage DecisionNewParamsInputArrayItemDecisionInputDeveloperMessageType = "message"` - `type DecisionNewParamsInputArrayItemDecisionInputSystemMessage struct{…}` A system message containing input text. - `Content DecisionNewParamsInputArrayItemDecisionInputSystemMessageContentUnion` A text string or an ordered list of input text parts. - `string` - `DecisionNewParamsInputArrayItemDecisionInputSystemMessageContentParts` - `Text string` - `Type InputText` - `PromptCacheBreakpoint DecisionPromptCacheBreakpoint` 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. - `Role System` - `const SystemSystem System = "system"` - `Type string` - `const DecisionNewParamsInputArrayItemDecisionInputSystemMessageTypeMessage DecisionNewParamsInputArrayItemDecisionInputSystemMessageType = "message"` - `type DecisionNewParamsInputArrayItemDecisionInputAssistantMessage struct{…}` An assistant message containing output text or refusals. - `Content DecisionNewParamsInputArrayItemDecisionInputAssistantMessageContentUnion` A text string or an ordered list of output text and refusal parts. - `string` - `type DecisionNewParamsInputArrayItemDecisionInputAssistantMessageContentParts []DecisionNewParamsInputArrayItemDecisionInputAssistantMessageContentPartsItemUnion` - `type DecisionNewParamsInputArrayItemDecisionInputAssistantMessageContentPartOutputText struct{…}` - `Text string` - `Type OutputText` - `const OutputTextOutputText OutputText = "output_text"` - `type DecisionNewParamsInputArrayItemDecisionInputAssistantMessageContentPartRefusal struct{…}` - `Refusal string` - `Type Refusal` - `const RefusalRefusal Refusal = "refusal"` - `Role Assistant` - `const AssistantAssistant Assistant = "assistant"` - `Phase string` The phase of an assistant message. - `const DecisionNewParamsInputArrayItemDecisionInputAssistantMessagePhaseCommentary DecisionNewParamsInputArrayItemDecisionInputAssistantMessagePhase = "commentary"` - `const DecisionNewParamsInputArrayItemDecisionInputAssistantMessagePhaseFinalAnswer DecisionNewParamsInputArrayItemDecisionInputAssistantMessagePhase = "final_answer"` - `Type string` - `const DecisionNewParamsInputArrayItemDecisionInputAssistantMessageTypeMessage DecisionNewParamsInputArrayItemDecisionInputAssistantMessageType = "message"` - `type DecisionNewParamsInputArrayItemFunctionCall struct{…}` - `Arguments string` - `CallID string` - `Name string` - `Type FunctionCall` - `const FunctionCallFunctionCall FunctionCall = "function_call"` - `ID string` - `Namespace string` - `Status string` - `const DecisionNewParamsInputArrayItemFunctionCallStatusInProgress DecisionNewParamsInputArrayItemFunctionCallStatus = "in_progress"` - `const DecisionNewParamsInputArrayItemFunctionCallStatusCompleted DecisionNewParamsInputArrayItemFunctionCallStatus = "completed"` - `const DecisionNewParamsInputArrayItemFunctionCallStatusIncomplete DecisionNewParamsInputArrayItemFunctionCallStatus = "incomplete"` - `Model param.Field[string]` The model to use. Only `gpt-6-luna` is supported. - `Questions param.Field[[]DecisionNewParamsQuestionUnion]` Ask 1–400 questions about the input. Each question can be a predicate, choice, or score. Answers come back in the same order. - `type DecisionNewParamsQuestionPredicate struct{…}` Estimate how likely it is that a statement about the input is true. - `Instructions DecisionNewParamsQuestionPredicateInstructionsUnion` - `string` - `type DecisionNewParamsQuestionPredicateInstructionsArray []DecisionQuestionInputPartUnion` - `type DecisionQuestionInputText struct{…}` - `Text string` - `Type InputText` - `const InputTextInputText InputText = "input_text"` - `type DecisionQuestionInputImage struct{…}` An image provided as a base64 data URL or a publicly accessible HTTP(S) URL. File IDs are not supported. - `ImageURL string` A base64-encoded image in a data URL or a publicly accessible HTTP(S) image URL. - `Type InputImage` - `const InputImageInputImage