Zed with an OpenAI-compatible provider: connect Heabsy

Q: Which model should I add first?

qwen38 — 262,144 tokens of context, images and tool calling, served on our own GPUs in the EEA. Add glm53 for a 1,048,576-token window.

Zed adds OpenAI-compatible providers under language_models.openai_compatible in settings.json. Add a Heabsy entry with api_url https://api.heabsy.com/v1 and the models you use, with their context windows and capabilities. Zed asks for the key and stores it in the system keychain, not in the file.

settings.json

{
  "language_models": {
    "openai_compatible": {
      "Heabsy": {
        "api_url": "https://api.heabsy.com/v1",
        "available_models": [
          {
            "name": "qwen38",
            "display_name": "Qwen3.8 27B",
            "max_tokens": 262144,
            "max_output_tokens": 32768,
            "capabilities": { "tools": true, "images": true, "parallel_tool_calls": false, "prompt_cache_key": false }
          }
        ]
      }
    }
  }
}

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

Step by step

Run agent: open settings and choose Add provider, or edit settings.json directly.
max_tokens is the model's context window and is required; take it from the table below.
Enable capabilities.tools — the Agent Panel works through tool calls.
Enter the key when Zed asks; it goes to the system keychain. Alternatively export HEABSY_API_KEY — Zed looks for <PROVIDER_NAME>_API_KEY.

Which model should I pick?

The Agent Panel needs tool calling; every model in the table has it. Add several models to available_models to switch between them in the panel.

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 Agent Panel, choose Heabsy › Qwen3.8 27B and ask it to read a file of your project. A correct answer means the connection and tool calling work.

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
The model does not appear in the Agent Panel	Add it to `available_models` with `name` equal to the catalog ID.
The agent answers but never edits files	Set `capabilities.tools` to true for that model.
401 Unauthorized	Re-enter the key in the provider settings, or check the `HEABSY_API_KEY` variable.
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 Zed 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 model should I add first?+

qwen38 — 262,144 tokens of context, images and tool calling, served on our own GPUs in the EEA. Add glm53 for a 1,048,576-token window.

Where does my code go?+

From Zed to api.heabsy.com. Our own models process it in the EEA and do not store it; partner-hosted models are marked in the catalog and follow their providers' policies.

Create a key and send the first request All integrations

Also set up:Claude Code · Cline · OpenCode

Zed is a trademark of Zed Industries; Heabsy is not affiliated with it.