Frequently Asked Questions

In SillyTavern, open API Connections (the plug icon), select Chat Completion and Custom (OpenAI-compatible), set the URL to https://tavernapi.com/v1, paste your sk-tav-... API key, and click Connect. Then select your model ID—such as gemini-4-argon or claude-opus-5.5—from the Available Models dropdown.

Download a preset JSON from the Presets tab in the TavernAPI console and import it into SillyTavern's AI Response Configuration panel (the sliders icon). Customizable rules like word count, output language, and anti-impersonation are plain text you can freely toggle or edit in SillyTavern, while locked core entries contain [[tav:pack/block]] placeholders that our server replaces with the full writing instructions when you send a message. No plugins are required.

Your first top-up of $5 or more permanently unlocks the Standard preset. The Pro preset can be unlocked in three ways: buy it standalone for $4.99, use it for free while an active $19 or $39 30-day credit pack is in effect, or unlock it permanently once your cumulative real-money spend reaches $25.

Yes. Using our preset is completely optional—if you keep your own local SillyTavern preset or connect from another OpenAI-compatible app (such as RisuAI, Agnaistic, Chub AI, or JanitorAI's Proxy), our gateway forwards your prompt straight to the official 1M-context model with automatic prompt caching. Only the locked [[tav:pack/block]] preset files require SillyTavern.

Regular pay-as-you-go balance added via crypto top-ups or redeem codes never expires. If you want extra credit without a recurring subscription, you can manually buy a 30-day credit pack: pay $9 for $10, $19 for $23 (Recommended), or $39 for $48. Pack credits work on all five models, never auto-renew, and remain valid for 30 days from purchase.

Our Claude and Gemini models cost 20%–40% less than official list rates: Claude Opus 5.5 is $2.80/$14 per 1M tokens (30% off), Sonnet 5.5 is $1.60/$8 (20% off), Gemini 4 Argon is $1.20/$6 (40% off), and Gemini 3.8 Flash is $0.49/$2.45 (~35% off). DeepSeek V4 Pro runs on the official DeepSeek API at a single flat rate 24/7 ($1.49/$4.49, close to official peak pricing).

Our server places cache breakpoints on your system/preset prefix, character card, and conversation history so upstream providers reuse those tokens at a 90%–95% discount on subsequent replies. In a typical 50-reply, 32k-context session on Claude Opus 5.5 (~1.6M input and 20k output tokens), caching lowers the total cost from roughly $4.76 to about $1.03.

New accounts receive $0.30 in free trial credit automatically after verifying an email address or signing in with a verified Google or Discord account. You can use the trial credit immediately on Gemini 3.8 Flash (gemini-3.8-flash) and Gemini 4 Argon (gemini-4-argon).

No, TavernAPI never stores your prompt text, character cards, lorebooks, or model completions in our database. We log only request metadata—timestamp, model ID, input/cached/output token counts, latency, HTTP status, and USD cost—so you can track your spending.

No, TavernAPI is not an uncensored model host because all requests run through official upstream channels (Anthropic via AWS/GCP, Google AI Studio, and the official DeepSeek API) whose safety classifiers still apply. While our presets establish clear fictional context to reduce false refusals on mature drama or dark fantasy, prompts that trigger upstream safety filters will still be declined.

No, we do not suspend or ban accounts simply because an upstream model refused a creative writing or mature roleplay prompt. Accounts are only suspended for severe violations of our Acceptable Use Policy, such as child sexual abuse material (CSAM), non-consensual content involving real people, or cyberattacks.

You can reach us on Telegram at @TavernAPI, on Discord by adding username alexovout, or by emailing support@tavernapi.com. Never send your full sk-tav-... API key—the last 4 characters shown in the console are enough.