[GH-ISSUE #18713] issue: Open WebUI API returns null when using minimax-m2:cloud model despite model being listed #121993

Closed
opened 2026-05-21 00:17:10 -05:00 by GiteaMirror · 3 comments
Owner

Originally created by @CarlosNeuratek on GitHub (Oct 29, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/18713

Check Existing Issues

  • I have searched for any existing and/or related issues.
  • I have searched for any existing and/or related discussions.
  • I am using the latest version of Open WebUI.

Installation Method

Docker

Open WebUI Version

v0.6.34

Ollama Version (if applicable)

0.12.6

Operating System

mac Tahoe 26.0.1

Browser (if applicable)

No response

Confirmation

  • I have read and followed all instructions in README.md.
  • I am using the latest version of both Open WebUI and Ollama.
  • I have included the browser console logs.
  • I have included the Docker container logs.
  • I have provided every relevant configuration, setting, and environment variable used in my setup.
  • I have clearly listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc).
  • I have documented step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation. My steps:
  • Start with the initial platform/version/OS and dependencies used,
  • Specify exact install/launch/configure commands,
  • List URLs visited, user input (incl. example values/emails/passwords if needed),
  • Describe all options and toggles enabled or changed,
  • Include any files or environmental changes,
  • Identify the expected and actual result at each stage,
  • Ensure any reasonably skilled user can follow and hit the same issue.

Expected Behavior

List available models (shows minimax-m2:cloud exists)

curl -H "Authorization: Bearer YOUR_API_KEY"
http://localhost:3000/api/models

Attempt to use the model (Chat completion response with generated text)

curl -X POST http://localhost:3000/api/chat/completions
-H "Authorization: Bearer API_KEY"
-H "Content-Type: application/json"
-d '{
"model": "minimax-m2:cloud",
"messages": [{"role": "user", "content": "Hello"}],
"stream": false
}'

Actual Behavior

Attempt to use the model (returns null)

curl -X POST http://localhost:3000/api/chat/completions
-H "Authorization: Bearer API_KEY"
-H "Content-Type: application/json"
-d '{
"model": "minimax-m2:cloud",
"messages": [{"role": "user", "content": "Hello"}],
"stream": false
}'

Steps to Reproduce

Prerequisites:
Open WebUI running on http://localhost:3000
Valid API key obtained from Open WebUI settings
minimax-m2:cloud model present in Ollama

Steps:

List available models (shows minimax-m2:cloud exists)

curl -H "Authorization: Bearer YOUR_API_KEY"
http://localhost:3000/api/models

Attempt to use the model (returns null)

curl -X POST http://localhost:3000/api/chat/completions
-H "Authorization: Bearer YOUR_API_KEY"
-H "Content-Type: application/json"
-d '{
"model": "minimax-m2:cloud",
"messages": [{"role": "user", "content": "Hello"}],
"stream": false
}'

Logs & Screenshots

curl -X POST http://localhost:3000/api/chat/completions \
-H "Authorization: Bearer XXXXX"
-H "Content-Type: application/json"
-d '{"model": "minimax-m2:cloud", "messages": [{"role": "user", "content": "Hello"}]}'
null%

Additional Information

No response

Originally created by @CarlosNeuratek on GitHub (Oct 29, 2025). Original GitHub issue: https://github.com/open-webui/open-webui/issues/18713 ### Check Existing Issues - [x] I have searched for any existing and/or related issues. - [x] I have searched for any existing and/or related discussions. - [x] I am using the latest version of Open WebUI. ### Installation Method Docker ### Open WebUI Version v0.6.34 ### Ollama Version (if applicable) 0.12.6 ### Operating System mac Tahoe 26.0.1 ### Browser (if applicable) _No response_ ### Confirmation - [x] I have read and followed all instructions in `README.md`. - [x] I am using the latest version of **both** Open WebUI and Ollama. - [x] I have included the browser console logs. - [x] I have included the Docker container logs. - [x] I have **provided every relevant configuration, setting, and environment variable used in my setup.** - [x] I have clearly **listed every relevant configuration, custom setting, environment variable, and command-line option that influences my setup** (such as Docker Compose overrides, .env values, browser settings, authentication configurations, etc). - [x] I have documented **step-by-step reproduction instructions that are precise, sequential, and leave nothing to interpretation**. My steps: - Start with the initial platform/version/OS and dependencies used, - Specify exact install/launch/configure commands, - List URLs visited, user input (incl. example values/emails/passwords if needed), - Describe all options and toggles enabled or changed, - Include any files or environmental changes, - Identify the expected and actual result at each stage, - Ensure any reasonably skilled user can follow and hit the same issue. ### Expected Behavior # List available models (shows minimax-m2:cloud exists) curl -H "Authorization: Bearer YOUR_API_KEY" \ http://localhost:3000/api/models # Attempt to use the model (Chat completion response with generated text) curl -X POST http://localhost:3000/api/chat/completions \ -H "Authorization: Bearer API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "minimax-m2:cloud", "messages": [{"role": "user", "content": "Hello"}], "stream": false }' ### Actual Behavior # Attempt to use the model (returns null) curl -X POST http://localhost:3000/api/chat/completions \ -H "Authorization: Bearer API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "minimax-m2:cloud", "messages": [{"role": "user", "content": "Hello"}], "stream": false }' ### Steps to Reproduce Prerequisites: Open WebUI running on http://localhost:3000 Valid API key obtained from Open WebUI settings minimax-m2:cloud model present in Ollama Steps: # List available models (shows minimax-m2:cloud exists) curl -H "Authorization: Bearer YOUR_API_KEY" \ http://localhost:3000/api/models # Attempt to use the model (returns null) curl -X POST http://localhost:3000/api/chat/completions \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "minimax-m2:cloud", "messages": [{"role": "user", "content": "Hello"}], "stream": false }' ### Logs & Screenshots curl -X POST http://localhost:3000/api/chat/completions \ -H "Authorization: Bearer XXXXX" \ -H "Content-Type: application/json" \ -d '{"model": "minimax-m2:cloud", "messages": [{"role": "user", "content": "Hello"}]}' null% ### Additional Information _No response_
GiteaMirror added the bug label 2026-05-21 00:17:10 -05:00
Author
Owner

