litellm - 💡(How to fix) Fix [Bug]: /v1/images/edits with mask fails — "Attempted to access streaming request content, without having called read()" [1 participants]

litellm2026-04-26 17:31:36

ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

GitHub issue URL

Helpful · Quick feedback

GitHub stats

BerriAI/litellm#26552•Fetched 2026-04-27 05:29:36

View on GitHub

Comments

Participants

Timeline

Reactions

Author

dawidkulpa

Participants

dawidkulpa

Timeline (top)

labeled ×3

Error Message

litellm.InternalServerError: InternalServerError: OpenAIException - Attempted to access streaming request content, without having called read().

Code Example

litellm.InternalServerError: InternalServerError: OpenAIException - Attempted to access streaming request content, without having called `read()`.

---

curl -X POST "https://<litellm-proxy>/v1/images/edits" \
  -H "Authorization: Bearer <api-key>" \
  -F "model=<openai-model-group>" \
  -F "[email protected]" \
  -F "[email protected]" \
  -F "prompt=Add a tree in the masked area" \
  -F "response_format=b64_json" \
  -F "size=1024x768"

---

{
  "model": "<openai-model-group>",
  "image": ["<_io.BytesIO object at 0x7fb36f41e6b0>"],
  "mask": ["<_io.BytesIO object at 0x7fb36f41d5d0>"],
  "prompt": "...(long prompt)...",
  "response_format": "b64_json",
  "size": "1024x768"
}

---

File "/app/.venv/lib/python3.13/site-packages/litellm/proxy/image_endpoints/endpoints.py", line 311, in image_edit_api
    return await processor.base_process_llm_request(
  File "/app/.venv/lib/python3.13/site-packages/litellm/proxy/common_request_processing.py", line 1068, in base_process_llm_request
    responses = await llm_responses
  File "/app/.venv/lib/python3.13/site-packages/litellm/router.py", line 5160, in async_wrapper
    return await self._ageneric_api_call_with_fallbacks(...)
  File "/app/.venv/lib/python3.13/site-packages/litellm/router.py", line 3810, in _ageneric_api_call_with_fallbacks
    raise e
  File "/app/.venv/lib/python3.13/site-packages/litellm/router.py", line 3797, in _ageneric_api_call_with_fallbacks
    response = await self.async_function_with_fallbacks(**kwargs)
  File "/app/.venv/lib/python3.13/site-packages/litellm/router.py", line 5634, in async_function_with_fallbacks
    return await self.async_function_with_fallbacks_common_utils(...)
  File "/app/.venv/lib/python3.13/site-packages/litellm/router.py", line 5591, in async_function_with_fallbacks_common_utils
    raise original_exception
  File "/app/.venv/lib/python3.13/site-packages/litellm/router.py", line 5549, in async_function_with_fallbacks_common_utils
    raise original_exception
  File "/app/.venv/lib/python3.13/site-packages/litellm/router.py", line 5625, in async_function_with_fallbacks
    response = await self.async_function_with_retries(*args, **kwargs)
  File "/app/.venv/lib/python3.13/site-packages/litellm/router.py", line 5888, in async_function_with_retries
    raise original_exception
  File "/app/.venv/lib/python3.13/site-packages/litellm/router.py", line 5817, in async_function_with_retries
    response = await self.make_call(original_function, *args, **kwargs)
  File "/app/.venv/lib/python3.13/site-packages/litellm/router.py", line 5899, in make_call
    response = await response
  File "/app/.venv/lib/python3.13/site-packages/litellm/router.py", line 3939, in _ageneric_api_call_with_fallbacks_helper
    raise e
  File "/app/.venv/lib/python3.13/site-packages/litellm/router.py", line 3925, in _ageneric_api_call_with_fallbacks_helper
    response = await response
  File "/app/.venv/lib/python3.13/site-packages/litellm/utils.py", line 2097, in wrapper_async
    raise e
  File "/app/.venv/lib/python3.13/site-packages/litellm/utils.py", line 1896, in wrapper_async
    result = await original_function(*args, **kwargs)
  File "/app/.venv/lib/python3.13/site-packages/litellm/images/main.py", line 1064, in aimage_edit
    raise litellm.exception_type(
        model=model, ...)
  File "/app/.venv/lib/python3.13/site-packages/litellm/litellm_core_utils/exception_mapping_utils.py", line 2456, in exception_type
    raise e
  File "/app/.venv/lib/python3.13/site-packages/litellm/litellm_core_utils/exception_mapping_utils.py", line 588, in exception_type
    raise InternalServerError(...)

