Use Obscurify.ai with SillyTavern

SillyTavern can talk to Obscurify.ai through its Custom (OpenAI-compatible) source, so your characters and chats stay in your own SillyTavern install while the model runs through Obscurify.ai.

You need an Obscurify.ai account (a random account number, no email) and its API key: create an account, then click Show API Key on the account page. The API works on every plan with a positive balance. New accounts get $1 of starter credit.

Connect

  1. In SillyTavern, open API Connections.
  2. Select Chat Completion.
  3. Select Custom (OpenAI-compatible) as the source.
  4. Enter https://obscurify.ai/v1 as the endpoint (the API root, not /chat/completions).
  5. Paste your API key (sk-obs1_...) and click Connect.
  6. Pick a model from the fetched list, for example deepseek/deepseek-v4-flash, or type a <lab>/<model> ID from the model list.
  7. Click Test Message.

What works

  • Model list: fetched from /v1/models.
  • Streaming: yes.
  • Tool calling: yes, on models that support it.
  • Vision: yes, on vision models.
  • Reasoning: set a reasoning effort; the reasoning text comes back in the reasoning field.

Plans

Prices per model are on the model list, and each model has its own page with its price and the plan it needs. Frontier models need the Casual plan; uncensored models need Pro. See pricing.

Support

Questions or problems: contact us (email optional).

Last checked with SillyTavern 1.19.0 on 2026-10-23.