CLI & IDE Compatibility Matrix
Reference for Openference client integration and verify flows.| Client | Verify / smoke test | Endpoint(s) needed | Status |
|---|---|---|---|
| Cursor | GET /v1/models + Bearer | /v1/models | Full |
| Continue | GET /v1/models | /v1/models | Full |
| Cline | GET /v1/models or chat | /v1/models | Full |
| Codex CLI | GET /v1/models or minimal chat | /v1/models, /v1/chat/completions | Full |
| Codex (Responses) | POST /v1/responses | /v1/responses | Full |
| OpenCode CLI | GET /v1/models or chat | /v1/models, /v1/chat/completions | Full |
| OpenAI Embeddings | POST /v1/embeddings | /v1/embeddings | Full |
| LiteLLM / generic | chat + models | existing | Full |
Base URL convention
All clients should use:sk-token-... (create in the dashboard).
Usage counting
Requests count toward daily limits when status issuccess or client_error. Upstream failures (upstream_error) do not count.
Cursor verify
Cursor’s Verify button callsGET {base_url}/models with the configured Bearer token. Openference returns an OpenAI-compatible model list filtered by token restrictions.
Detailed guides
See the individual pages:- Cursor
- OpenCode CLI
- Codex
- And others in the sidebar.
Model configuration tip
When a client lets you list specific models (e.g. OpenCode), only list the models you actually use. The model keys must exactly match the IDs returned byGET /v1/models.