Available connections
Each provider owns its endpoint defaults, request mapping, and model discovery. Available models can change independently of these docs.
1
Save the connection
Open Settings → Providers, choose a provider, and fill in its fields. Hosted services
require credentials. A local compatible server needs its base URL; LM Studio defaults to
http://localhost:1234 and OpenAI-compatible defaults to http://localhost:11434/v1. Whether a
local server needs a secret depends on that server.2
Select a model
Open the processing selector or Settings → Translation. Opening the processing selector, or
the Settings page, refreshes provider discovery. An unreachable provider may have no discovered
models even while its saved settings remain intact.
3
Choose whether to include the page image
Vision is on by default and the switch stays available for every model. If the selected
model does not accept images, Koharu drops the image from the request. OpenAI-compatible
endpoints are assumed to accept images, so turn the switch off when the server cannot handle
image messages.
4
Try one page
Check the source OCR, run translation on the current page, and review the response before
processing a chapter.
Credentials and privacy
Provider secrets use the operating system’s secure credential service. Non-secret endpoint settings live in~/.koharu/config.toml.
Local models keep prompts and text on your machine after download. Hosted providers receive request content and apply their own retention terms. Local detection and OCR do not make a hosted translation request local.