MindWorkAI/AI-Studio
MindWorkAI/AI-Studio
1
0
Fork 0
mirror of https://github.com/MindWorkAI/AI-Studio.git synced 2026-09-01 17:49:14 +00:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Added LiteLLM as a new LLM provider (#909)

Browse Source 
Co-authored-by: Thorsten Sommer <SommerEngineering@users.noreply.github.com>
This commit is contained in:
Prodman Devokadev 2026-08-30 16:25:18 +05:30 committed by GitHub
parent 2965102c53
commit 5966f0f6a5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
19 changed files with 206 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
README.md
View File

@ -117,6 +117,7 @@ MindWork AI Studio is a free desktop app for macOS, Windows, and Linux. It provi
- [OpenRouter](https://openrouter.ai/)
- [Hetzner](https://experiments.hetzner.com) (experimental inference API running open-source models in the EU)
- [IONOS](https://cloud.ionos.com/managed/ai-model-hub) (AI Model Hub running open-source models in Germany)
- [LiteLLM](https://www.litellm.ai/) (an AI gateway you run yourself, in front of models from many providers)
- [Hugging Face](https://huggingface.co/) using their [inference providers](https://huggingface.co/docs/inference-providers/index) such as Cerebras, Nebius, Sambanova, Novita, Hyperbolic, Together AI, Fireworks, Hugging Face
- Self-hosted models using [llama.cpp](https://github.com/ggerganov/llama.cpp), [ollama](https://github.com/ollama/ollama), [LM Studio](https://lmstudio.ai/), and [vLLM](https://github.com/vllm-project/vllm)
- [Groq](https://groq.com/)

9
app/MindWork AI Studio/Assistants/I18N/allTexts.lua
View File

@ -8356,6 +8356,9 @@ UI_TEXT_CONTENT["AISTUDIO::PAGES::HOME::T1024253064"] = "Welcome to MindWork AI
-- Thank you for considering MindWork AI Studio for your AI needs. This app is designed to help you harness the power of Large Language Models (LLMs). Please note that this app doesn't come with an integrated LLM. Instead, you will need to bring an API key from a suitable provider.
UI_TEXT_CONTENT["AISTUDIO::PAGES::HOME::T1146553980"] = "Thank you for considering MindWork AI Studio for your AI needs. This app is designed to help you harness the power of Large Language Models (LLMs). Please note that this app doesn't come with an integrated LLM. Instead, you will need to bring an API key from a suitable provider."
-- You are not tied to any single provider. Instead, you might choose the provider that best suits your needs. Right now, we support OpenAI (GPT5, o1, etc.), Perplexity, Mistral, Anthropic (Claude), Google Gemini, xAI (Grok), DeepSeek, Alibaba Cloud (Qwen), OpenRouter, Hetzner (experimental), IONOS, LiteLLM, Hugging Face, Groq, Fireworks, and self-hosted models using vLLM, llama.cpp, ollama, or LM Studio. For scientists and employees of research institutions, we also support Helmholtz and GWDG AI services. These are available through federated logins like eduGAIN to all 18 Helmholtz Centers, the Max Planck Society, most German, and many international universities.
UI_TEXT_CONTENT["AISTUDIO::PAGES::HOME::T1301599515"] = "You are not tied to any single provider. Instead, you might choose the provider that best suits your needs. Right now, we support OpenAI (GPT5, o1, etc.), Perplexity, Mistral, Anthropic (Claude), Google Gemini, xAI (Grok), DeepSeek, Alibaba Cloud (Qwen), OpenRouter, Hetzner (experimental), IONOS, LiteLLM, Hugging Face, Groq, Fireworks, and self-hosted models using vLLM, llama.cpp, ollama, or LM Studio. For scientists and employees of research institutions, we also support Helmholtz and GWDG AI services. These are available through federated logins like eduGAIN to all 18 Helmholtz Centers, the Max Planck Society, most German, and many international universities."
-- The app requires minimal storage for installation and operates with low memory usage. Additionally, it has a minimal impact on system resources, which is beneficial for battery life.
UI_TEXT_CONTENT["AISTUDIO::PAGES::HOME::T144565305"] = "The app requires minimal storage for installation and operates with low memory usage. Additionally, it has a minimal impact on system resources, which is beneficial for battery life."
@ -8419,9 +8422,6 @@ UI_TEXT_CONTENT["AISTUDIO::PAGES::HOME::T617579208"] = "Free of charge"
-- Independence
UI_TEXT_CONTENT["AISTUDIO::PAGES::HOME::T649448159"] = "Independence"
-- You are not tied to any single provider. Instead, you might choose the provider that best suits your needs. Right now, we support OpenAI (GPT5, o1, etc.), Perplexity, Mistral, Anthropic (Claude), Google Gemini, xAI (Grok), DeepSeek, Alibaba Cloud (Qwen), OpenRouter, Hetzner (experimental), IONOS, Hugging Face, Groq, Fireworks, and self-hosted models using vLLM, llama.cpp, ollama, or LM Studio. For scientists and employees of research institutions, we also support Helmholtz and GWDG AI services. These are available through federated logins like eduGAIN to all 18 Helmholtz Centers, the Max Planck Society, most German, and many international universities.
UI_TEXT_CONTENT["AISTUDIO::PAGES::HOME::T662688722"] = "You are not tied to any single provider. Instead, you might choose the provider that best suits your needs. Right now, we support OpenAI (GPT5, o1, etc.), Perplexity, Mistral, Anthropic (Claude), Google Gemini, xAI (Grok), DeepSeek, Alibaba Cloud (Qwen), OpenRouter, Hetzner (experimental), IONOS, Hugging Face, Groq, Fireworks, and self-hosted models using vLLM, llama.cpp, ollama, or LM Studio. For scientists and employees of research institutions, we also support Helmholtz and GWDG AI services. These are available through federated logins like eduGAIN to all 18 Helmholtz Centers, the Max Planck Society, most German, and many international universities."
-- No bloatware
UI_TEXT_CONTENT["AISTUDIO::PAGES::HOME::T858047957"] = "No bloatware"
@ -9238,6 +9238,9 @@ UI_TEXT_CONTENT["AISTUDIO::PROVIDER::CONFIDENCE::T3010553924"] = "The provider i
-- No provider selected. Please select a provider to get see its confidence level.
UI_TEXT_CONTENT["AISTUDIO::PROVIDER::CONFIDENCE::T3368531176"] = "No provider selected. Please select a provider to get see its confidence level."
-- You or your organization operate this gateway. However, it forwards your data to **whichever providers you configured behind it**, which may be cloud services in any jurisdiction. We cannot know where your data ends up, so **please assign the trust level yourself**.
UI_TEXT_CONTENT["AISTUDIO::PROVIDER::CONFIDENCE::T3370749159"] = "You or your organization operate this gateway. However, it forwards your data to **whichever providers you configured behind it**, which may be cloud services in any jurisdiction. We cannot know where your data ends up, so **please assign the trust level yourself**."
-- The provider operates its service from the USA and is subject to **US jurisdiction**. In case of suspicion, authorities in the USA can access your data. However, **your data is not used for training** purposes.
UI_TEXT_CONTENT["AISTUDIO::PROVIDER::CONFIDENCE::T3528165925"] = "The provider operates its service from the USA and is subject to **US jurisdiction**. In case of suspicion, authorities in the USA can access your data. However, **your data is not used for training** purposes."

