- A local server bound to loopback
- A compatible chat-completions response
- User-configured endpoint and optional token
- A locally available model
local runtime · paired
OpenAI-compatible local runtime
Local text inference through the user’s companion when the runtime follows the supported OpenAI-compatible response contract.

- DecaCap interface
- User-configured loopback chat-completions endpoint
- Published evidence
- The companion supports a user-configured local endpoint and token. Runtime-specific behavior must be tested with the hardware checker and companion health test.
- Exact-model probe
- Not published Account-, model-, region-, quota-, runtime-, and hardware-specific verification still requires a real user-owned key or device.
- Last reviewed
- 2026-07-26
- Compatibility is contract-based, not a promise that every OpenAI-like server behaves identically
- Remote LAN or internet endpoints are outside the intended local-only boundary
- Loopback endpoint configuration
- Optional local token
- Companion-authenticated browser path
- Text response extraction
- Access to a particular model on a user account
- Quality, speed, pricing, quota, or safety behavior
- Hardware fit or training-toolkit compatibility