github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 00:51:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #13715] 404 not found when using OpenAI responses API https://api.openai.com/v1/models/{model} #55505

New Issue
Open
opened 2026-04-29 09:18:31 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-29 09:18:31 -05:00
Owner
Copy Link

Originally created by @Fitmtfk on GitHub (Jan 14, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/13715

What is the issue?

Image get https://api.openai.com/v1/models/{model}： This API does not support models whose IDs contain a slash (/).

I simply followed the 'How to use from Ollama' on the huggingface website.
ollama run hf.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:Q4_K_M
ok it works.However, the model ID is 'hf.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:Q4_K_M', which contains /.

get https://api.openai.com/v1/models works well.It returned all the models.

But get https://api.openai.com/v1/models/{model} connot support some of them.

Relevant log output

❯ curl http://127.0.0.1:11434/v1/models
{"object":"list","data":[{"id":"hf.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:Q4_K_M","object":"model","created":1768216671,"owned_by":"unsloth"},{"id":"qwen3:30b","object":"model","created":1767370296,"owned_by":"library"}]}

❯ curl http://127.0.0.1:11434/v1/models/qwen3:30b
{"id":"qwen3:30b","object":"model","created":1767370296,"owned_by":"library"}

❯ curl http://127.0.0.1:11434/v1/models/hf.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:Q4_K_M
404 page not found
-----------------------------------------------------------------------------------
[GIN] 2026/01/14 - 21:45:33 | 200 |       503.5µs |       127.0.0.1 | GET      "/v1/models"
[GIN] 2026/01/14 - 21:45:37 | 200 |     48.8032ms |       127.0.0.1 | GET      "/v1/models/qwen3:30b"
[GIN] 2026/01/14 - 21:45:41 | 404 |            0s |       127.0.0.1 | GET      "/v1/models/hf.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:Q4_K_M"

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @Fitmtfk on GitHub (Jan 14, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/13715 ### What is the issue? <img width="1647" height="360" alt="Image" src="https://github.com/user-attachments/assets/020253dd-1130-44ae-98ba-4dc40e545366" /> get https://api.openai.com/v1/models/{model}： This API does not support models whose IDs contain a slash (/). I simply followed the 'How to use from Ollama' on the huggingface website. ollama run hf.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:Q4_K_M ok it works.However, the model ID is 'hf.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:Q4_K_M', which contains /. get https://api.openai.com/v1/models works well.It returned all the models. But get https://api.openai.com/v1/models/{model} connot support some of them. ### Relevant log output ```shell ❯ curl http://127.0.0.1:11434/v1/models {"object":"list","data":[{"id":"hf.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:Q4_K_M","object":"model","created":1768216671,"owned_by":"unsloth"},{"id":"qwen3:30b","object":"model","created":1767370296,"owned_by":"library"}]} ❯ curl http://127.0.0.1:11434/v1/models/qwen3:30b {"id":"qwen3:30b","object":"model","created":1767370296,"owned_by":"library"} ❯ curl http://127.0.0.1:11434/v1/models/hf.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:Q4_K_M 404 page not found ----------------------------------------------------------------------------------- [GIN] 2026/01/14 - 21:45:33 | 200 | 503.5µs | 127.0.0.1 | GET "/v1/models" [GIN] 2026/01/14 - 21:45:37 | 200 | 48.8032ms | 127.0.0.1 | GET "/v1/models/qwen3:30b" [GIN] 2026/01/14 - 21:45:41 | 404 | 0s | 127.0.0.1 | GET "/v1/models/hf.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:Q4_K_M" ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-29 09:18:31 -05:00
GiteaMirror commented 2026-04-29 09:18:33 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 14, 2026):

$ ollama cp hf.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:Q4_K_M qwen3-coder:30b-a3b-instruct-1m-q4_K_M
$ curl http://127.0.0.1:11434/v1/models/qwen3-coder:30b-a3b-instruct-1m-q4_K_M
{"id":"qwen3-coder:30b-a3b-instruct-1m-q4_K_M","object":"model","created":1768411708,"owned_by":"library"}
<!-- gh-comment-id:3750715665 --> @rick-github commented on GitHub (Jan 14, 2026): ```console $ ollama cp hf.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:Q4_K_M qwen3-coder:30b-a3b-instruct-1m-q4_K_M $ curl http://127.0.0.1:11434/v1/models/qwen3-coder:30b-a3b-instruct-1m-q4_K_M {"id":"qwen3-coder:30b-a3b-instruct-1m-q4_K_M","object":"model","created":1768411708,"owned_by":"library"} ```
GiteaMirror commented 2026-04-29 09:18:34 -05:00
Author
Owner
Copy Link

@Sekousuke commented on GitHub (Jan 14, 2026):

$ ollama cp hf.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:Q4_K_M qwen3-coder:30b-a3b-instruct-1m-q4_K_M
$ curl http://127.0.0.1:11434/v1/models/qwen3-coder:30b-a3b-instruct-1m-q4_K_M
{"id":"qwen3-coder:30b-a3b-instruct-1m-q4_K_M","object":"model","created":1768411708,"owned_by":"library"}

Hi @rick-github, I've submitted a PR #13716 to directly fix this issue. It enables the /v1/models/*model wildcard route, so nested model names (e.g., the HuggingFace model) can be used directly without manual renaming. Looking forward to your review!

<!-- gh-comment-id:3752122142 --> @Sekousuke commented on GitHub (Jan 14, 2026): > $ ollama cp hf.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-1M-GGUF:Q4_K_M qwen3-coder:30b-a3b-instruct-1m-q4_K_M > $ curl http://127.0.0.1:11434/v1/models/qwen3-coder:30b-a3b-instruct-1m-q4_K_M > {"id":"qwen3-coder:30b-a3b-instruct-1m-q4_K_M","object":"model","created":1768411708,"owned_by":"library"} Hi @rick-github, I've submitted a PR #13716 to directly fix this issue. It enables the `/v1/models/*model` wildcard route, so nested model names (e.g., the `HuggingFace` model) can be used directly without manual renaming. Looking forward to your review!
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
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#55505
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?