2
app/MindWork AI Studio/Pages/Home.razor.cs
View File

@ -63,7 +63,7 @@ public partial class Home : MSGComponentBase
this.itemsAdvantages = [
new(this.T("Free of charge"), this.T("The app is free to use, both for personal and commercial purposes.")),
new(this.T("Democratization of AI"), this.T("We want to contribute to the democratization of AI. MindWork AI Studio runs even on low-cost hardware, including computers around 100 EUR such as Raspberry Pi. This makes the app and its full feature set accessible to people and families with limited budgets. You can start with local LLMs or use affordable cloud models.")),
new(this.T("Independence"), this.T("You are not tied to any single provider. Instead, you might choose the provider that best suits your needs. Right now, we support OpenAI (GPT5, o1, etc.), Perplexity, Mistral, Anthropic (Claude), Google Gemini, xAI (Grok), DeepSeek, Alibaba Cloud (Qwen), OpenRouter, Hetzner (experimental), IONOS, Hugging Face, Groq, Fireworks, and self-hosted models using vLLM, llama.cpp, ollama, or LM Studio. For scientists and employees of research institutions, we also support Helmholtz and GWDG AI services. These are available through federated logins like eduGAIN to all 18 Helmholtz Centers, the Max Planck Society, most German, and many international universities.")),
new(this.T("Independence"), this.T("You are not tied to any single provider. Instead, you might choose the provider that best suits your needs. Right now, we support OpenAI (GPT5, o1, etc.), Perplexity, Mistral, Anthropic (Claude), Google Gemini, xAI (Grok), DeepSeek, Alibaba Cloud (Qwen), OpenRouter, Hetzner (experimental), IONOS, LiteLLM, Hugging Face, Groq, Fireworks, and self-hosted models using vLLM, llama.cpp, ollama, or LM Studio. For scientists and employees of research institutions, we also support Helmholtz and GWDG AI services. These are available through federated logins like eduGAIN to all 18 Helmholtz Centers, the Max Planck Society, most German, and many international universities.")),
new(this.T("Assistants"), this.T("You just want to quickly translate a text? AI Studio has so-called assistants for such and other tasks. No prompting is necessary when working with these assistants.")),
new(this.T("Unrestricted usage"), this.T("Unlike services like ChatGPT, which impose limits after intensive use, MindWork AI Studio offers unlimited usage through the providers API.")),
new(this.T("Cost-effective"), this.T("You only pay for what you use, which can be cheaper than monthly subscription services like ChatGPT Plus, especially if used infrequently. But beware, here be dragons: For extremely intensive usage, the API costs can be significantly higher. Unfortunately, providers currently do not offer a way to display current costs in the app. Therefore, check your account with the respective provider to see how your costs are developing. When available, use prepaid and set a cost limit.")),

5
app/MindWork AI Studio/Plugins/configuration/plugin.lua
View File

@ -711,8 +711,8 @@ CONFIG["SETTINGS"] = {}
-- Configure a custom confidence scheme.
-- This is used when DataConfidence.ConfidenceScheme is set to CUSTOM.
-- Allowed provider keys are: OPEN_AI, ANTHROPIC, MISTRAL, GOOGLE, X, DEEP_SEEK, ALIBABA_CLOUD,
-- PERPLEXITY, OPEN_ROUTER, HETZNER, IONOS, FIREWORKS, GROQ, HUGGINGFACE, SELF_HOSTED, HELMHOLTZ,
-- GWDG
-- PERPLEXITY, OPEN_ROUTER, HETZNER, IONOS, LITE_LLM, FIREWORKS, GROQ, HUGGINGFACE, SELF_HOSTED,
-- HELMHOLTZ, GWDG
-- Allowed confidence values are: UNTRUSTED, VERY_LOW, LOW, MODERATE, MEDIUM, HIGH
--
-- Replaces, does not merge: a configuration with a higher priority replaces the whole
@ -731,6 +731,7 @@ CONFIG["SETTINGS"] = {}
-- ["OPEN_ROUTER"] = "MODERATE",
-- ["HETZNER"] = "HIGH",
-- ["IONOS"] = "HIGH",
-- ["LITE_LLM"] = "MODERATE",
-- ["FIREWORKS"] = "MODERATE",
-- ["GROQ"] = "MODERATE",
-- ["HUGGINGFACE"] = "MODERATE",

