Compatible (BYOK)Use SillyTavern with GlideflowAI.
A flexible local front end for character chat and roleplay. Connect it through GlideflowAI's OpenAI-compatible API with a key you control.
What this connection is for
SillyTavern is a locally run chat front end centered on character cards, personas, lore, and long-form roleplay. Its appeal is the amount of control it gives a user over the chat experience: prompts, character context, presentation, extensions, and the model connection can be managed as parts of one personal setup. It is a front end, not a hosted model provider.
For roleplay, the quality of a session depends on more than a model name. Character instructions, context budgeting, memory choices, sampling settings, and the sensitivity of content all affect the result. A careful user starts with a simple character and a short conversation, then changes one variable at a time. That is more reliable than carrying a complex preset between unrelated model providers.
SillyTavern commonly supports OpenAI-compatible backends, so GlideflowAI is listed as Compatible (BYOK). Because labels and connection panes can change with extensions and releases, this gallery keeps the instruction protocol-level rather than claiming a permanent menu path. This connection does not mean SillyTavern endorses or partners with GlideflowAI.
Why pair it with GlideflowAI
Use one key for an OpenAI-compatible chat back end and other compatible tools, while keeping the roleplay interface local to your own setup.
The public model catalog and USD prices help you test a model with clear expectations before you invest time refining a character preset.
Setup
Use a new API key for the tool, select a model from the catalog, and begin with a small task. Do not put a key in a repository, screenshot, or shared configuration file.
Open SillyTavern's API connection panel
In your installed version, choose its supported OpenAI-compatible or custom OpenAI connection route. Extensions can affect the labels, so follow the current SillyTavern documentation for the exact panel.
Enter the compatible endpoint and key
Set the base URL, then enter a GlideflowAI key and select or type an exact available model ID.
Base URL : https://api.glideflowai.com/v1 API key : sk-your-key Model ID : glm-5.2Test before importing a complex preset
Send a simple message with a short character card. If it works, tune context and generation settings gradually rather than importing secrets into shared preset files.
Before you begin: Manual check: confirm the API connection route and URL field in the SillyTavern release and extensions you use.
Need the endpoint basics? Read authentication, browse the model catalog, or compare pricing.
Frequently asked questions
Is SillyTavern itself a model provider?
No. It is a front end that can connect to supported model back ends selected and configured by the user.
Can I publish a preset with my key?
Never. Remove keys from screenshots, character cards, backups, and any file you share.
Why is this Compatible rather than Verified?
The protocol is a fit, but the exact UI and extensions are user-specific and not represented here as an end-to-end test.
Ready to connect SillyTavern?
Create a key, use the setup above, and verify the connection on a small task before you scale it up.
