Choose when your AI work runs.

Now costs more. Later costs less.

POST /v1/batches illustrative

{
  "model": "glm-5.2",
  "completion_window": "6h",
  "messages": [
    {
      "role": "user",
      "content": "Summarize these 40,000 support tickets."
    }
  ]
}

A drop-in API for leading open models. One new field: your deadline.

Time turns into efficiency.

Your timeline gives us room to optimize. Surplus hosts models to maximize high-quality throughput and passes the savings on. Same models, same performance. Pay for work, not gaps.

Run now~55% utilized

Given time~98% utilized

Efficiency means savings.

The more time you give, the less you pay. Just say when.

today's market surplus

Join the beta.

We're onboarding a small group of teams & developers now.