Installation
OpenCode + Luma Cloud
OpenCode is the first native-listing target through Models.dev. Until native catalog listing ships, use the Custom provider form or the secret-free provider skeleton.
Recommended path
App -> API -> create and copy a key -> add the Luma Cloud Base URL and key in the Custom provider form -> select an exact id returned by authenticated /models. Set LUMA_CLOUD_API_KEY only for the optional config-file path.
OpenCode must show only the exact ids returned for this credential. Use the advertised base/default pair for the first stream smoke.
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.
provider: luma-cloud
npm: @ai-sdk/openai-compatible
baseURL: https://api.lumaos.cloud/v1
models: authenticated GET https://api.lumaos.cloud/v1/modelsProvider 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
OpenCode timeout
600000
chunkTimeout
300000
Distribution
Native listing path.
Submit provider.toml, logo.svg, and model TOML files to anomalyco/models.dev after public v1 conformance passes.