A list of one or many input items to the model, containing different content types.
A message input to the model with a role indicating instruction following
hierarchy. Instructions given with the developer or system role take
precedence over instructions given with the user role. Messages with the
assistant role are presumed to have been generated by the model in previous
interactions.
Text, image, or audio input to the model, used to generate a response. Can also contain previous assistant responses.
A list of one or many input items to the model, containing different content types.
An image input to the model. Learn about image inputs.
A file input to the model.
The detail level of the file to be sent to the model. Use auto to let the system select the detail level; for GPT-5.6 and later models, auto uses high-quality rendering, which may increase input token usage. Use low for lower-cost rendering, or high to render the file at higher quality. Defaults to auto.
The role of the message input. One of user, assistant, system, or
developer.
Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer).
For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend
phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
A message input to the model with a role indicating instruction following
hierarchy. Instructions given with the developer or system role take
precedence over instructions given with the user role.
A list of one or many input items to the model, containing different content types.
An image input to the model. Learn about image inputs.
A file input to the model.
The detail level of the file to be sent to the model. Use auto to let the system select the detail level; for GPT-5.6 and later models, auto uses high-quality rendering, which may increase input token usage. Use low for lower-cost rendering, or high to render the file at higher quality. Defaults to auto.
An output message from the model.
The content of the output message.
A text output from the model.
The annotations of the text output.
A citation for a web resource used to generate a model response.
The status of the message input. One of in_progress, completed, or
incomplete. Populated when input items are returned via API.
Labels an assistant message as intermediate commentary (commentary) or the final answer (final_answer).
For models like gpt-5.3-codex and beyond, when sending follow-up requests, preserve and resend
phase on all assistant messages — dropping it can degrade performance. Not used for user messages.
The results of a file search tool call. See the file search guide for more information.
The status of the file search tool call. One of in_progress,
searching, incomplete or failed,
The results of the file search tool call.
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, booleans, or numbers.
A tool call to a computer use tool. See the computer use guide for more information.
The pending safety checks for the computer call.
The status of the item. One of in_progress, completed, or
incomplete. Populated when items are returned via API.
A click action.
A click action.
A drag action.
Flattened batched actions for computer_use. Each action includes an
type discriminator and action-specific fields.
A click action.
A drag action.
The output of a computer tool call.
The results of a web search tool call. See the web search guide for more information.
An object describing the specific action taken in this web search call. Includes details on how the model used the web (search, open_page, find_in_page).
A tool call to run a function. See the function calling guide for more information.
The output of a function tool call.
Text, image, or file output of the function tool call.
An array of content outputs (text, image, file) for the function tool call.
A text input to the model.
An image input to the model. Learn about image inputs
A file input to the model.
The detail level of the file to be sent to the model. Use auto to let the system select the detail level; for GPT-5.6 and later models, auto uses high-quality rendering, which may increase input token usage. Use low for lower-cost rendering, or high to render the file at higher quality. Defaults to auto.
The unique ID of the function tool call output. Populated when this item is returned via API.
A message routed between agents.
Plaintext, image, or encrypted content sent between agents.
A text input to the model.
An image input to the model. Learn about image inputs
The multi-agent action that produced this result.
Text output returned by the multi-agent action.
Citations associated with the text content.
An update to the conversation’s response configuration. The configuration remains in effect for subsequent responses until it is replaced by another configuration update.
A description of the chain of thought used by a reasoning model while generating
a response. Be sure to include these items in your input to the Responses API
for subsequent turns of a conversation if you are manually
managing context.
A compaction item generated by the v1/responses/compact API.
An image generation request made by the model.
A tool call to run code.
A tool call to run a command on the local shell.
A tool representing a request to execute one or more shell commands.
The streamed output items emitted by a shell tool call.
A tool call representing a request to create, delete, or update files using diff patches.
The streamed output emitted by an apply patch tool call.
A request for human approval of a tool invocation.
A response to an MCP approval request.
The output of a custom tool call from your code, being sent back to the model.