9
app/MindWork AI Studio/Plugins/languages/de-de-43065dbc-78d0-45b7-92be-f14c2926e2dc/plugin.lua
View File

@ -8358,6 +8358,9 @@ UI_TEXT_CONTENT["AISTUDIO::PAGES::HOME::T1024253064"] = "Willkommen bei MindWork
-- Thank you for considering MindWork AI Studio for your AI needs. This app is designed to help you harness the power of Large Language Models (LLMs). Please note that this app doesn't come with an integrated LLM. Instead, you will need to bring an API key from a suitable provider.
UI_TEXT_CONTENT["AISTUDIO::PAGES::HOME::T1146553980"] = "Vielen Dank, dass Sie MindWork AI Studio für ihre KI-Anwendungen in Betracht ziehen. Diese App wurde entwickelt, um Ihnen die Nutzung von leistungsstarken Sprachmodellen (LLMs) zu ermöglichen. Bitte beachten Sie, dass die App kein integriertes LLM enthält. Stattdessen benötigen Sie einen API-Schlüssel von einem passenden Anbieter."
-- You are not tied to any single provider. Instead, you might choose the provider that best suits your needs. Right now, we support OpenAI (GPT5, o1, etc.), Perplexity, Mistral, Anthropic (Claude), Google Gemini, xAI (Grok), DeepSeek, Alibaba Cloud (Qwen), OpenRouter, Hetzner (experimental), IONOS, LiteLLM, Hugging Face, Groq, Fireworks, and self-hosted models using vLLM, llama.cpp, ollama, or LM Studio. For scientists and employees of research institutions, we also support Helmholtz and GWDG AI services. These are available through federated logins like eduGAIN to all 18 Helmholtz Centers, the Max Planck Society, most German, and many international universities.
UI_TEXT_CONTENT["AISTUDIO::PAGES::HOME::T1301599515"] = "Sie sind nicht an einen einzigen Anbieter gebunden. Stattdessen können Sie den Anbieter wählen, der am besten zu Ihren Anforderungen passt. Derzeit unterstützen wir OpenAI (GPT5, o1 usw.), Perplexity, Mistral, Anthropic (Claude), Google Gemini, xAI (Grok), DeepSeek, Alibaba Cloud (Qwen), OpenRouter, Hetzner (experimentell), IONOS, LiteLLM, Hugging Face, Groq, Fireworks sowie selbst gehostete Modelle mit vLLM, llama.cpp, ollama oder LM Studio. Für Wissenschaftlerinnen und Wissenschaftler sowie Mitarbeitende von Forschungseinrichtungen unterstützen wir außerdem die KI-Dienste von Helmholtz und GWDG. Diese sind über föderierte Logins wie eduGAIN für alle 18 Helmholtz-Zentren, die Max-Planck-Gesellschaft, die meisten deutschen sowie viele internationale Universitäten verfügbar."
-- The app requires minimal storage for installation and operates with low memory usage. Additionally, it has a minimal impact on system resources, which is beneficial for battery life.
UI_TEXT_CONTENT["AISTUDIO::PAGES::HOME::T144565305"] = "Die App benötigt nur wenig Speicherplatz für die Installation und verwendet wenig Arbeitsspeicher. Außerdem hat sie einen minimalen Einfluss auf die Systemressourcen, was sich positiv auf die Akkulaufzeit auswirkt."
@ -8421,9 +8424,6 @@ UI_TEXT_CONTENT["AISTUDIO::PAGES::HOME::T617579208"] = "Kostenlos"
-- Independence
UI_TEXT_CONTENT["AISTUDIO::PAGES::HOME::T649448159"] = "Unabhängigkeit"
-- You are not tied to any single provider. Instead, you might choose the provider that best suits your needs. Right now, we support OpenAI (GPT5, o1, etc.), Perplexity, Mistral, Anthropic (Claude), Google Gemini, xAI (Grok), DeepSeek, Alibaba Cloud (Qwen), OpenRouter, Hetzner (experimental), IONOS, Hugging Face, Groq, Fireworks, and self-hosted models using vLLM, llama.cpp, ollama, or LM Studio. For scientists and employees of research institutions, we also support Helmholtz and GWDG AI services. These are available through federated logins like eduGAIN to all 18 Helmholtz Centers, the Max Planck Society, most German, and many international universities.
UI_TEXT_CONTENT["AISTUDIO::PAGES::HOME::T662688722"] = "Sie sind nicht an einen einzelnen Anbieter gebunden. Stattdessen können Sie den Anbieter wählen, der am besten zu Ihren Bedürfnissen passt. Derzeit unterstützen wir OpenAI (GPT-5, o1 usw.), Perplexity, Mistral, Anthropic (Claude), Google Gemini, xAI (Grok), DeepSeek, Alibaba Cloud (Qwen), OpenRouter, Hetzner (experimentell), IONOS, Hugging Face, Groq, Fireworks sowie selbst gehostete Modelle mit vLLM, llama.cpp, ollama oder LM Studio. Für Wissenschaftlerinnen und Wissenschaftler sowie Mitarbeitende von Forschungseinrichtungen unterstützen wir außerdem die KI-Dienste von Helmholtz und GWDG. Diese sind über föderierte Logins wie eduGAIN für alle 18 Helmholtz-Zentren, die Max-Planck-Gesellschaft, die meisten deutschen und viele internationale Universitäten verfügbar."
-- No bloatware
UI_TEXT_CONTENT["AISTUDIO::PAGES::HOME::T858047957"] = "Keinen unnötigen Software-Ballast"
@ -9240,6 +9240,9 @@ UI_TEXT_CONTENT["AISTUDIO::PROVIDER::CONFIDENCE::T3010553924"] = "Der Anbieter h
-- No provider selected. Please select a provider to get see its confidence level.
UI_TEXT_CONTENT["AISTUDIO::PROVIDER::CONFIDENCE::T3368531176"] = "Kein Anbieter ausgewählt. Bitte wählen Sie einen Anbieter aus, um dessen Vertrauensniveau zu sehen."
-- You or your organization operate this gateway. However, it forwards your data to **whichever providers you configured behind it**, which may be cloud services in any jurisdiction. We cannot know where your data ends up, so **please assign the trust level yourself**.
UI_TEXT_CONTENT["AISTUDIO::PROVIDER::CONFIDENCE::T3370749159"] = "Sie oder Ihre Organisation betreiben dieses Gateway. Es leitet Ihre Daten jedoch an **die Anbieter weiter, die Sie dahinter konfiguriert haben**. Dabei kann es sich um Cloud-Dienste in beliebigen Rechtsräumen handeln. Wir können nicht wissen, wo Ihre Daten letztendlich landen. **Bitte legen Sie die Vertrauensstufe daher selbst fest.**"
-- The provider operates its service from the USA and is subject to **US jurisdiction**. In case of suspicion, authorities in the USA can access your data. However, **your data is not used for training** purposes.
UI_TEXT_CONTENT["AISTUDIO::PROVIDER::CONFIDENCE::T3528165925"] = "Der Anbieter betreibt seinen Dienst aus den USA und unterliegt der **US-amerikanischen Gerichtsbarkeit**. Bei Verdacht können US-Behörden auf ihre Daten zugreifen. **Ihre Daten werden jedoch nicht für Trainingszwecke** verwendet."

