I would like to use the responses API so that it is stateless and to re-use the reasoning tokens. With this code: rsp = openai_client.responses.create( model='o4-mini', input=messages, store=False, tool_choice='none', include=['reasoning.encrypted_content'] …

Basically, you take the reasoning element in the response.output and pass it as a json to the already existing conversation. In this example I just tossed the entire output as the python SDK can handle it, but if you need to do a REST request you must use an equivalent JSON. ▶ Here is a short examp…

This seems closer: prev_reasoning = rsp.reasoning and then: rsp = openai_client.responses.create( model='o4-mini', input=messages, store=False, tool_choice='none', include=['reasoning.encrypted_content'], reasoning=prev_reasoning ) No errors, but t…

This is what messages looks like: messages = [ {'role': 'system', 'content': sys_prompt}, {'role': 'user', 'content': user_prompt} ] I also tried prev_reasoning = rsp.reasoning messages.append({'role': 'reasoning', 'content': prev_reasoning}) That role is not all…

You will see that the tree of input items in the API reference for “input” splits between “input message” and merely “context item”. Despite that the assistant produces something like reasoning or tool calls at the same time that it can produce a response to a user, it is being delivered in another…

prev_reasoning = rsp.reasoning messages.append(prev_reasoning) This is my best understanding of your message, but that gives an error.

The API reference, again, shows you the type of reasoning object that must be passed back… This is INPUT: <a class="lightbox" href="https://us1.discourse-cdn.com/openai1/original/4X/8/b/c/8bc0ed3dc7304bd5e81c4d483c04de7374de0405.png" data-download-href="/uploads/short-url/jWjI8TE5KY49iCDW7g0utOPEC69.png?dl=1" title="The image shows documentation describing the properties of a 'Reasoning' object used in a function tool call output, detailing required and optional fields such as id, summary, type, encrypted_content, and status. (Captioned by AI)">[The image shows documentation describing the properties of a 'Reasoning' object used in a function tool call output, detailing required and optional fields such as id, summary, type, encrypt…

Thank you! This is really helpful! I was thinking that the encrypted reasoning would include some representation of the state so that you wouldn’t need to add the previous agent response, but it looks like you need to include both.

Yeah, since we are going stateless it seems to contain the full reasoning, but encrypted to prevent other companies to distill the model.

Note it is not documented anywhere, but the API is super particular. You need to maintain the exact shape you got including ids of both the reasoning and message and summary. Otherwise you get stuff like: {“error”: {“message”: “Item ‘rs_07db81b90333bde7006916cd15d23c81a2b6af8999a6235a7b’ of type ‘…

[image] sam.saffron: here it looks like you need to provide exact copies. Thanks for an interesting observation. In your error, I wonder what “following item” is supposed to be referring to, as an “rs_” ID is for an entire reasoning container, which can have multiple array items inside. “Fol…

How to use reasoning.encrypted_content with store=False (stateless)

API

_j June 13, 2025, 2:39am 2

Follow the API reference for Responses.

Expand this tree:

input → input item list (array) → item → reasoning → encrypted_content

Topic		Replies	Views
Does the responses API need reasoning summary from previous calls? API api	1	279	March 2, 2026
Requests API does not support manual context management? API api	1	293	May 26, 2025
Clarifications on `encrypted_content` usage pattern and impact API reasoning	3	2430	September 5, 2025
How stateless is reasoning.encrypted_content? API responses-api	2	367	January 13, 2026
Better performance from reasoning models using the Responses API (cookbook) Documentation responses-api	1	714	May 14, 2025

How to use reasoning.encrypted_content with store=False (stateless)

Related topics