Guide
LLM routing: match tasks to models
Routing is matching a task to a catalog row. Ashna-X1 is the default. Pin GPT, Claude, or Gemini when you need that row’s context, reasoning, or file flags. Brand preference is not routing.
AshnaAI
Write the constraint first
If the constraint is “any good answer,” stay on X1. If it is “400k context” or “thinking must stay on,” open the catalog.
Do not route PDFs to X1
Use chat-with-file. That is a pipeline choice, not a model-brand choice.
Frequently asked questions
- What is LLM routing?
- Choosing which catalog model should run a task based on tools, context, and reasoning needs.
- Is Ashna-X1 a router or a model?
- It is the default catalog model. Routing is the decision to stay there or pin another row.
- When should I pin Claude?
- When you need that provider’s reasoning or a customer requires Anthropic.
- Does routing replace agents?
- No. Agents still have specs and tools. Routing picks the model those tools run on.
- Where is the research?
- Ashna-X1 and task-aware model routing.
Tags
#routing#LLM
Related
Try this in AshnaAI. Create a free account.
Found this article helpful? Share it with your network.