One API for SillyTavern. About 8,000 DeepSeek V4.1 Flash messages for $10.

Set Chat Completion to Custom (OpenAI-compatible), paste one endpoint and one key, and pick DeepSeek, Gemini or Claude from the model list. Pay for what you use, with credit that never expires.

Your API Connections settings

API: Chat Completion
Chat Completion Source: Custom (OpenAI-compatible)
Custom Endpoint (Base URL): https://api.apisrouter.com/v1
Custom API Key: sk-your-apisrouter-key
Enter a Model ID: deepseek-v4.1-flash

What $10 buys

One message in a running chat: about 8,000 tokens of character card and history in, 400 out, priced without caching.

  • DeepSeek V4.1 Flash (deepseek-v4.1-flash): 8,000 messages for $10, $1.24 per 1,000 messages. The lowest cost here, so long chats stay cheap.
  • DeepSeek V4 Pro (deepseek-v4-pro): 2,000 messages for $10, $5 per 1,000 messages. DeepSeek's larger model, for replies that need more thought.
  • Gemini 3.8 Flash (gemini-3.8-flash): 1,600 messages for $10, $6 per 1,000 messages. Google's Gemini, for a different writing voice.
  • Claude Sonnet 4.6 (claude-sonnet-4-6): 400 messages for $10, $24 per 1,000 messages. Anthropic's Sonnet, between DeepSeek and Opus in price.
  • Claude Opus 5.5 (claude-opus-5-5): 300 messages for $10, $30.40 per 1,000 messages. Anthropic's Opus, for scenes where every line matters.

Set it up in one minute

  • Get a key: Start on the $2 trial credit, or top up from $10 below and the key arrives by email.
  • Open API Connections: Click the plug icon. Set API to Chat Completion and Chat Completion Source to Custom (OpenAI-compatible), not the plain OpenAI source.
  • Paste the endpoint and key: Custom Endpoint is https://api.apisrouter.com/v1, with nothing after /v1: SillyTavern adds /chat/completions itself. Paste your key under Custom API Key.
  • Connect and pick a model: Click Connect. When the light turns green, the model list fills in; pick a model and send a message.

If it does not connect

  • 404: The endpoint must end exactly at /v1: nothing after it, such as /chat/completions, and /v1 itself not missing.
  • 401: The key is incomplete, quoted or has a space at either end. Paste it again.
  • Empty model list: The source is plain OpenAI instead of Custom (OpenAI-compatible), or the endpoint or key is wrong. Fix those, then click Connect again.

Two ways to pay

Both fill one balance, spent as you chat. Pay as you go from $10 with no account, with +30% on the first top-up.

FAQ

What is the best API for SillyTavern?

For everyday roleplay, DeepSeek V4.1 Flash: about 8,000 messages for $10. For scenes that need more care, Claude Sonnet 4.6 or Claude Opus 5.5. With one APIsRouter key you switch between them in the model list, with no second account.

How much does a SillyTavern API cost?

Through APIsRouter, $10 buys about 8,000 messages on DeepSeek V4.1 Flash and about 300 on Claude Opus 5.5, for messages the size shown above; longer chats cost more per message.

Is there a free API for SillyTavern?

You can start on a $2 trial credit: sign in and claim it from your dashboard, no card needed. That covers about 1,600 DeepSeek V4.1 Flash messages. When it runs out, top up from $10.

How do I use Claude in SillyTavern?

Keep the Custom (OpenAI-compatible) source and pick a Claude model, such as claude-sonnet-4-6, from the list. One key covers Claude, DeepSeek and Gemini.

Why is my model list empty?

SillyTavern fills the list from the endpoint when you click Connect. An empty list means the endpoint does not end at /v1, the key is wrong, or the source is plain OpenAI.

Do unused credits expire?

No. Credit stays in your balance until you use it, and requests stop when it runs out, so there are no surprise bills.