SillyTavern with a custom OpenAI-compatible API: connect Heabsy
In SillyTavern open API Connections, choose Chat Completion with the source "Custom (OpenAI-compatible)", enter https://api.heabsy.com/v1 as the endpoint and your Heabsy key, then pick a model such as qwen38-queen. Our roleplay and uncensored models run in the EEA and do not store your chats.
API: Chat Completion
Chat Completion Source: Custom (OpenAI-compatible)
Custom Endpoint: https://api.heabsy.com/v1
Custom API Key: <your Heabsy key>
Model: qwen38-queenhttps://api.heabsy.com/v1 · Anthropic base URL https://api.heabsy.comStep by step
- Click the plug icon (API Connections).
- API: Chat Completion. Chat Completion Source: Custom (OpenAI-compatible).
- Custom Endpoint:
https://api.heabsy.com/v1— with/v1, without/chat/completions. - Custom API Key: your Heabsy key. Click Connect; the model list loads from
/v1/models. - Choose a model and send a test message.
If the model ignores roles or repeats itself
Some models want a strict order of roles. Under Prompt Post-Processing pick a stricter mode, such as a single system message or strict user/assistant alternation, and try again.
Which model should I pick?
For roleplay and creative writing: qwen38-queen stays in character without out-of-character disclaimers. Uncensored variants with refusals removed — glm-5.3-uncensored, qwen38-unc, glm53-flash-unc, mimo-v26-flash-unc — follow instructions without lecturing; moderation is on you. All of them run in the EEA and do not store prompts or completions.
| Model | ID | Context | Max output | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| Qwen3.8 27B Fable | qwen38-fable | 512K | 32K | $0.095 | $0.58 |
| Qwen3.8 27B Queen | qwen38-queen | 512K | 32K | $0.095 | $0.58 |
| GLM 5.3 Flash Uncensored | glm53-flash-unc | 1M | 128K | $0.1739 | $0.6957 |
| MiMo V2.6 Flash Uncensored | mimo-v26-flash-unc | 1M | 64K | $0.4404 | $1.4285 |
| MiMo V2.6 Flash | mimo-v26-flash | 1M | 64K | $0.4762 | $1.4286 |
| MiMo V2.6 Flash Abliterated | mimo-v26-flash-abl | 1M | 64K | $0.4762 | $1.4286 |
| GLM 5.3 | glm53 | 1M | 128K | $0.5217 | $0.9565 |
| Qwen3.8 27B Uncensored Fast by Heabsy | qwen38-unc-fast | 512K | 230K | $0.7904 | $2.4952 |
| Qwen3.8 27B Uncensored | qwen38-unc | 1M | 230K | $0.8095 | $2.5238 |
| Qwen3.8 27B | qwen38 | 256K | 32K | $1.00 | $3.00 |
| GLM 5.3 Uncensored | glm-5.3-uncensored | 1M | 128K | $1.1905 | $2.1429 |
| CyberHeabsy | cyberheabsy | 1M | 64K | $1.4286 | $4.2857 |
All models above run on Heabsy hardware in the EEA; prompts and completions are not stored. Thecatalog also lists 23 partner-hosted models — Claude, GPT-6, Kimi K3, DeepSeek V4 and others — with the same key and invoice, but without zero data retention and without an EEA guarantee.
Verify it works
Click Test Message in API Connections. A short reply means the endpoint, key and model work; the request also appears in the Logs page of your console.
If the tool shows an error you cannot read, test the key on its own first — one short request outside the tool:
curl https://api.heabsy.com/v1/chat/completions \
-H "Authorization: Bearer $HEABSY_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"qwen38","max_tokens":16,"messages":[{"role":"user","content":"Say hi"}]}'Troubleshooting
| What you see | What to change |
|---|---|
| Status check fails although the key is right | Enable "Bypass API status check" and send a message; some checks call endpoints other than chat. |
| 404 Not Found | The endpoint ends in /chat/completions or lacks /v1. Use https://api.heabsy.com/v1. |
| Empty model list | The key is missing or wrong. You can also type the model ID by hand. |
| 403 with an HTML page ("Sorry, you have been blocked") | No key was sent at all: the key variable is empty or not set where the tool runs. Requests without a key are stopped before they reach the API; a wrong key gets a JSON 401 instead. |
Where do my prompts go?
From SillyTavern straight to api.heabsy.com. On our own models the request is processed in the European Economic Area and the text is not stored — we keep what billing needs: the model, the token counts and the time. Partner-hosted models are processed by third-party inference providers; each is marked in the catalog, and none of them carries the no-retention promise. The terms are in the data processing agreement, the invoice comes from an EU company.
FAQ
Which Heabsy model is best for SillyTavern roleplay?+
Start with qwen38-queen: tuned for roleplay and creative writing, a 524,288-token window, $0.095 per million input and $0.58 per million output tokens. For fewer refusals, try glm-5.3-uncensored or qwen38-unc.
Are my chats logged?+
Not on our own models: prompts and completions are not stored, and processing happens in the EEA. We keep the billing data — tokens, model and time — not the text.
Can I pay as I go?+
Yes. You top up a balance and pay per token; there is no subscription and no minimum.
Does the long context really work in SillyTavern?+
Set Context Size in SillyTavern's generation settings to what you need, up to the model's window from the table. A longer context costs more per message, so most chats use far less than the maximum.
Also set up:n8n · OpenCode · Claude Code
SillyTavern is an open-source project; Heabsy is not affiliated with it.