n8n with an OpenAI-compatible model: connect Heabsy
n8n reaches any OpenAI-compatible API through its OpenAI credential: set the Base URL to https://api.heabsy.com/v1, paste your Heabsy key, and use the OpenAI Chat Model sub-node in an AI Agent or Basic LLM Chain with a model ID such as qwen38. Keep "Use Responses API" off — Heabsy serves Chat Completions.
API Key: <your Heabsy key>
Organization ID: (empty)
Base URL: https://api.heabsy.com/v1https://api.heabsy.com/v1 · Anthropic base URL https://api.heabsy.comStep by step
- Credentials → Add credential → OpenAI. API Key: your Heabsy key; Organization ID: empty; Base URL:
https://api.heabsy.com/v1. - In your workflow add an AI Agent (or Basic LLM Chain) and attach the OpenAI Chat Model sub-node with this credential.
- Model: choose "By ID" and enter the catalog ID, for example
qwen38. - Leave "Use Responses API" off. Heabsy answers
/v1/chat/completions; the Responses endpoint returns 404. - Set Max Retries to 0 or 1, so a failing step does not repeat a paid request several times.
Which model should I pick?
AI Agent nodes call tools, so pick a model with tool calling. For extraction and classification steps the cheapest own model in the table is often enough. Our own models run in the EEA and do not store prompts — useful when workflows process customer data.
| 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
Run the node once with a short prompt. The output appears in the node, and the request 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 |
|---|---|
| 404 Not Found | "Use Responses API" is on, or the base URL lacks /v1. |
| Model list stays empty | Select "By ID" and type the model ID; the list depends on the node version. |
| The agent never calls tools | The model has no tool calling. Pick one from the table. |
| 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 n8n 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
Does this work in n8n Cloud and self-hosted n8n?+
Yes. The credential only needs outbound HTTPS to api.heabsy.com.
Is customer data processed in the EU?+
With our own models, yes: processing in the EEA, prompts and completions not stored, invoice from an EU company. Partner models are marked separately and do not carry that guarantee.
Can I use one key for several workflows?+
Yes, and you can create separate keys per workflow with their own budgets and model restrictions in the console, so one runaway loop cannot spend everything.
Also set up:Claude Code · SillyTavern · OpenCode
n8n is a trademark of n8n GmbH; Heabsy is not affiliated with it.