How to Use DeepSeek API with SillyTavern

Open API Connections

1. Click the plug icon (API Connections) in the top bar.
2. Select Chat Completion from the API dropdown.
3. Choose OpenAI as the API type (or "Custom" / "OpenAI-compatible" depending on your version).

Configure the Endpoint

Fill in these fields exactly:

Important: The base URL must end with /v1. SillyTavern appends /chat/completions automatically.

Set the Model Name

Use exactly: deepseek-v4-flash

Do not add prefixes like openai/ or text-. Just the bare model ID.

Available models on this gateway:

• deepseek-v4-flash — Fast, great for chat/roleplay. Recommended for SillyTavern.
• deepseek-v4-pro — Higher capability, more expensive per token. Available on all plans.

Test the Connection

Click Connect or send a test message in your chat. If everything is configured correctly, you should get a response within seconds.

401 Unauthorized

Problem: Invalid or missing API key.

Fix: Check that your sk-gateway-... key is copied correctly — no extra spaces, no missing characters.

404 Not Found

Problem: The path does not exist.

Fix: Make sure your Base URL ends with /v1. SillyTavern calls /v1/chat/completions.

402 Payment Required

Problem: Your API budget is exhausted.

Fix: Buy a new package to get a fresh key with budget.

429 Too Many Requests

Problem: Exceeded rate limit (30 or 60 RPM depending on plan).

Fix: Wait 60 seconds and try again. Reduce auto-retry frequency in SillyTavern settings.

5xx Server Error

Problem: Gateway or upstream DeepSeek service temporarily unavailable.

Fix: Wait 1-2 minutes and retry.

Streaming

Streaming (SSE) is fully supported. Characters appear token-by-token. Make sure the Streaming toggle is enabled in your API connection settings.

Reasoning Content

This gateway filters reasoning_content by default. You only receive the final content field — exactly what SillyTavern expects. No stray thinking tokens in your character replies.