Inference Auth Posture
Overview
Section titled “Overview”GET /v1/models and the inference endpoints are gated by different
settings. The most natural probe an operator runs to answer “is my API
protected?” can therefore return the wrong answer.
| Endpoint | Gated by |
|---|---|
GET /v1/models |
The dashboard login posture — isAuthRequired(), overridable per-instance with requireAuthForModels (src/app/api/v1/models/catalogRequest.ts) |
POST /v1/chat/completions, POST /v1/responses, and the other client API routes |
REQUIRE_API_KEY (src/server/authz/policies/clientApi.ts) |
On an instance that has an admin password set and REQUIRE_API_KEY=false,
/v1/models answers 401 while inference is open to anyone who can reach the
port.
Probing caveat: a
401from/v1/modelsdoes not verify that inference is protected. It only tells you the dashboard requires login.
This is not hypothetical. In discussion #13310 a self-hosted instance behind
Traefik had its Codex quota spent by anonymous POST /v1/responses traffic
while /v1/models returned 401 — which, in the reporter’s words, “initially
created the impression that the entire API was protected” and sent them
investigating the wrong component.
How to actually check
Section titled “How to actually check”Probe an inference route, not the catalog:
curl -s -o /dev/null -w '%{http_code}\n' \ -X POST http://<host>:<api-port>/v1/chat/completions \ -H 'content-type: application/json' \ -d '{"model":"<any-model>","messages":[{"role":"user","content":"ping"}]}'A 401 means REQUIRE_API_KEY is enforcing. Anything that reaches routing
(including a model-not-found error) means anonymous traffic is accepted.
Note that with REQUIRE_API_KEY=false an invalid bearer degrades to
anonymous rather than rejecting (#2257), so sending a junk key is not a valid
probe either.
Startup warning
Section titled “Startup warning”When REQUIRE_API_KEY is disabled and a server binds a non-loopback interface,
OmniRoute logs a warning at boot (src/lib/startup/nonLoopbackApiKeyGuard.ts).
This covers three surfaces:
- the Dashboard/API server that serves
/v1inference —HOST, default0.0.0.0 - the API bridge —
API_HOST, default127.0.0.1 - the live dashboard WebSocket — its own host
The warning never blocks boot: a reverse proxy in front of OmniRoute may already be enforcing its own authentication.
Related
Section titled “Related”REQUIRE_API_KEYin ENVIRONMENT.mdAPP_BIND_HOSTand the compose loopback defaults (#12568)- #2257 — invalid bearer degrades to anonymous when
REQUIRE_API_KEYis off - #13695 — this document
HagiCode
HagiCode is an agentic coding workspace. Rich, convenient UI interactions make planning, agent execution, and project work approachable and easy to navigate, creating an engaging development experience.
Explore an engaging development experience through rich, convenient UI interactions.
- SmartOpenSpec workflows turn intent into an executable path, from proposal to design, tasks, and a shipped change.
- EfficientMulti-agent execution keeps research, implementation, and review moving in parallel, across several repositories and the Agent CLIs you already use.
- InterestingRich, convenient UI interactions make planning, agent execution, and project work approachable and easy to navigate.
Download for Windows
Share HagiCode
Turn ideas into shipped software.
HagiCode is an agentic coding workspace. OpenSpec workflows plan the change, multi-agent execution carries it out, and Hero Scenario makes the long run visible, so ideas become shipped software.
- Smart
- OpenSpec workflows turn intent into a path from proposal to shipped change.
- Efficient
- Multi-agent execution runs research, build, and review in parallel.
- Fun
- Rich UI interactions make planning, agent work, and projects easier to follow.
© 2026 HagiCode | Powered By hagilight-starlight@0.21.0 | Branch: main | Commit: de60bcd | Built:

