{"id":419,"date":"2026-11-02T18:52:46","date_gmt":"2026-11-02T10:52:46","guid":{"rendered":"https:\/\/qoraapi.com\/blog\/sillytavern-claude-api-cheap\/"},"modified":"2026-11-02T20:36:08","modified_gmt":"2026-11-02T12:36:08","slug":"sillytavern-claude-api-cheap","status":"publish","type":"post","link":"https:\/\/qoraapi.com\/blog\/sillytavern-claude-api-cheap\/","title":{"rendered":"How to Use Claude in SillyTavern for 70% Less (2026 Setup Guide)"},"content":{"rendered":"

Claude is the favorite model for roleplay in SillyTavern, and it is also the one that drains your wallet fastest. Long character cards, lorebooks and chat history mean every reply resends thousands of tokens. This guide shows how to keep using Claude (and GPT or Gemini) in SillyTavern for about 70% less by connecting it to an OpenAI-compatible gateway.<\/p>\n

Why SillyTavern gets expensive<\/h2>\n

SillyTavern sends the whole prompt on every message: system prompt, character card, persona, lorebook entries, example dialogue and as much chat history as fits in your context setting. A typical roleplay turn with a 16k context easily sends 10,000 to 15,000 input tokens and gets back 300 to 800 output tokens.<\/p>\n

At official Claude Opus prices ($5 per million input tokens, $25 per million output), a session of 200 messages at 12,000 input and 500 output tokens costs about $14.50<\/strong>. Heavy users run several of those a week.<\/p>\n

The cheaper route: an OpenAI-compatible gateway<\/h2>\n

Qora API<\/a> gives you one API key for 350+ models, with Claude Opus, Sonnet and Haiku, GPT and Gemini at around 30% of official prices. Because it speaks the standard OpenAI format, SillyTavern connects to it with the built-in Custom (OpenAI-compatible) source. No extensions needed.<\/p>\n\n\n\n\n\n\n\n
Same 200-message session<\/th>\nOfficial price<\/th>\nQora API (30%)<\/th>\n<\/tr>\n<\/thead>\n
Claude Opus<\/td>\n$14.50<\/td>\nabout $4.35<\/td>\n<\/tr>\n
Claude Sonnet<\/td>\nabout $8.70<\/td>\nabout $2.60<\/td>\n<\/tr>\n
Claude Haiku<\/td>\nabout $2.90<\/td>\nabout $0.87<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

Exact per-model prices are listed on the Qora API pricing page<\/a>.<\/p>\n

Step-by-step setup in SillyTavern<\/h2>\n
    \n
  1. Get a key.<\/strong> Create an account at qoraapi.com<\/a>, open the console and create an API key. New users can get $5 of free credit<\/strong> by DMing @QoraAPI<\/a> on X or emailing support@qoraapi.com.<\/li>\n
  2. Open API Connections.<\/strong> In SillyTavern, click the plug icon at the top.<\/li>\n
  3. Choose the API type.<\/strong> Set API to Chat Completion<\/em>, and Chat Completion Source to Custom (OpenAI-compatible)<\/em>.<\/li>\n
  4. Enter the endpoint.<\/strong> In Custom Endpoint (Base URL) enter https:\/\/qoraapi.com\/v1<\/code>.<\/li>\n
  5. Paste your key<\/strong> into Custom API Key.<\/li>\n
  6. Pick a model.<\/strong> Click Connect, then choose a model from the list or type its ID, for example claude-opus-4-7<\/code>, claude-sonnet-4-6<\/code> or deepseek-chat<\/code>.<\/li>\n
  7. Send a test message.<\/strong> If you get a reply, you are done.<\/li>\n<\/ol>\n

    Five more ways to cut your SillyTavern bill<\/h2>\n