9
app/MindWork AI Studio/Plugins/languages/en-us-97dfb1ba-50c4-4440-8dfa-6575daf543c8/plugin.lua
View File

@ -8358,6 +8358,9 @@ UI_TEXT_CONTENT["AISTUDIO::PAGES::HOME::T1024253064"] = "Welcome to MindWork AI
-- Thank you for considering MindWork AI Studio for your AI needs. This app is designed to help you harness the power of Large Language Models (LLMs). Please note that this app doesn't come with an integrated LLM. Instead, you will need to bring an API key from a suitable provider.
UI_TEXT_CONTENT["AISTUDIO::PAGES::HOME::T1146553980"] = "Thank you for considering MindWork AI Studio for your AI needs. This app is designed to help you harness the power of Large Language Models (LLMs). Please note that this app doesn't come with an integrated LLM. Instead, you will need to bring an API key from a suitable provider."
-- You are not tied to any single provider. Instead, you might choose the provider that best suits your needs. Right now, we support OpenAI (GPT5, o1, etc.), Perplexity, Mistral, Anthropic (Claude), Google Gemini, xAI (Grok), DeepSeek, Alibaba Cloud (Qwen), OpenRouter, Hetzner (experimental), IONOS, LiteLLM, Hugging Face, Groq, Fireworks, and self-hosted models using vLLM, llama.cpp, ollama, or LM Studio. For scientists and employees of research institutions, we also support Helmholtz and GWDG AI services. These are available through federated logins like eduGAIN to all 18 Helmholtz Centers, the Max Planck Society, most German, and many international universities.
UI_TEXT_CONTENT["AISTUDIO::PAGES::HOME::T1301599515"] = "You are not tied to any single provider. Instead, you might choose the provider that best suits your needs. Right now, we support OpenAI (GPT5, o1, etc.), Perplexity, Mistral, Anthropic (Claude), Google Gemini, xAI (Grok), DeepSeek, Alibaba Cloud (Qwen), OpenRouter, Hetzner (experimental), IONOS, LiteLLM, Hugging Face, Groq, Fireworks, and self-hosted models using vLLM, llama.cpp, ollama, or LM Studio. For scientists and employees of research institutions, we also support Helmholtz and GWDG AI services. These are available through federated logins like eduGAIN to all 18 Helmholtz Centers, the Max Planck Society, most German, and many international universities."
-- The app requires minimal storage for installation and operates with low memory usage. Additionally, it has a minimal impact on system resources, which is beneficial for battery life.
UI_TEXT_CONTENT["AISTUDIO::PAGES::HOME::T144565305"] = "The app requires minimal storage for installation and operates with low memory usage. Additionally, it has a minimal impact on system resources, which is beneficial for battery life."
@ -8421,9 +8424,6 @@ UI_TEXT_CONTENT["AISTUDIO::PAGES::HOME::T617579208"] = "Free of charge"
-- Independence
UI_TEXT_CONTENT["AISTUDIO::PAGES::HOME::T649448159"] = "Independence"
-- You are not tied to any single provider. Instead, you might choose the provider that best suits your needs. Right now, we support OpenAI (GPT5, o1, etc.), Perplexity, Mistral, Anthropic (Claude), Google Gemini, xAI (Grok), DeepSeek, Alibaba Cloud (Qwen), OpenRouter, Hetzner (experimental), IONOS, Hugging Face, Groq, Fireworks, and self-hosted models using vLLM, llama.cpp, ollama, or LM Studio. For scientists and employees of research institutions, we also support Helmholtz and GWDG AI services. These are available through federated logins like eduGAIN to all 18 Helmholtz Centers, the Max Planck Society, most German, and many international universities.
UI_TEXT_CONTENT["AISTUDIO::PAGES::HOME::T662688722"] = "You are not tied to any single provider. Instead, you might choose the provider that best suits your needs. Right now, we support OpenAI (GPT5, o1, etc.), Perplexity, Mistral, Anthropic (Claude), Google Gemini, xAI (Grok), DeepSeek, Alibaba Cloud (Qwen), OpenRouter, Hetzner (experimental), IONOS, Hugging Face, Groq, Fireworks, and self-hosted models using vLLM, llama.cpp, ollama, or LM Studio. For scientists and employees of research institutions, we also support Helmholtz and GWDG AI services. These are available through federated logins like eduGAIN to all 18 Helmholtz Centers, the Max Planck Society, most German, and many international universities."
-- No bloatware
UI_TEXT_CONTENT["AISTUDIO::PAGES::HOME::T858047957"] = "No bloatware"
@ -9240,6 +9240,9 @@ UI_TEXT_CONTENT["AISTUDIO::PROVIDER::CONFIDENCE::T3010553924"] = "The provider i
-- No provider selected. Please select a provider to get see its confidence level.
UI_TEXT_CONTENT["AISTUDIO::PROVIDER::CONFIDENCE::T3368531176"] = "No provider selected. Please select a provider to get see its confidence level."
-- You or your organization operate this gateway. However, it forwards your data to **whichever providers you configured behind it**, which may be cloud services in any jurisdiction. We cannot know where your data ends up, so **please assign the trust level yourself**.
UI_TEXT_CONTENT["AISTUDIO::PROVIDER::CONFIDENCE::T3370749159"] = "You or your organization operate this gateway. However, it forwards your data to **whichever providers you configured behind it**, which may be cloud services in any jurisdiction. We cannot know where your data ends up, so **please assign the trust level yourself**."
-- The provider operates its service from the USA and is subject to **US jurisdiction**. In case of suspicion, authorities in the USA can access your data. However, **your data is not used for training** purposes.
UI_TEXT_CONTENT["AISTUDIO::PROVIDER::CONFIDENCE::T3528165925"] = "The provider operates its service from the USA and is subject to **US jurisdiction**. In case of suspicion, authorities in the USA can access your data. However, **your data is not used for training** purposes."