RAW_BUFFERClick to expand / collapse

Check for existing issues

I have searched the existing issues and checked that my issue is not a duplicate.

What happened?

Sending a POST /v1/images/edits request with image, mask, prompt, size, and response_format through the LiteLLM proxy to an OpenAI model results in 500 with:

litellm.InternalServerError: InternalServerError: OpenAIException - Attempted to access streaming request content, without having called `read()`.

The request is well-formed multipart/form-data with a single image file and a single mask file (both PNG). The error occurs consistently on every retry (2 retries attempted).

This appears to be an httpx.RequestNotRead exception surfacing inside the image edit handler — the proxy seems to try accessing the streamed request body without calling .read() first.

Expected behavior: The proxy should forward the multipart form data to OpenAI's /v1/images/edits endpoint and return the edited image as b64_json.

Steps to Reproduce

curl -X POST "https://<litellm-proxy>/v1/images/edits" \
  -H "Authorization: Bearer <api-key>" \
  -F "model=<openai-model-group>" \
  -F "[email protected]" \
  -F "[email protected]" \
  -F "prompt=Add a tree in the masked area" \
  -F "response_format=b64_json" \
  -F "size=1024x768"

The client is a Node.js app using the Fetch API with FormData (undici). Single image, single mask, both sent as PNG blobs.

Request details from logs:

{
  "model": "<openai-model-group>",
  "image": ["<_io.BytesIO object at 0x7fb36f41e6b0>"],
  "mask": ["<_io.BytesIO object at 0x7fb36f41d5d0>"],
  "prompt": "...(long prompt)...",
  "response_format": "b64_json",
  "size": "1024x768"
}

Note: both image and mask are received as lists with a single BytesIO element each.

Relevant log output

File "/app/.venv/lib/python3.13/site-packages/litellm/proxy/image_endpoints/endpoints.py", line 311, in image_edit_api
    return await processor.base_process_llm_request(
  File "/app/.venv/lib/python3.13/site-packages/litellm/proxy/common_request_processing.py", line 1068, in base_process_llm_request
    responses = await llm_responses
  File "/app/.venv/lib/python3.13/site-packages/litellm/router.py", line 5160, in async_wrapper
    return await self._ageneric_api_call_with_fallbacks(...)
  File "/app/.venv/lib/python3.13/site-packages/litellm/router.py", line 3810, in _ageneric_api_call_with_fallbacks
    raise e
  File "/app/.venv/lib/python3.13/site-packages/litellm/router.py", line 3797, in _ageneric_api_call_with_fallbacks
    response = await self.async_function_with_fallbacks(**kwargs)
  File "/app/.venv/lib/python3.13/site-packages/litellm/router.py", line 5634, in async_function_with_fallbacks
    return await self.async_function_with_fallbacks_common_utils(...)
  File "/app/.venv/lib/python3.13/site-packages/litellm/router.py", line 5591, in async_function_with_fallbacks_common_utils
    raise original_exception
  File "/app/.venv/lib/python3.13/site-packages/litellm/router.py", line 5549, in async_function_with_fallbacks_common_utils
    raise original_exception
  File "/app/.venv/lib/python3.13/site-packages/litellm/router.py", line 5625, in async_function_with_fallbacks
    response = await self.async_function_with_retries(*args, **kwargs)
  File "/app/.venv/lib/python3.13/site-packages/litellm/router.py", line 5888, in async_function_with_retries
    raise original_exception
  File "/app/.venv/lib/python3.13/site-packages/litellm/router.py", line 5817, in async_function_with_retries
    response = await self.make_call(original_function, *args, **kwargs)
  File "/app/.venv/lib/python3.13/site-packages/litellm/router.py", line 5899, in make_call
    response = await response
  File "/app/.venv/lib/python3.13/site-packages/litellm/router.py", line 3939, in _ageneric_api_call_with_fallbacks_helper
    raise e
  File "/app/.venv/lib/python3.13/site-packages/litellm/router.py", line 3925, in _ageneric_api_call_with_fallbacks_helper
    response = await response
  File "/app/.venv/lib/python3.13/site-packages/litellm/utils.py", line 2097, in wrapper_async
    raise e
  File "/app/.venv/lib/python3.13/site-packages/litellm/utils.py", line 1896, in wrapper_async
    result = await original_function(*args, **kwargs)
  File "/app/.venv/lib/python3.13/site-packages/litellm/images/main.py", line 1064, in aimage_edit
    raise litellm.exception_type(
        model=model, ...)
  File "/app/.venv/lib/python3.13/site-packages/litellm/litellm_core_utils/exception_mapping_utils.py", line 2456, in exception_type
    raise e
  File "/app/.venv/lib/python3.13/site-packages/litellm/litellm_core_utils/exception_mapping_utils.py", line 588, in exception_type
    raise InternalServerError(...)

