The cheapest way to run an agent at scale.
Same model, same task: Vetta finishes it 2.7x cheaper than the next-best harness. Set up in a few lines.
See how Vetta runsimport { createClient } from "@usenaive-sdk/vetta";
const vetta = createClient({
baseUrl: "https://api.vetta.sh",
apiKey: process.env.VETTA_API_KEY!,
});
const agent = await vetta.agents.create({
name: "support",
model: "zai-org/GLM-5.2-FP8",
budget: { cap_micro_usd: 50_000_000, period: "month" },
});
const session = await vetta.sessions.create({
agent_id: agent.id,
message: "Clear the overnight queue.",
});