9
app/MindWork AI Studio/Provider/BaseProvider.cs
View File

@ -1097,6 +1097,15 @@ public abstract class BaseProvider : IProvider, ISecretId
form.Add(new StringContent(modelName), "model");
//
// Ask for the plain JSON format explicitly. We only ever read the 'text' field, so the
// additional data of 'verbose_json' would be wasted anyway. More importantly, gateways
// fill in a format of their own when the client names none: LiteLLM asks for
// 'verbose_json' to get the duration it needs for its cost tracking, and the newer
// transcription models of OpenAI reject that format.
//
form.Add(new StringContent("json"), "response_format");
using var request = new HttpRequestMessage(HttpMethod.Post, host.TranscriptionURL());
request.Content = form;

6
app/MindWork AI Studio/Provider/Confidence.cs
View File

@ -47,6 +47,12 @@ public sealed record Confidence
Description = TB("The trust level of this provider **has not yet** been thoroughly **investigated and evaluated**. We do not know if your data is safe."),
};
public static readonly Confidence USER_OPERATED_GATEWAY = new()
{
Level = ConfidenceLevel.UNKNOWN,
Description = TB("You or your organization operate this gateway. However, it forwards your data to **whichever providers you configured behind it**, which may be cloud services in any jurisdiction. We cannot know where your data ends up, so **please assign the trust level yourself**."),
};
public static readonly Confidence USA_NO_TRAINING = new()
{
Level = ConfidenceLevel.MODERATE,

1
app/MindWork AI Studio/Provider/LLMProviders.cs
View File

@ -18,6 +18,7 @@ public enum LLMProviders
OPEN_ROUTER = 15,
HETZNER = 16,
IONOS = 17,
LITE_LLM = 18,
FIREWORKS = 5,
GROQ = 6,

