Thibault Jaigu fe61acc5b2 Added Requesty as a provider ... Requesty is an OpenAI compatible AI gateway. The provider mirrors OpenRouter: chat completions over https://router.requesty.ai/v1/, the same project headers, and a model list read from both the managed policies (models/managed) and the full catalog (models), including the context window.		2026-09-25 10:04:02 +01:00
..
AlibabaCloud	Sorted every model list by what a model is made for (#984)	2026-09-19 17:54:10 +02:00
Anthropic	Added the exact token count for Anthropic and OpenAI (#1004)	2026-09-24 13:36:06 +02:00
DeepSeek	Rebuilt how AI Studio knows what a model can do (#960)	2026-09-13 14:17:25 +02:00
Fireworks	Added the exact token count where the provider reports it (#989)	2026-09-23 20:17:02 +02:00
Google	Sorted every model list by what a model is made for (#984)	2026-09-19 17:54:10 +02:00
Groq	Rebuilt how AI Studio knows what a model can do (#960)	2026-09-13 14:17:25 +02:00
GWDG	Sorted every model list by what a model is made for (#984)	2026-09-19 17:54:10 +02:00
Helmholtz	Rebuilt how AI Studio knows what a model can do (#960)	2026-09-13 14:17:25 +02:00
Hetzner	Rebuilt how AI Studio knows what a model can do (#960)	2026-09-13 14:17:25 +02:00
HuggingFace	Added the exact token count where the provider reports it (#989)	2026-09-23 20:17:02 +02:00
IONOS	Rebuilt how AI Studio knows what a model can do (#960)	2026-09-13 14:17:25 +02:00
LiteLLM	Rebuilt how AI Studio knows what a model can do (#960)	2026-09-13 14:17:25 +02:00
Mistral	Sorted every model list by what a model is made for (#984)	2026-09-19 17:54:10 +02:00
OpenAI	Added the exact token count for Anthropic and OpenAI (#1004)	2026-09-24 13:36:06 +02:00
OpenRouter	Sorted every model list by what a model is made for (#984)	2026-09-19 17:54:10 +02:00
Perplexity	Added the exact token count where the provider reports it (#989)	2026-09-23 20:17:02 +02:00
Reasoning	Added Requesty as a provider	2026-09-25 10:04:02 +01:00
Requesty	Added Requesty as a provider	2026-09-25 10:04:02 +01:00
SelfHosted	Sorted every model list by what a model is made for (#984)	2026-09-19 17:54:10 +02:00
X	Sorted every model list by what a model is made for (#984)	2026-09-19 17:54:10 +02:00
AdditionalApiParametersParser.cs	Added icons to visualize model capabilities to the provider dropdown menu (#829)	2026-07-04 18:28:52 +02:00
BaseProvider.cs	Added the exact token count for Anthropic and OpenAI (#1004)	2026-09-24 13:36:06 +02:00
Capability.cs	Rebuilt how AI Studio knows what a model can do (#960)	2026-09-13 14:17:25 +02:00
Confidence.cs	Added LiteLLM as a new LLM provider (#909)	2026-08-30 12:55:18 +02:00
ConfidenceLevel.cs	Add confidence levels (#140)	2024-09-11 23:08:02 +02:00
ConfidenceLevelExtensions.cs	Added local RAG (#756)	2026-09-09 18:43:37 +02:00
ContentStreamChunk.cs	Added the exact token count where the provider reports it (#989)	2026-09-23 20:17:02 +02:00
EmbeddingData.cs	Added embedding API (#654)	2026-02-20 15:32:54 +01:00
EmbeddingResponse.cs	Added embedding API (#654)	2026-02-20 15:32:54 +01:00
EmbeddingUsage.cs	Added embedding API (#654)	2026-02-20 15:32:54 +01:00
IAnnotationStreamLine.cs	Improved the OpenAI provider (#548)	2025-09-03 10:08:04 +02:00
ImageURL.cs	Spelling	2024-05-19 16:06:48 +02:00
IMessage.cs	Refactored chat requests (#607)	2025-12-28 14:10:20 +01:00
IMessageBase.cs	Refactored chat requests (#607)	2025-12-28 14:10:20 +01:00
IProvider.cs	Added local RAG (#756)	2026-09-09 18:43:37 +02:00
IResponseStreamLine.cs	Added the exact token count where the provider reports it (#989)	2026-09-23 20:17:02 +02:00
LLMProviders.cs	Added Requesty as a provider	2026-09-25 10:04:02 +01:00
LLMProvidersExtensions.cs	Added Requesty as a provider	2026-09-25 10:04:02 +01:00
LLMProvidersIconExtensions.cs	Added Requesty as a provider	2026-09-25 10:04:02 +01:00
MessageBaseConverter.cs	Refactored chat requests (#607)	2025-12-28 14:10:20 +01:00
Model.cs	Added IONOS as a provider and unified how providers sort their model lists (#941)	2026-08-29 20:45:39 +02:00
ModelKind.cs	Sorted every model list by what a model is made for (#984)	2026-09-19 17:54:10 +02:00
ModelLoadFailureReason.cs	Fixed error messages for provider requests (#778)	2026-05-25 17:32:54 +02:00
ModelLoadFailureReasonExtensions.cs	Fixed error messages for provider requests (#778)	2026-05-25 17:32:54 +02:00
ModelLoadResult.cs	Improved error handling for model loading (#732)	2026-04-14 13:39:11 +02:00
NoChatCompletionAnnotationStreamLine.cs	Improved the OpenAI provider (#548)	2025-09-03 10:08:04 +02:00
NoProvider.cs	Rebuilt how AI Studio knows what a model can do (#960)	2026-09-13 14:17:25 +02:00
NoResponsesAnnotationStreamLine.cs	Improved the OpenAI provider (#548)	2025-09-03 10:08:04 +02:00
ProviderJsonOptions.cs	Stream the answers again whenever tools are in play (#986)	2026-09-20 10:44:33 +02:00
ProviderRequestException.cs	Fixed error messages for provider requests (#778)	2026-05-25 17:32:54 +02:00
ProviderRequestFailureReason.cs	Fixed model capabilities and how model names are matched (#958)	2026-09-11 15:24:02 +02:00
ProviderRequestFailureReasonExtensions.cs	Added local RAG (#756)	2026-09-09 18:43:37 +02:00
ProviderToolAdapters.cs	Fixed tool calling with Groq and OpenRouter (#1003)	2026-09-24 12:08:54 +02:00
ReasoningIndicatorState.cs	Added icons to visualize model capabilities to the provider dropdown menu (#829)	2026-07-04 18:28:52 +02:00
ServerSentEvent.cs	Stream the answers again whenever tools are in play (#986)	2026-09-20 10:44:33 +02:00
SubContentConverter.cs	Added support for images (#609)	2025-12-30 18:30:32 +01:00
SubContentImageUrlConverter.cs	Added support for images (#609)	2025-12-30 18:30:32 +01:00
SubContentType.cs	Added support for images (#609)	2025-12-30 18:30:32 +01:00
TokenUsage.cs	Added the exact token count where the provider reports it (#989)	2026-09-23 20:17:02 +02:00
TranscriptionResponse.cs	Implemented the transcription API (#623)	2026-01-11 16:02:28 +01:00
TranscriptionResult.cs	Fixed error messages for provider requests (#778)	2026-05-25 17:32:54 +02:00