github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #12694] Incorrect content type in cloud-hosted models #8422

New Issue
Closed
opened 2026-04-12 21:05:34 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-12 21:05:34 -05:00
Owner
Copy Link

Originally created by @pljones on GitHub (Oct 19, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12694

What is the issue?

Hi,

I'm accessing Ollama remotely through API calls. I'm seeing an error in the Open WebUI log and I can reproduce it using curl (see relevant log output).

The API requests Content-Type: application/json but Ollama is responding with a Content-Type: text/plain; charset=utf-8 header in certain circumstances.

I've done only two tests: deepseek-v3.1:671b-cloud (i.e. an Ollama cloud-hosted model) and mistral:7b (i.e. an unrelated locally hosted model).

I've not investigated the source at all to see if I can see where this is happening.

(The error from Open WebUI's perspective appears to cause it to fail to set a useful chat title and it won't create chat prompts.)

Thanks,

-- Peter

Relevant log output

---- REMOTE MODEL ----
$ curl -X POST http://X.X.X.X:11434/api/chat   -H "Content-Type: application/json"   -d '{
    "model": "deepseek-v3.1:671b-cloud",
    "messages": [{"role": "user", "content": "Test message"}],
    "stream": false
  }' -v
Note: Unnecessary use of -X or --request, POST is already inferred.
*   Trying X.X.X.X:11434...
* Connected to X.X.X.X (X.X.X.X) port 11434
> POST /api/chat HTTP/1.1
> Host: X.X.X.X:11434
> User-Agent: curl/8.5.0
> Accept: */*
> Content-Type: application/json
> Content-Length: 129
>
< HTTP/1.1 200 OK
< Date: Sun, 19 Oct 2025 17:21:02 GMT
< Content-Type: text/plain; charset=utf-8
< Transfer-Encoding: chunked
<
{"model":"deepseek-v3.1:671b-cloud","remote_model":"deepseek-v3.1:671b","remote_host":"https://ollama.com:443","created_at":"2025-10-19T17:21:26.853081314Z","message":{"role":"assistant","content":"Hello! I received your test message. 😊 \n\nHow can I help you today? Whether you have questions, need assistance with something, or just want to chat, I'm here for you!"},"done":true,"done_reason":"stop","total_duration":3739430136,"prompt_eval_count":6,"eval_count":41}


---- LOCAL MODEL ----
$ curl -X POST http://X.X.X.X:11434/api/chat   -H "Content-Type: application/json"   -d '{
    "model": "mistral:7b",
    "messages": [{"role": "user", "content": "Test message"}],
    "stream": false
  }' -v
Note: Unnecessary use of -X or --request, POST is already inferred.
*   Trying X.X.X.X:11434...
* Connected to X.X.X.X (X.X.X.X) port 11434
> POST /api/chat HTTP/1.1
> Host: X.X.X.X:11434
> User-Agent: curl/8.5.0
> Accept: */*
> Content-Type: application/json
> Content-Length: 115
>
< HTTP/1.1 200 OK
< Content-Type: application/json; charset=utf-8
< Date: Sun, 19 Oct 2025 17:26:54 GMT
< Content-Length: 494
<
* Connection #0 to host X.X.X.X left intact
{"model":"mistral:7b","created_at":"2025-10-19T17:26:54.4666709Z","message":{"role":"assistant","content":" Hello! Your test message has been received. Is there anything specific you would like to discuss or ask about? I'm here to help with your questions and provide information on a wide range of topics."},"done":true,"done_reason":"stop","total_duration":44941127400,"load_duration":17435800,"prompt_eval_count":6,"prompt_eval_duration":107990000,"eval_count":42,"eval_duration":3844336200}

OS

Windows

GPU

No response

CPU

AMD

Ollama version

0.12.6

Originally created by @pljones on GitHub (Oct 19, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12694 ### What is the issue? Hi, I'm accessing Ollama remotely through API calls. I'm seeing an error in the Open WebUI log and I can reproduce it using `curl` (see relevant log output). The API requests `Content-Type: application/json` but Ollama is responding with a `Content-Type: text/plain; charset=utf-8` header in certain circumstances. I've done only two tests: `deepseek-v3.1:671b-cloud` (i.e. an [Ollama cloud](https://ollama.com/blog/cloud-models)-hosted model) and `mistral:7b` (i.e. an unrelated locally hosted model). I've not investigated the source at all to see if I can see where this is happening. (The error from Open WebUI's perspective appears to cause it to fail to set a useful chat title and it won't create chat prompts.) Thanks, -- Peter ### Relevant log output ```shell ---- REMOTE MODEL ---- $ curl -X POST http://X.X.X.X:11434/api/chat -H "Content-Type: application/json" -d '{ "model": "deepseek-v3.1:671b-cloud", "messages": [{"role": "user", "content": "Test message"}], "stream": false }' -v Note: Unnecessary use of -X or --request, POST is already inferred. * Trying X.X.X.X:11434... * Connected to X.X.X.X (X.X.X.X) port 11434 > POST /api/chat HTTP/1.1 > Host: X.X.X.X:11434 > User-Agent: curl/8.5.0 > Accept: */* > Content-Type: application/json > Content-Length: 129 > < HTTP/1.1 200 OK < Date: Sun, 19 Oct 2025 17:21:02 GMT < Content-Type: text/plain; charset=utf-8 < Transfer-Encoding: chunked < {"model":"deepseek-v3.1:671b-cloud","remote_model":"deepseek-v3.1:671b","remote_host":"https://ollama.com:443","created_at":"2025-10-19T17:21:26.853081314Z","message":{"role":"assistant","content":"Hello! I received your test message. 😊 \n\nHow can I help you today? Whether you have questions, need assistance with something, or just want to chat, I'm here for you!"},"done":true,"done_reason":"stop","total_duration":3739430136,"prompt_eval_count":6,"eval_count":41} ---- LOCAL MODEL ---- $ curl -X POST http://X.X.X.X:11434/api/chat -H "Content-Type: application/json" -d '{ "model": "mistral:7b", "messages": [{"role": "user", "content": "Test message"}], "stream": false }' -v Note: Unnecessary use of -X or --request, POST is already inferred. * Trying X.X.X.X:11434... * Connected to X.X.X.X (X.X.X.X) port 11434 > POST /api/chat HTTP/1.1 > Host: X.X.X.X:11434 > User-Agent: curl/8.5.0 > Accept: */* > Content-Type: application/json > Content-Length: 115 > < HTTP/1.1 200 OK < Content-Type: application/json; charset=utf-8 < Date: Sun, 19 Oct 2025 17:26:54 GMT < Content-Length: 494 < * Connection #0 to host X.X.X.X left intact {"model":"mistral:7b","created_at":"2025-10-19T17:26:54.4666709Z","message":{"role":"assistant","content":" Hello! Your test message has been received. Is there anything specific you would like to discuss or ask about? I'm here to help with your questions and provide information on a wide range of topics."},"done":true,"done_reason":"stop","total_duration":44941127400,"load_duration":17435800,"prompt_eval_count":6,"prompt_eval_duration":107990000,"eval_count":42,"eval_duration":3844336200} ``` ### OS Windows ### GPU _No response_ ### CPU AMD ### Ollama version 0.12.6
GiteaMirror added the cloudbug labels 2026-04-12 21:05:34 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug cloud
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#8422
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?