{% extends "admin_base.html" %} {% block extra_head %} {{ super() }} {% endblock %} {% block admin_content %}
{{ error }}
The source model is the name clients request; the target model is what is actually sent to the provider.
Loaded live from the selected provider's model list.
When set, image content is described by this vision model before the chat request is forwarded. Leave blank to disable image-to-text merging for this route.
Chat uses cache-hit, cache-miss and output prices (USD per 1M tokens). Embeddings and the vision augmentation use the input price. Image routes use the input price as a flat USD amount per generated image.
Some providers charge a different rate once a request crosses a context-length threshold. Leave the tier-2 fields blank to keep the flat rates above at all times; 0 disables the threshold.
A percentage discount applied to whichever tier's rates are active during a fixed UTC time window. Leave both times blank to disable.