Create a model response
Creates a model response. Provide text or image inputs to generate text or JSON outputs. Have the model call your own custom code or use built-in tools like web search or file search to use your own data as input for the model's response.
Request body
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.
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.
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.
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.
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.
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 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.
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', then the request will be processed with the Flex Processing service tier.
- To opt-in to 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.
- 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.
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. 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.
The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with conversation.
Whether to run the model response in the background. Learn more.
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.
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.
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).
Whether to allow the model to run tool calls in parallel.
Whether to store the generated model response for later retrieval via API.
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.
If set to true, the model response data will be streamed to the client as it is generated using server-sent events. See the Streaming section below for more information.
An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.
Response
OK
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.
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.
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.
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.
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.
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 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.
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', then the request will be processed with the Flex Processing service tier.
- To opt-in to 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.
- 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.
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. 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.
The unique ID of the previous response to the model. Use this to create multi-turn conversations. Learn more about conversation state. Cannot be used in conjunction with conversation.
Whether to run the model response in the background. Learn more.
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.
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.
Unique identifier for this Response.
The object type of this resource - always set to response.
The status of the response generation. One of completed, failed, in_progress, cancelled, queued, or incomplete.
Unix timestamp (in seconds) of when this Response was created.
Unix timestamp (in seconds) of when this Response was completed. Only present when the status is completed.
SDK-only convenience property that contains the aggregated text output from all output_text items in the output array, if any are present. Supported in the Python and JavaScript SDKs.
Whether to allow the model to run tool calls in parallel.
An upper bound for the number of tokens that can be generated for a response, including visible output tokens and reasoning tokens.