Kimi K3 for AI agents
Open-weight frontier reasoning, with a 1.05M-token context window.
$3 / $15 per 1M
What it's for
Best for open-weight frontier reasoning.
Get a second opinion next to the model you already use.
No Moonshot account or key: calls settle against your Vaaya credit.
Name any other model to swap mid-conversation.
How to ask your agent
Connect Vaaya, then just say it in plain language. For example:
❯Use Vaaya to ask Kimi K3 for a second opinion on this plan.
❯Use Vaaya to have Kimi K3 and your own model answer this, then compare.
What you get back
{
"text": "Short answer: ship it behind a flag. The riskiest piece is the\n backfill, not the schema change…",
"model_used": "moonshotai/kimi-k3",
"charged_usd": 0.00649
}
Pricing
$3 in / $15 out per 1M tokens, plus 3%. 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