Menlo / Jan. Desktop API-server docs in the Jan repo, checked 2026-10-12.
Desktop local-AI app with a built-in OpenAI-compatible server (default 127.0.0.1:1337/v1), powered by llama.cpp.
What it’s for
Local chat and a loopback /v1 for other tools.
Local endpoint
llama-server base
http://127.0.0.1:8080/v1
Strata base
http://127.0.0.1:8083/v1
Model name
Model id as listed in Jan
API key
Optional in Settings; required in Authorization if you set one
Tool calling
Chat completions documented. Images/audio endpoints listed as not yet supported on the API-server page we opened.
Long context
Set in Jan. Pointing Jan *at* our llama-server (instead of its built-in engine) is not documented on that page — treat as check the current UI.
ROCm / Radeon gotchas
Jan’s llama.cpp backend on AMD is not documented as HIP gfx1201 on that page. Safer: run our Vulkan llama-server and use Jan only as a client if the UI allows a remote OpenAI URL.
Hybrid local + cloud
Remote API connections are mentioned in third-party writeups; official hybrid steps are not copied here.
This is the same question as the calculator’sfully localversushybridtoggle. This page does not quote cloud prices.
More on the connect page. Prove http://127.0.0.1:8080/v1/models first.
Jan — documented server vs our :8080
# Documented desktop API server: http://127.0.0.1:1337/v1
# Prefix /v1. Optional API key in Settings.
#
# Pointing Jan *at* our llama-server :8080 (http://127.0.0.1:8080/v1) is not documented on the
# API-server page we opened — treat as check the current UI.
Jan’s llama.cpp backend on AMD / HIP gfx1201 is not documented on that page.
Jan — documented server vs our :8083
# Documented desktop API server: http://127.0.0.1:1337/v1
# Prefix /v1. Optional API key in Settings.
#
# Pointing Jan *at* our Strata :8083 (http://127.0.0.1:8083/v1) is not documented on the
# API-server page we opened — treat as check the current UI.
Jan’s llama.cpp backend on AMD / HIP gfx1201 is not documented on that page.