POST
POST /responses?beta=true — OpenAI API
Beta
OpenAI API key (required); https://api.openai.com/v1
OpenAI APICreate a model response
- Base URL
- https://api.openai.com/v1
- Auth
- Authorization: Bearer <OPENAI_API_KEY>
- Last verified
- 2026-10-20 · upstream hash matched
Actions Try in browser→
Agents: curl -H "Accept: text/markdown" this URL
→ 431 tokens · Vary: Accept
→ 431 tokens · Vary: Accept
Critical gotchas
The Responses API is the primary interface for new text and tool workflows; Chat Completions remains a separate compatibility API.
Audio transcription uploads use multipart form data rather than a JSON request body.
cURL
curl -X POST 'https://api.openai.com/v1/responses?beta=true' \ -H "Authorization: Bearer $OPENAI_API_KEY" \ -H 'Content-Type: application/json' \ -H 'openai-beta: responses_multi_agent=v1' \ -d '{}'
Parameters
| Name | In | Type | Required | Description |
|---|---|---|---|---|
| metadata | body | object | No | Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters. |
| top_logprobs | body | integer | No | An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested. |
| temperature | body | number | No | What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. |
| top_p | body | number | No | An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both. |
| user | body | string | No | This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use `prompt_cache_key` instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. [Learn more](https://developers.openai.com/api/docs/guides/safety-best-practices#implement-safety-identifiers). |
| safety_identifier | body | string | No | A stable identifier used to help detect users of your application that may be violating OpenAI's usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 128 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. [Learn more](https://developers.openai.com/api/docs/guides/safety-best-practices#implement-safety-identifiers). |
| prompt_cache_key | body | string | No | Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the `user` field. [Learn more](https://developers.openai.com/api/docs/guides/prompt-caching). |
| prompt_cache_retention | body | string | No | Deprecated. Use `prompt_cache_options.ttl` instead. The retention policy for the prompt cache. Set to `24h` to enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. [Learn more](https://developers.openai.com/api/docs/guides/prompt-caching#prompt-cache-retention). This field expresses a maximum retention policy, while `prompt_cache_options.ttl` expresses a minimum cache lifetime. The two fields are independent and do not interact. For `gpt-5.5`, `gpt-5.5-pro`, and future models, only `24h` is supported. For older models that support both `in_memory` and `24h`, the default depends on your organization's data retention policy: - Organizations without ZDR enabled default to `24h`. - Organizations with ZDR enabled default to `in_memory` when `prompt_cache_retention` is not specified. |
| prompt_cache_options | body | object | No | 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](https://developers.openai.com/api/docs/guides/prompt-caching) for current details. |
| previous_response_id | body | string | No | The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about [conversation state](https://developers.openai.com/api/docs/guides/conversation-state). Cannot be used in conjunction with `conversation`. |
| model | body | string | No | Request body field model. |
| background | body | boolean | No | Whether to run the model response in the background. [Learn more](https://developers.openai.com/api/docs/guides/background). |
| max_tool_calls | body | integer | No | The maximum number of total calls to built-in tools that can be processed in a response. This maximum number applies across all built-in tool calls, not per individual tool. Any further attempts to call a tool by the model will be ignored. |
| text | body | object | No | Configuration options for a text response from the model. Can be plain text or structured JSON data. Learn more: - [Text inputs and outputs](https://developers.openai.com/api/docs/guides/text) - [Structured Outputs](https://developers.openai.com/api/docs/guides/structured-outputs) |