24
app/MindWork AI Studio/Provider/LLMProvidersExtensions.cs
View File

@ -9,6 +9,7 @@ using AIStudio.Provider.Helmholtz;
using AIStudio.Provider.Hetzner;
using AIStudio.Provider.HuggingFace;
using AIStudio.Provider.IONOS;
using AIStudio.Provider.LiteLLM;
using AIStudio.Provider.Mistral;
using AIStudio.Provider.OpenAI;
using AIStudio.Provider.OpenRouter;
@ -60,11 +61,12 @@ public static class LLMProvidersExtensions
LLMProviders.OPEN_ROUTER => "OpenRouter",
LLMProviders.HETZNER => "Hetzner (Experimental)",
LLMProviders.IONOS => "IONOS",
LLMProviders.LITE_LLM => "LiteLLM",
LLMProviders.GROQ => "Groq",
LLMProviders.FIREWORKS => "Fireworks.ai",
LLMProviders.HUGGINGFACE => "Hugging Face",
LLMProviders.SELF_HOSTED => translate ? TB("Self-hosted") : "Self-hosted",
LLMProviders.HELMHOLTZ => "Helmholtz Blablador",
@ -97,6 +99,7 @@ public static class LLMProvidersExtensions
LLMProviders.OPEN_ROUTER => "OpenRouter",
LLMProviders.HETZNER => "Hetzner",
LLMProviders.IONOS => "IONOS",
LLMProviders.LITE_LLM => "LiteLLM",
LLMProviders.GROQ => "Groq",
LLMProviders.FIREWORKS => "Fireworks.ai",
@ -161,6 +164,12 @@ public static class LLMProvidersExtensions
"https://www.ionos.com/terms-gtc/privacy-policy/"
).WithLevel(settingsManager.GetConfiguredConfidenceLevel(llmProvider)),
// LiteLLM is a gateway the user runs, but it is not a self-hosted LLM: the proxy owner decides
// which downstream providers it routes to, and those are usually cloud services. Self-hosting
// the proxy therefore says nothing about where the data ends up, so we do not claim the trust
// of a self-hosted model here and let the user assign the level themselves.
LLMProviders.LITE_LLM => Confidence.USER_OPERATED_GATEWAY.WithSources("https://docs.litellm.ai/docs/data_security").WithLevel(settingsManager.GetConfiguredConfidenceLevel(llmProvider)),
LLMProviders.SELF_HOSTED => Confidence.SELF_HOSTED.WithLevel(settingsManager.GetConfiguredConfidenceLevel(llmProvider)),
LLMProviders.HELMHOLTZ => Confidence.GDPR_NO_TRAINING.WithRegion("Europe, Germany").WithSources("https://helmholtz.cloud/services/?serviceID=d7d5c597-a2f6-4bd1-b71e-4d6499d98570").WithLevel(settingsManager.GetConfiguredConfidenceLevel(llmProvider)),
@ -187,6 +196,7 @@ public static class LLMProvidersExtensions
LLMProviders.IONOS => true,
LLMProviders.GWDG => true,
LLMProviders.OPEN_ROUTER => true,
LLMProviders.LITE_LLM => true,
//
// Providers that do not support embeddings:
@ -204,10 +214,10 @@ public static class LLMProvidersExtensions
// Self-hosted providers are treated as a special case anyway.
//
LLMProviders.SELF_HOSTED => true,
_ => false,
};
public static bool ProvideTranscriptionAPI(this LLMProviders llmProvider) => llmProvider switch
{
//
@ -219,6 +229,7 @@ public static class LLMProvidersExtensions
LLMProviders.GWDG => true,
LLMProviders.HELMHOLTZ => true,
LLMProviders.GROQ => true,
LLMProviders.LITE_LLM => true,
//
// Providers that support transcription but provide no OpenAI-compatible API yet:
@ -293,6 +304,7 @@ public static class LLMProvidersExtensions
LLMProviders.OPEN_ROUTER => new ProviderOpenRouter { InstanceName = instanceName, ConfiguredProviderId = configuredProviderId, AdditionalJsonApiParameters = expertProviderApiParameter, IsEnterpriseConfiguration = isEnterpriseConfiguration },
LLMProviders.HETZNER => new ProviderHetzner { InstanceName = instanceName, ConfiguredProviderId = configuredProviderId, AdditionalJsonApiParameters = expertProviderApiParameter, IsEnterpriseConfiguration = isEnterpriseConfiguration },
LLMProviders.IONOS => new ProviderIONOS { InstanceName = instanceName, ConfiguredProviderId = configuredProviderId, AdditionalJsonApiParameters = expertProviderApiParameter, IsEnterpriseConfiguration = isEnterpriseConfiguration },
LLMProviders.LITE_LLM => new ProviderLiteLLM(hostname) { InstanceName = instanceName, ConfiguredProviderId = configuredProviderId, AdditionalJsonApiParameters = expertProviderApiParameter, IsEnterpriseConfiguration = isEnterpriseConfiguration },
LLMProviders.GROQ => new ProviderGroq { InstanceName = instanceName, ConfiguredProviderId = configuredProviderId, AdditionalJsonApiParameters = expertProviderApiParameter, IsEnterpriseConfiguration = isEnterpriseConfiguration },
LLMProviders.FIREWORKS => new ProviderFireworks { InstanceName = instanceName, ConfiguredProviderId = configuredProviderId, AdditionalJsonApiParameters = expertProviderApiParameter, IsEnterpriseConfiguration = isEnterpriseConfiguration },
@ -436,6 +448,7 @@ public static class LLMProvidersExtensions
public static bool IsHostnameNeeded(this LLMProviders provider) => provider switch
{
LLMProviders.SELF_HOSTED => true,
LLMProviders.LITE_LLM => true,
_ => false,
};
@ -452,15 +465,16 @@ public static class LLMProvidersExtensions
LLMProviders.OPEN_ROUTER => true,
LLMProviders.HETZNER => true,
LLMProviders.IONOS => true,
LLMProviders.LITE_LLM => true,
LLMProviders.GROQ => true,
LLMProviders.FIREWORKS => true,
LLMProviders.HELMHOLTZ => true,
LLMProviders.GWDG => true,
LLMProviders.HUGGINGFACE => true,
LLMProviders.SELF_HOSTED => host is (Host.OLLAMA or Host.VLLM),
_ => false,
};

1
app/MindWork AI Studio/Provider/LLMProvidersIconExtensions.cs
View File

@ -30,6 +30,7 @@ public static class LLMProvidersIconExtensions
LLMProviders.OPEN_ROUTER => $"{ICON_ROOT}/openrouter.svg",
LLMProviders.HETZNER => $"{ICON_ROOT}/hetzner.svg",
LLMProviders.IONOS => $"{ICON_ROOT}/ionos.svg",
LLMProviders.LITE_LLM => $"{ICON_ROOT}/litellm.svg",
LLMProviders.GROQ => $"{ICON_ROOT}/groq.svg",
LLMProviders.FIREWORKS => $"{ICON_ROOT}/fireworks.svg",
LLMProviders.HUGGINGFACE => $"{ICON_ROOT}/hugging-face.svg",

125
app/MindWork AI Studio/Provider/LiteLLM/ProviderLiteLLM.cs Normal file
View File