What part of LiteLLM is this about?

Proxy

What LiteLLM version are you on ?

v1.83.13-nightly

Twitter / LinkedIn details

No response

extent analysis

TL;DR

The issue can likely be fixed by calling .read() on the request body before accessing its content in the LiteLLM proxy.

Guidance

Verify that the image and mask files are being sent correctly as multipart/form-data in the request.
Check the LiteLLM proxy code to ensure that .read() is called on the request body before accessing its content.
Consider adding error handling to catch and handle httpx.RequestNotRead exceptions.
Review the request logging to confirm that the image and mask files are being received as expected.

Example

# Example of calling .read() on the request body
async def image_edit_api(request):
    # ...
    body = await request.read()
    # Process the request body
    # ...

Notes

The issue seems to be related to the LiteLLM proxy not calling .read() on the request body before accessing its content. This is a common issue when working with asynchronous requests. The provided log output and request details suggest that the issue is occurring in the image_edit_api function.

Recommendation

Apply a workaround by calling .read() on the request body before accessing its content. This should fix the issue and allow the LiteLLM proxy to correctly process the request.

Vote matrix · Quick signals

Works

Did the solution work? Tap to confirm.

Easy Fix

Was it a quick fix?

Time Saver

Did it save you time?

Blocking

Was it severely blocking?

Common Issue

Are others likely hitting this too?

Flaky / Intermittent

Is it intermittent?

Verified / Reproducible

Can you reproduce it reliably?

#api #file not found #serialization error #model compatibility #GPU setup

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Data

Security

Network

Code

UI/UX

Text

System

Multimedia

Protocol

API

Engineering

litellm - 💡(How to fix) Fix [Bug]: /v1/images/edits with mask fails — "Attempted to access streaming request content, without having called read()" [1 participants]

Recommended Tools

GitHub issue graph ai analysis

Error Message

Code Example

Check for existing issues

What happened?

Steps to Reproduce

Relevant log output

What part of LiteLLM is this about?

What LiteLLM version are you on ?

Twitter / LinkedIn details

extent analysis

TL;DR

Guidance

Example

Notes

Recommendation

Still need to ship something?

TRENDING

litellm - 💡(How to fix) Fix [Bug]: /v1/images/edits with mask fails — "Attempted to access streaming request content, without having called read()" [1 participants]

Recommended Tools

GitHub issue graph ai analysis

Error Message

Code Example

Check for existing issues

What happened?

Steps to Reproduce

Relevant log output

What part of LiteLLM is this about?

What LiteLLM version are you on ?

Twitter / LinkedIn details

extent analysis

TL;DR

Guidance

Example

Notes

Recommendation

Still need to ship something?

RELATED_DISCOVERY

TRENDING