| tools | body | object[] | No | An array of tools the model may call while generating a response. You can specify which tool to use by setting the `tool_choice` parameter. We support the following categories of tools: - **Built-in tools**: Tools that are provided by OpenAI that extend the model's capabilities, like [web search](https://developers.openai.com/api/docs/guides/tools-web-search) or [file search](https://developers.openai.com/api/docs/guides/tools-file-search). Learn more about [built-in tools](https://developers.openai.com/api/docs/guides/tools). - **MCP Tools**: Integrations with third-party systems via custom MCP servers or predefined connectors such as Google Drive and SharePoint. Learn more about [MCP Tools](https://developers.openai.com/api/docs/guides/tools-connectors-mcp). - **Function calls (custom tools)**: Functions that are defined by you, enabling the model to call your own code with strongly typed arguments and outputs. Learn more about [function calling](https://developers.openai.com/api/docs/guides/function-calling). You can also use custom tools to call your own code. |
| tool_choice | body | string | No | How the model should select which tool (or tools) to use when generating a response. See the `tools` parameter to see how to specify which tools the model can call. |
| prompt | body | object | No | Reference to a prompt template and its variables. [Learn more](https://developers.openai.com/api/docs/guides/text?api-mode=responses#version-prompts-in-code). |
| access_programs | body | object | No | Domain-specific access programs to use for this request. |
| service_tier | body | string | No | Specifies the processing type used for serving the request. - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'. - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model. - If set to '[flex](https://developers.openai.com/api/docs/guides/flex-processing)', then the request will be processed with the Flex Processing service tier. - To opt-in to [Fast mode](https://developers.openai.com/api/docs/guides/fast-mode) at the request level, include the `service_tier=fast` or `service_tier=priority` parameter for Responses or Chat Completions. The response will show `service_tier=priority` regardless of if you specify `service_tier=fast` or `priority` in your request. - If set to 'ultrafast', then the request will be processed with the access-controlled Ultrafast Processing service tier. This tier is currently available for `gpt-5.6-sol`; a response served through it will show `service_tier=ultrafast`. - When not set, the default behavior is 'auto'. When the `service_tier` parameter is set, the response body will include the `service_tier` value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter. |
| truncation | body | string | No | The truncation strategy to use for the model response. - `auto`: If the input to this Response exceeds the model's context window size, the model will truncate the response to fit the context window by dropping items from the beginning of the conversation. - `disabled` (default): If the input size will exceed the context window size for a model, the request will fail with a 400 error. |
| reasoning | body | object | No | Configuration options for [reasoning models](https://developers.openai.com/api/docs/guides/reasoning). |
| input | body | string | No | Text, image, or file inputs to the model, used to generate a response. Learn more: - [Text inputs and outputs](https://developers.openai.com/api/docs/guides/text) - [Image inputs](https://developers.openai.com/api/docs/guides/images-vision) - [File inputs](https://developers.openai.com/api/docs/guides/file-inputs) - [Conversation state](https://developers.openai.com/api/docs/guides/conversation-state) - [Function calling](https://developers.openai.com/api/docs/guides/function-calling) |
| include | body | string[] | No | Specify additional output data to include in the model response. Currently supported values are: - `web_search_call.action.sources`: Include the sources of the web search tool call. - `code_interpreter_call.outputs`: Includes the outputs of python code execution in code interpreter tool call items. - `computer_call_output.output.image_url`: Include image urls from the computer call output. - `file_search_call.results`: Include the search results of the file search tool call. - `message.input_image.image_url`: Include image urls from the input message. - `message.output_text.logprobs`: Include logprobs with assistant messages. - `reasoning.encrypted_content`: Includes an encrypted version of reasoning tokens in reasoning item outputs. This enables reasoning items to be used in multi-turn conversations when using the Responses API statelessly (like when the `store` parameter is set to `false`, or when an organization is enrolled in the zero data retention program). |
| parallel_tool_calls | body | boolean | No | Whether to allow the model to run tool calls in parallel. |