@rgaricano commented on GitHub (Oct 29, 2025):

hide your auth key!

The API KEY have to be OLLAMA's one (to use its cloud models), you can create it in https://ollama.com/settings/keys

<!-- gh-comment-id:3461498245 --> @rgaricano commented on GitHub (Oct 29, 2025): hide your auth key! The API KEY have to be OLLAMA's one (to use its cloud models), you can create it in https://ollama.com/settings/keys
Author
Owner

@CarlosNeuratek commented on GitHub (Oct 29, 2025):

Thanks @rgaricano, I forgot to remove it from the image.

I'm using two local models with Open WebUI on the same machine, same API key. One works via API, the other returns null.

curl -X POST http://localhost:3000/api/chat/completions
-H "Authorization: Bearer XXXX"
-H "Content-Type: application/json"
-d '{"model": "llama3.1:latest", "messages": [{"role": "user", "content": "Hello"}]}'

Result:
{"id":"llama3.1:latest-535c7799-90cb-4505-a309-4ad043948ea4","created":1761745278,"model":"llama3.1:latest","choices":[{"index":0,"logprobs":null,"finish_reason":"stop","message":{"role":"assistant","content":"Hello! How can I assist you today?"}}],"object":"chat.completion","usage":{"response_token/s":22.98,"prompt_token/s":11.37,"total_duration":2517144500,"load_duration":1110476709,"prompt_eval_count":11,"prompt_tokens":11,"prompt_eval_duration":967049208,"eval_count":10,"completion_tokens":10,"eval_duration":435087917,"approximate_total":"0h0m2s","total_tokens":21,"completion_tokens_details":{"reasoning_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}}}%

curl -X POST http://localhost:3000/api/chat/completions
-H "Authorization: Bearer XXXX"
-H "Content-Type: application/json"
-d '{"model": "minimax-m2:cloud", "messages": [{"role": "user", "content": "Hello"}]}'

Result:
null%

<!-- gh-comment-id:3461619817 --> @CarlosNeuratek commented on GitHub (Oct 29, 2025): Thanks @rgaricano, I forgot to remove it from the image. I'm using two local models with Open WebUI on the same machine, same API key. One works via API, the other returns null. curl -X POST http://localhost:3000/api/chat/completions \ -H "Authorization: Bearer XXXX" \ -H "Content-Type: application/json" \ -d '{"model": "llama3.1:latest", "messages": [{"role": "user", "content": "Hello"}]}' ✅ **Result:** {"id":"llama3.1:latest-535c7799-90cb-4505-a309-4ad043948ea4","created":1761745278,"model":"llama3.1:latest","choices":[{"index":0,"logprobs":null,"finish_reason":"stop","message":{"role":"assistant","content":"Hello! How can I assist you today?"}}],"object":"chat.completion","usage":{"response_token/s":22.98,"prompt_token/s":11.37,"total_duration":2517144500,"load_duration":1110476709,"prompt_eval_count":11,"prompt_tokens":11,"prompt_eval_duration":967049208,"eval_count":10,"completion_tokens":10,"eval_duration":435087917,"approximate_total":"0h0m2s","total_tokens":21,"completion_tokens_details":{"reasoning_tokens":0,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}}}% curl -X POST http://localhost:3000/api/chat/completions \ -H "Authorization: Bearer XXXX" \ -H "Content-Type: application/json" \ -d '{"model": "minimax-m2:cloud", "messages": [{"role": "user", "content": "Hello"}]}' ❌**Result:** **null%**
Author
Owner

@rgaricano commented on GitHub (Oct 29, 2025):

yes Carlos, but one is local served (llama3.1:latest) and the other is ollama's cloud served (minimax-m2:cloud).

<!-- gh-comment-id:3461742384 --> @rgaricano commented on GitHub (Oct 29, 2025): yes Carlos, but one is local served (llama3.1:latest) and the other is ollama's cloud served (minimax-m2:cloud).
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/open-webui#121993