LibreChat custom endpoint: connect Heabsy in librechat.yaml

LibreChat adds OpenAI-compatible providers as custom endpoints in librechat.yaml. Add a Heabsy entry with baseURL: https://api.heabsy.com/v1, the key from .env, fetch: true for the model list, and a titleModel that exists in our catalog — the default title model would fail on every new chat.

librechat.yaml

endpoints:
  custom:
    - name: "Heabsy"
      apiKey: "${HEABSY_API_KEY}"
      baseURL: "https://api.heabsy.com/v1"
      models:
        default: ["qwen38"]
        fetch: true
      titleConvo: true
      titleModel: "qwen38-fable"
      modelDisplayLabel: "Heabsy"

Create a Heabsy key OpenAI base URL https://api.heabsy.com/v1 · Anthropic base URL https://api.heabsy.com

Step by step

Put HEABSY_API_KEY=<your key> into LibreChat's .env.
Add the block above to librechat.yaml. With Docker, mount the file through docker-compose.override.yml.
Restart LibreChat. Heabsy appears as an endpoint; fetch: true loads the models your key may call.
LibreChat appends /chat/completions to baseURL itself — keep the URL ending in /v1.

Parameters a model rejects

If a model returns an error for a parameter LibreChat sends by default, list it under dropParams in the endpoint block.

Which model should I pick?

qwen38-fable makes a cheap title model at $0.095 per million input tokens. For the chats themselves our own models run in the EEA and store no prompts — useful when LibreChat is the company's internal assistant.

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

Start a chat with Heabsy › qwen38. The reply and an automatic chat title confirm both the chat model and the title model.

If the tool shows an error you cannot read, test the key on its own first — one short request outside the tool:

curl

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
Chats work but titles fail	Set `titleModel` to a model from our catalog; the default title model does not exist at Heabsy.
404 Not Found	`baseURL` must end in `/v1`, not `/chat/completions`.
The model list is empty	Check the key in `.env`, or list models under `default`.
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 LibreChat 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

Can LibreChat use partner models such as Claude through Heabsy?+

Yes, with the same key; they appear in the fetched list. They are partner-hosted — no zero data retention and no EEA guarantee.

Can each department have its own budget?+

Create one Heabsy key per department with its own budget and model allow-list, and one custom endpoint per key in librechat.yaml.

Create a key and send the first request All integrations

Also set up:Open WebUI · SillyTavern · LangChain

LibreChat is an open-source project; Heabsy is not affiliated with it.