LM Studio Failure to refresh models

I'm running LM Studio locally and I've found that if I add/remove models in LM Studio the list of models in opencode isn't getting refreshed even if I do an auth logout auth login cycle, is there a quick way to fix this?

Removing the model cache file in ~/.cache/opencode/models.json also did not help this issue

I think I am gonna have to install LM Studio to see what you mean (never used it)

I'm not sure it's an issue with the LM Studio exactly it's more an issue with how refreshing the models cache works - it seems like there's not a way to easily force a refresh or break the cache

When I run models in LM Studio the list of models available has a much higher rate of change then it does for a commercial vendor you can "eject" models and "load" models somewhat arbitrarily.

Ran into this too

I've removed certain models from the OC config file, as well as LM Studio models dir

Removed OC cache dir as well

But I still see ghost models when I do /models too

I believe I have encountered a similar issue. Although GitHub made Claude Sonnet General available, I see it as a preview. (GitHub Copilot Claude Sonnet 4.5 (Preview))

thats because the list of models comes from a models api that hasnt been updated with that change quite yet

models.dev

ill update that tho

@perlator

@perlator fixed, may require u to restart opencode but model list should refresh

I'm still having this issue despite running the latest version of opencode

opencode --version
0.15.30

 opencode models | grep lmstudio
lmstudio/openai/gpt-oss-20b
lmstudio/qwen/qwen3-30b-a3b-2507

curl localhost:1234/v1/models
{
  "data": [
    {
      "id": "qwen/qwen3-vl-30b",
      "object": "model",
      "owned_by": "organization_owner"
    },
    {
      "id": "text-embedding-nomic-embed-text-v1.5",
      "object": "model",
      "owned_by": "organization_owner"
    },
    {
      "id": "openai/gpt-oss-20b",
      "object": "model",
      "owned_by": "organization_owner"
    }
  ],
  "object": "list"
}

currently opencode isnt hitting the models endpoint of your provider, we should add something like that but currently everything comes from models.dev and your opencode config

I think removing the ghost endpoint when its found no longer alive is the best way to implement this. This way, we don't need to refresh model list everytime launch etc.

or get this, use the api correctly?

It seems when you delete models via the interface, some may not be getting cleaned up properly in the .internal/model-data.json when the names or aliases are close or the same. I think in my case, the alias was the same qwen3-coder-next. When I modified the .internal/model-data.json to remove two deleted model entries, once saved, the list of models refreshed on its own. Initially, it listed the models with their full name and the alias, and double entries for all models. I tried the refresh list, and it listed everything as expected. My issue involved similarly named models qwen3-coder-next (lingering entry) and the newly added Qwen3-Coder-Next-MLX-6bit.

I'm running into this problem too. I downloaded a new model in LM Studio and want to use it in OpenCode. When I do opencode models --refresh, it just gets the old list of models. Going to http://localhost:1234/v1/models shows the updated list so I think LM Studio is working fine. I reinstalled OpenCode and LM Studio, cleared cache files, and it's still the same.

It seems when you delete models via the interface, some may not be getting cleaned up properly in the .internal/model-data.json when the names or aliases are close or the same. I think in my case, the alias was the same qwen3-coder-next. When I modified the .internal/model-data.json to remove two deleted model entries, once saved, the list of models refreshed on its own. Initially, it listed the models with their full name and the alias, and double entries for all models. I tried the refresh list, and it listed everything as expected. My issue involved similarly named models qwen3-coder-next (lingering entry) and the newly added Qwen3-Coder-Next-MLX-6bit.

In my case
1, i deleted a model
2. then restored it from backup

the model refused to appear on the list of models inside the UI of LM studio
model was not showing up via the API http://localhost:1234/v1/models

and when going to its download page it was showing the model as already downloaded
... and i could still load it manually

So deleting this
USER_FOLDER/.lmstudio/.internal/model-data.json
did the trick (to make the restored-from-backup model to reappear):

Alternatively this worked too:
Changing the flag
transient: true
to
transient: false

Another option was to rename the parent folder of the model, this also made the model to reappear inside the ui and in the list via the API

Hello, the problem is still present in version 1.16.2

opencode --version
1.16.2

I had LMStudio installed on my computer with several models that I hadn't used for a long time. I decided to update the list, but in the process, I accidentally deleted them and downloaded more recent versions. As a result, they remained in the opencode memory. The command opencode models --refresh doesn't update the list.
Could you please tell me where the model list is stored? I might try to fix this bug myself, if I can.

PS. If I request a list of models from LM Studio using curl http://localhost:1234/v1/models it returns a correct list. Therefore, I suspect that the models are not being updated by opencode.

@Red-Cat-Fat

@Red-Cat-Fat
Just found this project, and this problem... I think what they mean is https://models.dev/providers/lmstudio/

It is building its models list from models.dev (website), not your local models list.

@wweeks

@wweeks do you know how we can get it to read the local models list instead?

@Red-Cat-Fat Just found this project, and this problem... I think what they mean is https://models.dev/providers/lmstudio/

It is building its models list from models.dev (website), not your local models list.

This appears to be exactly what's going on, and the problem still persists.

This is very crucial. How can we solve this? Add the model manually?

My current workaround is to use this project https://github.com/agustif/opencode-lmstudio

There is an unmerged pull request at sethjones/opencode/pull/2 that was referenced in #18011 but closed last month. Curious why it was not merged.

Likely duplicate: #23327

To stay organized issues are automatically closed after 60 days of no activity. If the issue is still relevant please open a new one.

Navigation Menu

Repository navigation

LM Studio Failure to refresh models #2047

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

LM Studio Failure to refresh models #2047

Description

Activity

blankenshipz commented on Aug 18, 2025

rekram1-node commented on Aug 18, 2025

blankenshipz commented on Aug 18, 2025

shrwnsan commented on Sep 26, 2025

perlator commented on Oct 17, 2025

rekram1-node commented on Oct 17, 2025

rekram1-node commented on Oct 17, 2025

blankenshipz commented on Oct 31, 2025

rekram1-node commented on Oct 31, 2025

KarthiDreamr commented on Nov 16, 2025

marduk191 commented on Feb 5, 2026

jecruz commented on Feb 11, 2026

SpencerGraffunder commented on Feb 12, 2026

ggppdk commented on Apr 10, 2026

Red-Cat-Fat commented on Jun 5, 2026

wweeks commented on Jun 12, 2026

kingeke commented on Jun 16, 2026

HyperboreanSlug commented on Jul 6, 2026

GBry commented on Jul 13, 2026

PigeonCoding commented on Jul 17, 2026

aadityabhatia commented on Jul 18, 2026

aadityabhatia commented on Jul 18, 2026

github-actions commented on Sep 17, 2026

Metadata

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Issue actions