OpenResponsesNonStreamingResponse | OpenRouter TypeScript SDK

The TypeScript SDK and docs are currently in beta. Report issues on GitHub.

Complete non-streaming response from the Responses API

Example Usage

import { OpenResponsesNonStreamingResponse } from "@openrouter/sdk/models";

let value: OpenResponsesNonStreamingResponse = {
  id: "resp-abc123",
  object: "response",
  createdAt: 1704067200,
  model: "gpt-4",
  status: "completed",
  completedAt: null,
  output: [
    {
      id: "msg-abc123",
      role: "assistant",
      type: "message",
      content: [
        {
          type: "output_text",
          text: "Hello! How can I help you today?",
        },
      ],
    },
  ],
  error: null,
  incompleteDetails: null,
  temperature: null,
  topP: null,
  presencePenalty: 293.66,
  frequencyPenalty: 9884.38,
  instructions: null,
  metadata: null,
  tools: [],
  toolChoice: "auto",
  parallelToolCalls: true,
};

Fields

Field	Type	Required	Description	Example
`id`	string	:heavy_check_mark:	N/A
`object`	models.ObjectT	:heavy_check_mark:	N/A
`createdAt`	number	:heavy_check_mark:	N/A
`model`	string	:heavy_check_mark:	N/A
`status`	models.OpenAIResponsesResponseStatus	:heavy_check_mark:	N/A
`completedAt`	number	:heavy_check_mark:	N/A
`output`	models.ResponsesOutputItem[]	:heavy_check_mark:	N/A
`user`	string	:heavy_minus_sign:	N/A
`outputText`	string	:heavy_minus_sign:	N/A
`promptCacheKey`	string	:heavy_minus_sign:	N/A
`safetyIdentifier`	string	:heavy_minus_sign:	N/A
`error`	models.ResponsesErrorField	:heavy_check_mark:	Error information returned from the API	`{"code": "rate_limit_exceeded","message": "Rate limit exceeded. Please try again later."}`
`incompleteDetails`	models.OpenAIResponsesIncompleteDetails	:heavy_check_mark:	N/A
`usage`	models.OpenResponsesUsage	:heavy_minus_sign:	Token usage information for the response	`{"input_tokens": 10,"output_tokens": 25,"total_tokens": 35,"input_tokens_details": {"cached_tokens": 0}`, “output_tokens_details”: `{"reasoning_tokens": 0}`, “cost”: 0.0012, “cost_details”: `{"upstream_inference_cost": null,"upstream_inference_input_cost": 0.0008,"upstream_inference_output_cost": 0.0004}` }
`maxToolCalls`	number	:heavy_minus_sign:	N/A
`topLogprobs`	number	:heavy_minus_sign:	N/A
`maxOutputTokens`	number	:heavy_minus_sign:	N/A
`temperature`	number	:heavy_check_mark:	N/A
`topP`	number	:heavy_check_mark:	N/A
`presencePenalty`	number	:heavy_check_mark:	N/A
`frequencyPenalty`	number	:heavy_check_mark:	N/A
`instructions`	models.OpenAIResponsesInputUnion	:heavy_check_mark:	N/A
`metadata`	`Record<string, string>`	:heavy_check_mark:	Metadata key-value pairs for the request. Keys must be ≤64 characters and cannot contain brackets. Values must be ≤512 characters. Maximum 16 pairs allowed.	`{"user_id": "123","session_id": "abc-def-ghi"}`
`tools`	models.OpenResponsesNonStreamingResponseToolUnion[]	:heavy_check_mark:	N/A
`toolChoice`	models.OpenAIResponsesToolChoiceUnion	:heavy_check_mark:	N/A
`parallelToolCalls`	boolean	:heavy_check_mark:	N/A
`prompt`	models.OpenAIResponsesPrompt	:heavy_minus_sign:	N/A
`background`	boolean	:heavy_minus_sign:	N/A
`previousResponseId`	string	:heavy_minus_sign:	N/A
`reasoning`	models.OpenAIResponsesReasoningConfig	:heavy_minus_sign:	N/A
`serviceTier`	models.OpenAIResponsesServiceTier	:heavy_minus_sign:	N/A
`store`	boolean	:heavy_minus_sign:	N/A
`truncation`	models.OpenAIResponsesTruncation	:heavy_minus_sign:	N/A
`text`	models.ResponseTextConfig	:heavy_minus_sign:	Text output configuration including format and verbosity	`{"format": {"type": "text"}`, “verbosity”: “medium” }

​Example Usage

​Fields

Example Usage

Fields