@ -0,0 +1,125 @@
using System.Runtime.CompilerServices;
using AIStudio.Chat;
using AIStudio.Provider.OpenAI;
using AIStudio.Settings;
namespace AIStudio.Provider.LiteLLM;
public sealed class ProviderLiteLLM(string hostname) : BaseProvider(LLMProviders.LITE_LLM, BuildBaseUri(hostname), ExternalHttpTrustPolicy.ALLOW_CUSTOM_ROOTS_WHEN_HOST_WHITELISTED, LOGGER)
{
private static readonly ILogger<ProviderLiteLLM> LOGGER = Program.LOGGER_FACTORY.CreateLogger<ProviderLiteLLM>();
#region Implementation of IProvider
/// <inheritdoc />
public override string Id => LLMProviders.LITE_LLM.ToSecretId();
/// <inheritdoc />
public override string InstanceName { get; set; } = "LiteLLM";
/// <inheritdoc />
public override bool HasModelLoadingCapability => true;
/// <inheritdoc />
public override async IAsyncEnumerable<ContentStreamChunk> StreamChatCompletion(Model chatModel, ChatThread chatThread, SettingsManager settingsManager, [EnumeratorCancellation] CancellationToken token = default)
{
await foreach (var content in this.StreamOpenAICompatibleChatCompletion<ChatCompletionAPIRequest, ChatCompletionDeltaStreamLine, NoChatCompletionAnnotationStreamLine>(
"LiteLLM",
chatModel,
chatThread,
settingsManager,
async (systemPrompt, apiParameters) =>
{
// Build the list of messages:
var messages = await chatThread.Blocks.BuildMessagesUsingDirectImageUrlAsync(this.Provider, chatModel);
return new ChatCompletionAPIRequest
{
Model = chatModel.Id,
// Build the messages:
// - First of all the system prompt
// - Then none-empty user and AI messages
Messages = [systemPrompt, ..messages],
Stream = true,
AdditionalApiParameters = apiParameters
};
},
token: token))
yield return content;
}
#pragma warning disable CS1998 // Async method lacks 'await' operators and will run synchronously
/// <inheritdoc />
public override async IAsyncEnumerable<ImageURL> StreamImageCompletion(Model imageModel, string promptPositive, string promptNegative = FilterOperator.String.Empty, ImageURL referenceImageURL = default, [EnumeratorCancellation] CancellationToken token = default)
{
yield break;
}
#pragma warning restore CS1998 // Async method lacks 'await' operators and will run synchronously
/// <inheritdoc />
public override async Task<TranscriptionResult> TranscribeAudioAsync(Model transcriptionModel, string audioFilePath, SettingsManager settingsManager, CancellationToken token = default)
{
var requestedSecret = await Program.RUST_SERVICE.GetAPIKey(this, SecretStoreType.TRANSCRIPTION_PROVIDER);
return await this.PerformStandardTranscriptionRequest(requestedSecret, transcriptionModel, audioFilePath, token: token);
}
/// <inheritdoc />
public override async Task<IReadOnlyList<IReadOnlyList<float>>> EmbedTextAsync(Model embeddingModel, SettingsManager settingsManager, CancellationToken token = default, params List<string> texts)
{
var requestedSecret = await Program.RUST_SERVICE.GetAPIKey(this, SecretStoreType.EMBEDDING_PROVIDER);
return await this.PerformStandardTextEmbeddingRequest(requestedSecret, embeddingModel, token: token, texts: texts);
}
/// <inheritdoc />
public override Task<ModelLoadResult> GetTextModels(string? apiKeyProvisional = null, CancellationToken token = default)
{
return this.LoadModels(SecretStoreType.LLM_PROVIDER, static model => model.IsChatModel(), token, apiKeyProvisional);
}
/// <inheritdoc />
public override Task<ModelLoadResult> GetImageModels(string? apiKeyProvisional = null, CancellationToken token = default)
{
return Task.FromResult(ModelLoadResult.FromModels([]));
}
/// <inheritdoc />
public override Task<ModelLoadResult> GetEmbeddingModels(string? apiKeyProvisional = null, CancellationToken token = default)
{
return this.LoadModels(SecretStoreType.EMBEDDING_PROVIDER, static model => model.IsEmbeddingModel(), token, apiKeyProvisional);
}
/// <inheritdoc />
public override Task<ModelLoadResult> GetTranscriptionModels(string? apiKeyProvisional = null, CancellationToken token = default)
{
return this.LoadModels(SecretStoreType.TRANSCRIPTION_PROVIDER, static model => model.IsTranscriptionModel(), token, apiKeyProvisional);
}
#endregion
private static Uri BuildBaseUri(string hostname)
{
// LiteLLM exposes an OpenAI-compatible API under the "/v1/" path. Users configure the
// base URL of their LiteLLM proxy (e.g. http://localhost:4000); we normalize any trailing
// slash and append the OpenAI-compatible path.
var normalizedHostname = hostname.TrimEnd('/');
return new Uri($"{normalizedHostname}/v1/");
}
private Task<ModelLoadResult> LoadModels(SecretStoreType storeType, Func<Model, bool> isWantedKind, CancellationToken token, string? apiKeyProvisional = null)
{
//
// The gateway serves every kind of model through one endpoint, so we have to sort
// them apart ourselves. We use the shared model kind detection for that, which every
// other provider uses as well:
//
return this.LoadModelsResponse<ModelsResponse>(
storeType,
"models",
modelResponse => modelResponse.Data.Where(isWantedKind),
token,
apiKeyProvisional);
}
}

1
app/MindWork AI Studio/Settings/ProviderExtensions.Reasoning.cs
View File

@ -92,6 +92,7 @@ public static partial class ProviderExtensions
LLMProviders.OPEN_ROUTER or
LLMProviders.HETZNER or
LLMProviders.IONOS or
LLMProviders.LITE_LLM or
LLMProviders.X or
LLMProviders.DEEP_SEEK or
LLMProviders.GROQ or

12
app/MindWork AI Studio/Settings/ProviderExtensions.cs
View File

@ -54,8 +54,16 @@ public static partial class ProviderExtensions
LLMProviders.ALIBABA_CLOUD => GetModelCapabilitiesAlibaba(model),
LLMProviders.PERPLEXITY => GetModelCapabilitiesPerplexity(model),
LLMProviders.OPEN_ROUTER => GetModelCapabilitiesOpenRouter(model),
LLMProviders.HETZNER => GetModelCapabilitiesOpenSource(model),
LLMProviders.IONOS => GetModelCapabilitiesOpenSource(model),
LLMProviders.HETZNER or LLMProviders.IONOS => GetModelCapabilitiesOpenSource(model),
//
// LiteLLM is a gateway just like OpenRouter, and it names its models the same way:
// "vendor/model", e.g. "anthropic/claude-opus-5" or "azure/gpt-5.6". So we let the
// OpenRouter detection handle it, which resolves the vendor prefix and asks the
// provider who really knows the model. Everything it cannot place is treated as
// an open source model, which is the right fallback for a freely named alias:
//
LLMProviders.LITE_LLM => GetModelCapabilitiesOpenRouter(model),
LLMProviders.GROQ => GetModelCapabilitiesOpenSource(model),
LLMProviders.FIREWORKS => GetModelCapabilitiesOpenSource(model),