| store | body | boolean | No | Whether to store the generated model response for later retrieval via API. Defaults to true when omitted. If set to true, response data will be stored for at least 30 days, subject to the [data retention exceptions](https://developers.openai.com/api/docs/guides/your-data#v1responses). |
| instructions | body | string | No | A system (or developer) message inserted into the model's context. When using along with `previous_response_id`, the instructions from a previous response will not be carried over to the next response. This makes it simple to swap out system (or developer) messages in new responses. |
| moderation | body | object | No | Configuration for running moderation on the input and output of this response. |
| stream | body | boolean | No | If set to true, the model response data will be streamed to the client as it is generated using [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format). See the [Streaming section below](https://developers.openai.com/api/reference/resources/responses/streaming-events) for more information. |
| stream_options | body | object | No | Options for streaming responses. Only set this when you set `stream: true`. |
| conversation | body | string | No | The conversation that this response belongs to. Items from this conversation are prepended to `input_items` for this response request. Input items and output items from this response are automatically added to this conversation after this response completes. |
| context_management | body | object[] | No | Context management configuration for this request. |
| max_output_tokens | body | integer | No | An upper bound for the number of tokens that can be generated for a response, including visible output tokens and [reasoning tokens](https://developers.openai.com/api/docs/guides/reasoning). |
| multi_agent | body | object | No | Configuration for server-hosted multi-agent execution. |
Response 200 OK
{
"metadata": {},
"top_logprobs": 0,
"temperature": 1,
"top_p": 1,
"user": "user-1234",
"safety_identifier": "safety-identifier-1234",
"prompt_cache_key": "prompt-cache-key-1234",
"prompt_cache_retention": "in_memory",
"previous_response_id": "string",
"model": "gpt-6-astra",
"background": false,
"max_tool_calls": 0,
"text": {
"format": {
"type": "text"
},
"verbosity": "medium"
},
"tools": [
{
"type": "function",
"name": "string",
"async": true,
"description": "string",
"parameters": {},
"output_schema": {},
"strict": true,
"defer_loading": true,
"allowed_callers": [
"direct"
]
}
],
"tool_choice": "none",
"prompt": {
"id": "string",
"version": "string",
"variables": {}
},
"service_tier": "auto",
"truncation": "disabled",
"id": "string",
"object": "response",
"status": "completed",
"access_programs": {
"cyber": "standard"
},
"created_at": 0,
"completed_at": 0,
"error": {
"type": "string",
"param": "string",
"code": "server_error",
"message": "string",
"misalignment": {
"review_target": "string",
"error_type": "string",
"detailed_explanation": "string",
"steer": {
"message": "string"
}
}
},
"incomplete_details": {
"reason": "max_output_tokens"
},
"output": [
{
"agent": {
"agent_name": "string"
},
"id": "string",
"type": "message",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "string",
"annotations": [
"[recursive or deeply nested schema]"
],
"logprobs": [
"[recursive or deeply nested schema]"
]
}
],
"phase": "commentary",
"status": "in_progress"
}
],
"reasoning": {
"mode": "string",
"effort": "medium",
"summary": "auto",
"context": "auto",
"generate_summary": "auto"
},
"instructions": "string",
"output_text": "string",
"usage": {
"input_tokens": 0,
"input_tokens_details": {
"cached_tokens": 0,
"cache_write_tokens": 0
},
"output_tokens": 0,
"output_tokens_details": {
"reasoning_tokens": 0
},
"total_tokens": 0
},
"prompt_cache_options": {
"ttl": "30m",
"mode": "implicit",
"comparison_response_id": "string"
},
"prompt_cache_diagnostics": {
"type": "cache_miss",
"reason": "model_changed",
"cache_missed_tokens": 0,
"comparison_reusable_tokens": 0
},
"moderation": {
"input": {
"type": "moderation_result",
"model": "string",
"flagged": true,
"categories": {},
"category_scores": {},
"category_applied_input_types": {}
},
"output": {
"type": "moderation_result",
"model": "string",
"flagged": true,
"categories": {},
"category_scores": {},
"category_applied_input_types": {}
}
},
"parallel_tool_calls": true,
"conversation": {
"id": "string"
},
"max_output_tokens": 0
} Get a free OpenAI API key → sponsored Affiliate link - we may earn a commission, at no extra cost to you.