InputImage = "input_image"` - `Detail DecisionQuestionInputImageDetail` The image detail level, using the selected model's image profile. Defaults to auto. - `const DecisionQuestionInputImageDetailLow DecisionQuestionInputImageDetail = "low"` - `const DecisionQuestionInputImageDetailHigh DecisionQuestionInputImageDetail = "high"` - `const DecisionQuestionInputImageDetailAuto DecisionQuestionInputImageDetail = "auto"` - `const DecisionQuestionInputImageDetailOriginal DecisionQuestionInputImageDetail = "original"` - `type DecisionInputJSON struct{…}` A JSON object or an array of objects rendered as text. Nested values may be any JSON value. Limited to 32 container levels, 10,000 values, and 256 KiB of compact UTF-8 JSON. - `Type Predicate` The type of the object. Always `predicate`. - `const PredicatePredicate Predicate = "predicate"` - `Name string` - `type DecisionNewParamsQuestionChoice struct{…}` Choose from the supplied options based on the input. - `Choices []DecisionNewParamsQuestionChoiceChoice` Provide between 2 and 255 choices. Each choice must be unique. - `Value DecisionNewParamsQuestionChoiceChoiceValueUnion` Choice values are typed: a string and a boolean with the same text are distinct. - `string` - `bool` - `Description string` - `Instructions DecisionNewParamsQuestionChoiceInstructionsUnion` - `string` - `type DecisionNewParamsQuestionChoiceInstructionsArray []DecisionQuestionInputPartUnion` - `type DecisionQuestionInputText struct{…}` - `type DecisionQuestionInputImage struct{…}` An image provided as a base64 data URL or a publicly accessible HTTP(S) URL. File IDs are not supported. - `type DecisionInputJSON struct{…}` A JSON object or an array of objects rendered as text. Nested values may be any JSON value. Limited to 32 container levels, 10,000 values, and 256 KiB of compact UTF-8 JSON. - `Type Choice` The type of the object. Always `choice`. - `const ChoiceChoice Choice = "choice"` - `Name string` - `type DecisionNewParamsQuestionScore struct{…}` Rate the input against the supplied ordered levels. - `Instructions DecisionNewParamsQuestionScoreInstructionsUnion` - `string` - `type DecisionNewParamsQuestionScoreInstructionsArray []DecisionQuestionInputPartUnion` - `type DecisionQuestionInputText struct{…}` - `type DecisionQuestionInputImage struct{…}` An image provided as a base64 data URL or a publicly accessible HTTP(S) URL. File IDs are not supported. - `type DecisionInputJSON struct{…}` A JSON object or an array of objects rendered as text. Nested values may be any JSON value. Limited to 32 container levels, 10,000 values, and 256 KiB of compact UTF-8 JSON. - `Levels []DecisionNewParamsQuestionScoreLevel` - `Label string` - `Description string` - `Type Score` The type of the object. Always `score`. - `const ScoreScore Score = "score"` - `Name string` - `PromptCacheKey param.Field[string]` Partition prompt cache reuse by caller-provided key. - `PromptCacheOptions param.Field[DecisionNewParamsPromptCacheOptions]` Options for prompt caching. Supported for `gpt-5.6` and later models. By default, OpenAI automatically chooses one implicit cache breakpoint. You can add explicit breakpoints to content blocks with `prompt_cache_breakpoint`. Each request can write up to four breakpoints. For cache matching, OpenAI considers up to the latest 80 breakpoints in the conversation, without a content-block lookback limit. Set `mode` to `explicit` to disable the implicit breakpoint. The `ttl` defaults to `30m`, which is currently the only supported value. See the [prompt caching guide](/api/docs/guides/prompt-caching) for current details. - `Mode string` Controls whether OpenAI automatically creates an implicit cache breakpoint. Defaults to `implicit`. With `implicit`, OpenAI creates one implicit breakpoint and writes up to the latest three explicit breakpoints in the request. With `explicit`, OpenAI does not create an implicit breakpoint