7
app/MindWork AI Studio/Tools/Validation/ProviderValidation.cs
View File

@ -26,7 +26,12 @@ public sealed class ProviderValidation
public string? ValidatingHostname(string hostname)
{
if(this.GetProvider() != LLMProviders.SELF_HOSTED)
//
// Every provider for which IsHostnameNeeded is true must be validated here. Otherwise,
// the dialog shows a hostname field which nobody checks, and the provider silently ends
// up as a NoProvider later on, because its base URI cannot be built:
//
if(this.GetProvider() is not (LLMProviders.SELF_HOSTED or LLMProviders.LITE_LLM))
return null;
if(string.IsNullOrWhiteSpace(hostname))

1
app/MindWork AI Studio/wwwroot/changelog/v26.8.2.md
View File

@ -5,6 +5,7 @@
- Added the option for IT departments to enable assistant plugins they rolled out. Approving an assistant only stated that it is safe, so everybody still had to switch it on themselves. An approval can now also enable the assistant, either as a default which you may switch off again, or in a way your IT department keeps in place. The plugin page and the security card of the assistant tell you which of the two applies.
- Added knowledge about the latest AI models. AI Studio now recognizes Qwen 3.8 Flash, GLM-5.3 Flash, Meta's Muse Glimmer, NVIDIA's Nemotron 3.5, Tencent's Hunyuan Hy3, Grok 4, Claude Opus 5 and Sonnet 5, and Gemini 3.6 and 3.7. It knows what each of them is capable of, so images, videos, tool usage, and reasoning are available right away instead of staying hidden.
- Added the IONOS AI Model Hub as a provider for chats and embeddings. It runs open-source models in Germany, is subject to the GDPR, and IONOS states that your data is not used for training.
- Added LiteLLM as a new LLM provider for chats, embeddings, and speech-to-text. LiteLLM is an AI gateway you run yourself in front of models from many providers. Because your gateway decides where your data goes, you set its trust level yourself. Thanks Prodman Devokadev (`prodmanpd`) for this first contribution.
- Added speech-to-text for Helmholtz Blablador and GroqCloud, and embeddings for GWDG SAIA. These providers offer these services now, so you can select them when you dictate a message or when you set up a data source.
- Improved the safety of plugin symbols: AI Studio now shows the symbol of a plugin in isolation, so nothing inside a symbol can reach the rest of the app.
- Improved how much memory AI Studio needs. Working with large documents used to grow the app to several gigabytes, and on macOS that memory was never handed back. AI Studio now stays at a fraction of that and returns memory to your system. This matters most on devices with little memory, such as a Raspberry Pi.

1
app/MindWork AI Studio/wwwroot/images/provider-icons/README.md
View File

@ -9,6 +9,7 @@ All provider icons are shipped with AI Studio and loaded locally. No icon trigge
- `openai*.svg` uses the OpenAI mark path from [Simple Icons 15.15.0](https://github.com/simple-icons/simple-icons/blob/15.15.0/icons/openai.svg) and black/white variants following the [OpenAI Design Guidelines](https://openai.com/brand/).
- `fireworks.svg` is adapted from the [Fireworks AI site icon](https://fireworks.ai/icon0.svg).
- `groq.svg` is adapted from the [Groq site icon](https://groq.com/favicon.svg).
- `litellm.svg` is the bullet train emoji from [Twemoji 17.0.3](https://github.com/jdecked/twemoji/tree/v17.0.3), licensed under [CC-BY 4.0](https://creativecommons.org/licenses/by/4.0/). LiteLLM has no mark of its own and identifies itself with that emoji. Retrieved on 2026-08-30.
- `provider*.svg` and `self-hosted*.svg` are neutral project-owned fallback graphics.
- `gwdg.svg`, `openrouter.svg`, `google.svg` and `helmholtz.svg` were created by taking the official logo from their respective websites as images and creating a svg from them.

1
app/MindWork AI Studio/wwwroot/images/provider-icons/litellm.svg Normal file
View File

@ -0,0 +1 @@
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 36 36"><path fill="#939598" d="M0 34h36v2H0z"/><path fill="#D1D3D4" d="M3 35h33V6H21c-4 0-5 2-5 2l-4 6S0 19 0 24c0 4 6 6 6 6l-3 5z"/><path fill="#231F20" d="M14 35l2-3h20v3z"/><path d="M0 23.999c0 4 6 6 6 6V17.125C3 19 0 21.499 0 23.999zM6 30v-.001V30z" fill="#3B88C3"/><path fill="#269" d="M6 30l-3 5h33v-5z"/><path fill="#3B88C3" d="M20 30l4-6h12v6z"/><path fill="#55ACEE" d="M26 8H16l-4 6h-.001 10.843c.477 0 1.108-.448 1.412-1l2.197-4c.303-.552.102-1-.451-1z"/><path fill="#3B88C3" d="M25.902 10l.549-1c.303-.552.102-1-.451-1H16l-1.333 2h11.235z"/></svg>
Side by Side

After

Width:  |  Height:  |  Size: 611 B

4
runtime/packaging/linux/org.mindworkai.AIStudio.metainfo.xml
View File

@ -31,8 +31,8 @@
<li>
Independence: You are not tied to any single provider. Choose the providers that best
suit your needs, including OpenAI, Perplexity, Mistral, Anthropic, Google Gemini, xAI,
DeepSeek, Alibaba Cloud, OpenRouter, Hetzner, IONOS, Hugging Face, Groq, Fireworks,
Helmholtz, GWDG, and self-hosted models.
DeepSeek, Alibaba Cloud, OpenRouter, Hetzner, IONOS, LiteLLM, Hugging Face, Groq,
Fireworks, Helmholtz, GWDG, and self-hosted models.
</li>
<li>
Assistants: Use ready-made assistants for common business and other tasks without writing prompts yourself.