{% extends "admin/base.html" %} {% block title %}Models Manager{% endblock %} {% block header_title %}Models Manager & Auto-Routing{% endblock %} {% block content %}

AI Auto-Config

Ground model metadata in industry standard scorecards

Filter by Infrastructure

{% for server in servers %} {% endfor %}

Auto-Routing Logic & Metadata

The Models Manager defines the "Intelligence DNA" for the virtual auto model. Instead of managing server hardware here (which has moved to **Workflows**), this page focuses on tagging models so the Gateway knows how to route requests based on prompt content.

👁️ Supports Images

Required for vision tasks. If a user attaches an image, the 'auto' router filters for these models only.

🧠 Think (CoT)

Enable for models supporting internal reasoning (DeepSeek R1, etc). Prevents 'think' parameter stripping.

💻 Code

Tagged as programming experts. Used when the router detects code keywords (e.g. 'def', 'class', 'import').

⚡ Fast

Small, optimized models. Used when 'fast_model' option is set in the request for low-latency tasks.

🧩 Reasoning

Complex logic models. Triggered by keywords like 'solve', 'math', 'why', or 'step by step'.

📏 Max Context

Token limit. The router checks if the current chat history fits before selecting the model.

Configure Model Capabilities

{% for meta in metadata_list %} {% else %} {% endfor %}
Model Name Servers Description
Embedding
|
Supports Images
|
Think (CoT)
|
Code
|
Fast
|
Reasoning
|
Max Context Size (B) Scale Priority
No models found across any active servers. Go to the Server Management page and refresh your servers to discover models.
{% endblock %}