and writes up to the latest four explicit breakpoints. If there are no explicit breakpoints, the request does not use prompt caching. - `const DecisionNewParamsPromptCacheOptionsModeImplicit DecisionNewParamsPromptCacheOptionsMode = "implicit"` - `const DecisionNewParamsPromptCacheOptionsModeExplicit DecisionNewParamsPromptCacheOptionsMode = "explicit"` - `Ttl string` The minimum lifetime applied to every implicit and explicit cache breakpoint written by the request. Defaults to `30m`, which is currently the only supported value. The backend may retain cache entries for longer. - `const DecisionNewParamsPromptCacheOptionsTtl30m DecisionNewParamsPromptCacheOptionsTtl = "30m"` - `SafetyIdentifier param.Field[string]` Opaque caller-provided end-user identifier, scoped by the verified org. Match Responses' limit; this is never the authenticated user identity. ### Returns - `type Decision struct{…}` - `Answers []DecisionAnswerUnion` Answers in question order. Any question can return a refusal instead of an answer; other questions can still receive answers. A refusal has `type: "refusal"` and the question's `name`, or `null` if it was unnamed. - `type DecisionAnswerPredicate struct{…}` - `Name string` - `Probability float64` - `Type Predicate` The type of the object. Always `predicate`. - `const PredicatePredicate Predicate = "predicate"` - `type DecisionAnswerChoice struct{…}` - `Choice DecisionAnswerChoiceChoiceUnion` Choice values are typed: a string and a boolean with the same text are distinct. - `string` - `bool` - `Confidence float64` - `Name string` - `Probabilities []DecisionAnswerChoiceProbability` - `Probability float64` - `Value DecisionAnswerChoiceProbabilityValueUnion` Choice values are typed: a string and a boolean with the same text are distinct. - `string` - `bool` - `Type Choice` The type of the object. Always `choice`. - `const ChoiceChoice Choice = "choice"` - `type DecisionAnswerScore struct{…}` - `Confidence float64` - `Name string` - `Probabilities []DecisionAnswerScoreProbability` - `Label string` - `Probability float64` - `Value int64` - `Score float64` - `Type Score` The type of the object. Always `score`. - `const ScoreScore Score = "score"` - `type DecisionAnswerRefusal struct{…}` The model declined to answer this question. Other questions in the same request can still receive answers. - `Name string` - `Type Refusal` The type of the object. Always `refusal`. - `const RefusalRefusal Refusal = "refusal"` - `Model string` The model used. - `Usage DecisionUsage` Token usage for the request. - `InputTokens int64` - `InputTokensDetails DecisionUsageInputTokensDetails` - `CacheWriteTokens int64` - `CachedTokens int64` - `OutputTokens int64` - `OutputTokensDetails DecisionUsageOutputTokensDetails` - `ReasoningTokens int64` - `TotalTokens int64` ### Example ```go package main import ( "context" "fmt" "github.com/openai/openai-go" "github.com/openai/openai-go/option" ) func main() { client := openai.NewClient( option.WithAPIKey("My API Key"), ) decision, err := client.Decisions.New(context.TODO(), openai.DecisionNewParams{ Input: openai.DecisionNewParamsInputUnion{ OfString: openai.String("string"), }, Model: "model", Questions: []openai.DecisionNewParamsQuestionUnion{openai.DecisionNewParamsQuestionUnion{ OfPredicate: &openai.DecisionNewParamsQuestionPredicate{ Instructions: openai.DecisionNewParamsQuestionPredicateInstructionsUnion{ OfString: openai.String("string"), }, }, }}, }) if err != nil { panic(err.Error()) } fmt.Printf("%+v\n", decision.Answers) } ``` #### Response ```json { "answers": [ { "name": "name", "probability": 0, "type": "predicate" } ], "model": "model", "usage": { "input_tokens": -2147483648, "input_tokens_details": { "cache_write_tokens": -2147483648, "cached_tokens": -2147483648 }, "output_tokens": -2147483648, "output_tokens_details": { "reasoning_tokens": -2147483648 }, "total_tokens": -2147483648 } } ```