# Invalid Type for 'Input' Error when Try Using Local LLM
**URL:** https://forum.bootstrapstudio.io/t/invalid-type-for-input-error-when-try-using-local-llm/12647
**Category:** Bug Reports
**Created:** [February 11, 2026, 2:13am UTC](https://forum.bootstrapstudio.io/t/invalid-type-for-input-error-when-try-using-local-llm/12647 "2026-02-11T02:13:12Z")
**Posts on this page:** 11
**Page:** 1
### Author:  [@raniaamina](https://forum.bootstrapstudio.io/u/raniaamina)
#### Post date: [February 11, 2026, 2:13am UTC](https://forum.bootstrapstudio.io/t/invalid-type-for-input-error-when-try-using-local-llm/12647/1 "2026-02-11T02:13:12Z")
Just try some models in Assistant feature, i use LM Studio with openAI Compatible API.
Some models that fall to this error:
- Nvidia nemotron nano
- qwen3
- GLM-4.6
and this is what i found in LM Studio log:
**2026-02-11 09:11:42 [ERROR]**
```auto
{
"error": {
"message": "Invalid type for 'input'.",
"type": "invalid_request_error",
"param": "input",
"code": "invalid_union"
}
}
```
---
### Author:  [@martin](https://forum.bootstrapstudio.io/u/martin)
#### Post date: [February 11, 2026, 10:03am UTC](https://forum.bootstrapstudio.io/t/invalid-type-for-input-error-when-try-using-local-llm/12647/2 "2026-02-11T10:03:56Z")
We haven’t developed with LM Studio in mind, but it should work if you add a custom openai model in Bootstrap Studio and providing the endpoint to the responses api: [Responses | LM Studio Docs](https://lmstudio.ai/docs/developer/openai-compat/responses)
---
### Author:  [@raniaamina](https://forum.bootstrapstudio.io/u/raniaamina)
#### Post date: [February 11, 2026, 2:52pm UTC](https://forum.bootstrapstudio.io/t/invalid-type-for-input-error-when-try-using-local-llm/12647/3 "2026-02-11T14:52:44Z")
Thanks for respons Martin, but this mostly happpened not in first request. So, after first request successfully done, and i need to reply to next step this problem happen. I usually use this API url in other editor and no issue, so maybe if there is something that i can do for help to figure out the issue with bs studio, i will.
Thanks.
---
### Author:  [@martin](https://forum.bootstrapstudio.io/u/martin)
#### Post date: [February 11, 2026, 4:13pm UTC](https://forum.bootstrapstudio.io/t/invalid-type-for-input-error-when-try-using-local-llm/12647/4 "2026-02-11T16:13:12Z")
If possible can you test if Ollama works for you?
---
### Author:  [@raniaamina](https://forum.bootstrapstudio.io/u/raniaamina)
#### Post date: [February 11, 2026, 5:11pm UTC](https://forum.bootstrapstudio.io/t/invalid-type-for-input-error-when-try-using-local-llm/12647/5 "2026-02-11T17:11:38Z")
Ok, let me test wiht ollama tomorrow with same model.
---
### Author:  [@raniaamina](https://forum.bootstrapstudio.io/u/raniaamina)
#### Post date: [February 13, 2026, 12:18pm UTC](https://forum.bootstrapstudio.io/t/invalid-type-for-input-error-when-try-using-local-llm/12647/6 "2026-02-13T12:18:44Z")
Tested with Ollama with same models, no error appears, but after waiting long respons it seem stuck and get this message,
---
### Author:  [@martin](https://forum.bootstrapstudio.io/u/martin)
#### Post date: [February 13, 2026, 1:59pm UTC](https://forum.bootstrapstudio.io/t/invalid-type-for-input-error-when-try-using-local-llm/12647/7 "2026-02-13T13:59:29Z")
Unfortunately I don’t think it’s a problem with Bootstrap Studio. The app just calls the model API as we do with Google/Anthropic/OpenAI/OpenRouter. Maybe the models you’re trying are too small and not “smart enough” to respect the instructions the app gives them. I’ve reliably used gpt-oss, but there are new models constantly being released so the only way is to try them.
---
### Author:  [@laurent](https://forum.bootstrapstudio.io/u/laurent)
#### Post date: [February 13, 2026, 4:03pm UTC](https://forum.bootstrapstudio.io/t/invalid-type-for-input-error-when-try-using-local-llm/12647/8 "2026-02-13T16:03:19Z")
Hi, tested with LM Studio, with those settings and test connection ok.
But nothing happen in BSS.
All with context @256k256k
With Ollama it’s ok 🙂
But after a moment, at the end of response when nearly finished, BSS freeze.
---
### Author:  [@raniaamina](https://forum.bootstrapstudio.io/u/raniaamina)
#### Post date: [February 13, 2026, 5:02pm UTC](https://forum.bootstrapstudio.io/t/invalid-type-for-input-error-when-try-using-local-llm/12647/9 "2026-02-13T17:02:32Z")
Is there any minimum criteria for model used? Mostly i use about 8–20B model for local LLM.
---
### Author:  [@raniaamina](https://forum.bootstrapstudio.io/u/raniaamina)
#### Post date: [February 13, 2026, 5:05pm UTC](https://forum.bootstrapstudio.io/t/invalid-type-for-input-error-when-try-using-local-llm/12647/10 "2026-02-13T17:05:40Z")
Just guess, there problem with handling [object] [object] but BSS doesn’t catch this event as error, so BSS still idle for waiting while ollama or LM Studio already stop processing stream.
---
### Author:  [@laurent](https://forum.bootstrapstudio.io/u/laurent)
#### Post date: [February 13, 2026, 5:20pm UTC](https://forum.bootstrapstudio.io/t/invalid-type-for-input-error-when-try-using-local-llm/12647/11 "2026-02-13T17:20:23Z")
Thanks.
It doesn’t happen every time…I noticed this problem when he wanted to create a file.
I need to do more tests.
During another attempt, he did not find the tool, so he asked me to copy paste HTML code and CSS 😅.