Connect SillyTavern to QCode

Chat with QCode.cc's Claude / GPT models in SillyTavern; an honest note on whether gpt-image-2 image generation can be connected, plus alternatives

Connect SillyTavern to QCode¶

SillyTavern is a popular local LLM frontend focused on role-play and multi-turn conversations. It supports connecting to all kinds of chat models and ships with extensions for image generation, TTS, and more. This guide explains how to use QCode.cc's models in SillyTavern.

Bottom line first¶

1. Chat with QCode's Claude models¶

SillyTavern's Claude integration includes a built-in "Reverse Proxy" option, which is exactly what you use to point at QCode:

1. Open API Connections (the plug icon) → Chat Completion.
2. Set Chat Completion Source to Claude.
3. Check Use a reverse proxy.

4. Fill in:

5. Proxy Server URL: https://api.qcode.cc/api (in mainland China, prefer https://asia.qcode.cc/api)

6. Proxy Password: your QCode API Key (starts with cr_)
7. Model: select / enter claude-opus-4-8, claude-sonnet-4-6, claude-haiku-4-5, etc.
8. Click Connect; once connected you can chat in your character cards.

QCode's Anthropic protocol prefix is /api, and SillyTavern automatically appends it into /api/v1/messages. The BASE_URL must not have a trailing slash.

2. Chat with QCode's GPT models¶

Use the OpenAI-compatible endpoint:

1. API Connections → Chat Completion.
2. Set Chat Completion Source to Custom (OpenAI-compatible).

3. Fill in:

4. Custom Endpoint (Base URL): https://api.qcode.cc/openai/v1 (in mainland China, prefer https://asia.qcode.cc/openai/v1)

5. API Key: your QCode API Key
6. Model: enter gpt-5.5, gpt-5.4, gpt-5.3-codex, etc.
7. Click Connect.

A single API Key works across all three protocols (Anthropic / OpenAI / Gemini); the protocol is determined by the path. See Endpoints and API formats.

3. About image-2 generation (an honest note)¶

Many users ask: Can I connect QCode's gpt-image-2 to SillyTavern for character portraits / illustrations?

Not for now. Why:

• SillyTavern's image generation (the Stable Diffusion extension) only supports a fixed set of backends: ComfyUI, Stable Diffusion WebUI (AUTOMATIC1111 / Forge), NovelAI, Stability AI, OpenAI (DALL·E), Pollinations, and so on.
• It does not have a "custom OpenAI-compatible image endpoint" option — meaning you cannot, the way you do for chat, give image generation a custom base_url pointing at QCode's /v1/images/generations.
• There is already a community feature request #4851 ("Add custom openai compatible endpoint for the image generation extension"), but it is not yet implemented.

Its built-in "OpenAI" image source is hardwired to api.openai.com's DALL·E and cannot have its base URL changed, so it cannot be repurposed to reach gpt-image-2 either.

Alternatives¶

If you want to use QCode's gpt-image-2 (its text rendering is currently the strongest among publicly available image models), you can:

• Use the official OpenAI SDK / any tool that supports a custom images endpoint to call it directly: base https://api.qcode.cc/qcode-img/v1, model gpt-image-2, reusing the same QCode Key. See gpt-image-2 image generation.
• Track the progress of SillyTavern issue #4851; once a custom OpenAI-compatible image endpoint is supported, you can fill in QCode's image endpoint the same way as for "chat" on this page.

FAQ¶

Q: Connection returns 401 / 403? A: Check that the API Key is correct and not expired. Claude uses the "Proxy Password" field, while OpenAI-compatible uses the "API Key" field — don't put it in the wrong place.

Q: Unstable network in mainland China? A: Switch the BASE_URL domain to asia.qcode.cc (Hong Kong node, low latency nearby); if that's unstable, switch to api.qcode.cc (global routing).

Q: Can I look up my request records? A: Yes. Requests across all domains are reported to probe.qcode.cc; enter your API Key to view them.

Want one plan that covers Claude Code, Codex, and third-party clients like this all at once? Check out QCode.cc pricing — one API Key works across all three protocols.