Installation
Zed + Luma Cloud
Zed supports OpenAI-compatible LLM provider settings with api_url and available_models.
Recommended path
Add an OpenAI-compatible provider entry with the Luma endpoint and available model ids.
Replace the sample family only with an exact id returned by the authenticated catalog, then confirm streaming.
Use only the /v1 endpoint from your dashboard. Never paste localhost or other internal URLs into client settings.
Copy-safe config
Use this as the exact client-facing fallback when no native provider listing exists yet.
"language_models": {
"openai_compatible": {
"Luma Cloud": {
"api_url": "https://api.lumaos.cloud/v1",
"available_models": [
{
"name": "gpt-5.5",
"display_name": "GPT-5.5 (default Medium)",
"max_tokens": 272000,
"max_output_tokens": 128000,
"capabilities": {
"tools": true,
"images": false,
"parallel_tool_calls": false,
"prompt_cache_key": false,
"chat_completions": true
}
}
]
}
}
}Provider fields
Use the same values across clients.
These values come from the shared Luma Cloud provider registry and must match /v1/models and provider-catalog submissions.
Provider ID
luma-cloud
Display name
Luma Cloud
Provider type
OpenAI-compatible
Base URL
https://api.lumaos.cloud/v1
API key env
LUMA_CLOUD_API_KEY
Catalog source
Authenticated GET https://api.lumaos.cloud/v1/models
Example family
gpt-5.5 only when returned by the catalog
Distribution
Native listing path.
Submit docs/sample settings only after a live Zed smoke passes.