200 OK from /v1/responses but body times out (UND_ERR_BODY_TIMEOUT)

API Bugs
,
1

I’m seeing a frequent failure when calling the Responses API that looks like a client-side body timeout even though the API returns 200 OK.

Stack

  • Node.js (v22, using built-in fetch and undici)

  • ai@6.0.7

  • @ai-sdk/openai@3.0.2

  • @ai-sdk/provider-utils@4.0.2

  • Model: gpt-5.2-2025-12-11

What happens

  • OpenAI responds with 200 OK

  • Headers arrive successfully

  • While reading the response body, undici aborts with BodyTimeoutError (UND_ERR_BODY_TIMEOUT)

  • The AI SDK then throws Failed to process successful response because the body is undefined

Key error excerpt

APICallError: Failed to process successful response
cause: TypeError: terminated
cause: BodyTimeoutError: Body Timeout Error (UND_ERR_BODY_TIMEOUT)

statusCode: 200
url: https://api.openai.com/v1/responses
responseBody: undefined

Response headers (partial)

content-type: application/json
transfer-encoding: chunked
openai-processing-ms: 2459
x-request-id: req_097e64f2e839478ebf5f2e737b1fad55

2 Likes
Agents SDK -> TypeError: terminated
2

I’m experiencing the same issue

1 Like
3

I’m shocked there aren’t any other posts about this yet - it’s been happening with alarming frequency. When did you start noticing issues?

1 Like
4

Just to confirm, what happens if you make a call to the OpenAI API using one of the official SDKs, or even a simple curl request?
I have not worked with the AI SDK yet. Is there a community where similar issues are being reported?

Regardless of the outcome, I will monitor the community to see if additional reports come in.

5

We have been facing something very similar when calling via OpenAI SDK itself.
response = client.responses.create(**request_params)
But the response is never received although HTTP 200 OK logs comes for the same.

1 Like
6

I’m raising this with the team so they can take a closer look. To help us escalate this properly, could you please confirm that you haven’t set unusually low timeout values on your side, and whether this is a new issue for you?

Thanks for your understanding. This information will make it easier to get the right attention on the problem, as these are among the first questions that will need to be answered anyway.

1 Like
7

Timeouts are set to default, and yes it’s a relatively new issue that became increasingly frequent over the past ~week. I should also note that I haven’t seen the error in the past 24 hours. This was an abrupt drop-off in errors, so something may have been fixed on OpenAI’s side?

1 Like
8

Thanks for following up. It’s good to hear that you’re not encountering the issue at the moment.

If this was a temporary problem, did you notice anything unusual in your account health dashboard that might indicate an issue?

I’ll continue to monitor the situation in case additional reports come in.

9

we’re also experiencing this issue — it’s been happening for a few weeks now, but was especially bad 2 days ago. In our traces the call to the openai sdk gets stuck indefinitely until it times out with the same error as OP.

1 Like
10

FYI @vb this error does appear to still be happening - I’m seeing a small spike from this morning

11

The team is actively investigating this. I cannot provide a timeline at this point, but if you have any additional information to share, please do so here or via a support ticket and reference this community topic.

Thank you, and I hope this is resolved soon.

2 Likes
12

Hey everyone, Apologies for the inconvenience. Our team is taking a look into this issue. We will provide an update as soon as we identify the issue. Thank you!

3 Likes
13

I suspect this is the underlying issue causing the error we’re seeing here because Agents SDK uses Responses API by default: