TavernAPI vs OpenRouter for SillyTavern
OpenRouter is a general-purpose gateway with 400+ models and credit card checkout, while TavernAPI is built specifically for SillyTavern roleplay with 20%–40% lower prices on Claude and Gemini, server-locked storytelling presets, automatic prompt caching on Custom endpoints, and no 5.5% top-up fee.
| Feature | TavernAPI | OpenRouter |
|---|---|---|
| Focus | 5 official 1M-context roleplay models (Claude, Gemini, DeepSeek) | 400+ general-purpose models |
| Model pricing | Claude & Gemini 20%–40% below official rates; DeepSeek V4 Pro at one flat rate 24/7 | Official list rates passed through |
| Roleplay presets | Yes — import our SillyTavern preset with editable toggles & server-locked core blocks | No — bring and maintain your own local presets |
| Top-up fee & packs | No top-up fee, plus optional 30-day discount credit packs ($9→$10, $19→$23, $39→$48) | 5.5% fee on cards ($0.80 min), 5% on crypto |
| Prompt caching over Custom OpenAI endpoint | Automatic server-side breakpoints on every chat | Requires specific source/header setup in SillyTavern |
| Cache savings shown in console | Yes — exact USD saved displayed on Usage page | No dedicated savings counter |
| Upstream provider consistency | Official channels only (AWS/GCP, Google AI Studio, DeepSeek official API) | Rotates across multiple providers with varying filter strictness |
| Payment methods | Crypto (USDT/USDC) and redeem codes | Credit cards, Alipay, USDC |
When OpenRouter is the better choice
- You want to experiment with dozens of small open-weight models (Llama, Qwen, Mistral) alongside closed models.
- You prefer paying directly with a traditional credit card and don't mind the 5.5% top-up fee.
- You already maintain your own local SillyTavern presets and don't need Claude or Gemini discounts.
When TavernAPI is the better choice
- You mainly play with Claude Opus 5.5, Gemini 4 Argon, Gemini 3.8 Flash, or DeepSeek V4 Pro and want official 1M-context routing at 20%–40% off Claude and Gemini list prices.
- You want a ready-made SillyTavern preset where you can still toggle word count, language, and anti-impersonation rules locally while the core writing blocks expand on the server.
- You want automatic prompt caching that works cleanly over SillyTavern's Custom endpoint, with a console that shows how much money caching saved you.
- You prefer non-expiring pay-as-you-go balance or manual 30-day discount credit packs ($9 for $10, $19 for $23, $39 for $48) without a 5.5% top-up fee.
Common questions
How do I use TavernAPI presets in SillyTavern?
Download a TavernAPI preset JSON from the Presets page in our console, import it into SillyTavern's AI Response Configuration panel, and select a standard model ID like gemini-4-argon or claude-opus-5.5. You can freely toggle or edit plain-text rules (word count, output language, anti-impersonation) in SillyTavern, while locked core entries ([[tav:pack/block]]) expand automatically on our server. No plugins are needed, and you can also skip the preset to use your own local setup.
How do I unlock the Standard and Pro presets?
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 spend reaches $25.
How do I get the $0.30 free trial credit?
You receive $0.30 in free trial credit automatically after signing in and verifying your email address (or signing in with a verified Google or Discord account). Trial credit works right away on Gemini 3.8 Flash (gemini-3.8-flash) and Gemini 4 Argon (gemini-4-argon).
Does TavernAPI store or read my roleplay messages?
No, TavernAPI does not store your message content, character cards, or model replies. Our database records only the timestamp, model name, input/cached/output token counts, latency, and cost for each request so you can check your usage.
Why don't you offer GPT models?
We intentionally exclude GPT models because they tend to produce stiff, repetitive, and overly moralizing prose in roleplay. We focus strictly on the five official 1M-context models that roleplay communities actually prefer: Claude Opus 5.5, Gemini 4 Argon, Gemini 3.8 Flash, DeepSeek V4 Pro, and Claude Sonnet 5.5.