Others for AI agents
Every other model, by name: coder variants, older snapshots, niche open-weight releases. 340+ in all.
priced per model
What it's for
Query any of 340+ models by name, not just the featured ones.
Pin an exact snapshot when reproducibility matters.
Run bulk summarize or classify passes on the cheapest capable model.
No per-provider accounts or keys: every model settles against one Vaaya credit account.
How to ask your agent
Connect Vaaya, then just say it in plain language. For example:
❯Use Vaaya to ask Qwen3 Coder to write this parser.
❯Use Vaaya to run this classify pass on the cheapest capable model.
What you get back
{
"text": "def parse(line: str) -> Row:\n …",
"model_used": "qwen/qwen3-coder",
"charged_usd": 0.000556
}
Pricing
Each model’s provider rate per token, plus 3%. See every price at /catalog/llms.. Charges are shown in cents and recorded in your transaction history. Set a maximum cost for each call. Failed calls are not charged.
Try it with your agent.
Connect Vaaya and describe what you want to do. Your agent can find a suitable service and call it within your budget.
npx @vaaya/mcp install