Open WebUI with an OpenAI-compatible API: connect Heabsy
Open WebUI connects to any OpenAI-compatible API. In Admin Settings → Connections add an OpenAI API connection with URL https://api.heabsy.com/v1 and your Heabsy key, or start the container with OPENAI_API_BASE_URL and OPENAI_API_KEY. The model menu fills itself from /v1/models.
docker run -d -p 3000:8080 \
-e OPENAI_API_BASE_URL="https://api.heabsy.com/v1" \
-e OPENAI_API_KEY="$HEABSY_API_KEY" \
-v open-webui:/app/backend/data \
--name open-webui ghcr.io/open-webui/open-webui:mainhttps://api.heabsy.com/v1 · Anthropic base URL https://api.heabsy.comIn the interface
- Admin Panel → Settings → Connections → Manage OpenAI API Connections → Add.
- URL
https://api.heabsy.com/v1— without/chat/completions. Key: your Heabsy key. - Leave Model IDs empty to load the list from
/v1/models, or enter IDs by hand to show only some models.
Environment variables and the interface
A connection saved in the interface overrides the environment variables — if a changed variable seems to be ignored, edit the connection instead. Several providers at once: OPENAI_API_BASE_URLS and OPENAI_API_KEYS, separated by semicolons.
Which model should I pick?
For teams that put internal documents into chats, our own models matter most: processing in the EEA, prompts and completions not stored. Open WebUI's built-in tools work best with models that support tool calling — all models in the table do.
| 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
Open the model menu: Heabsy models appear by ID. Send a message; the request also appears in the Logs page of your Heabsy 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 |
|---|---|
| No models in the menu | Check the key and that the URL ends in /v1; or list the model IDs by hand in the connection. |
| Changed environment variables have no effect | The connection saved in the interface wins. Edit or delete it there. |
| 404 Not Found | The URL contains /chat/completions. Use https://api.heabsy.com/v1. |
| 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 Open WebUI 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
Do uploaded documents leave our server?+
Retrieval runs inside Open WebUI with its own embedding model; only the passages it selects go to the chat model with the question. With our own models those requests are processed in the EEA and not stored.
Can a whole team share one key?+
Yes, but separate keys per team or department give each its own budget and model allow-list in the Heabsy console.
Which model should be the default?+
qwen38 for general work and documents with images; glm53 when chats get very long — it has a 1,048,576-token window.
Also set up:LibreChat · SillyTavern · LangChain
Open WebUI is an open-source project; Heabsy is not affiliated with it.