Add rapid LLM decision making directly to your app

Most AI calls in a product are small. Which repo did the user mean? Is this ticket urgent? What should this thing be called?

rapid.dance gives each of those questions its own URL as a JSON API. If the model can't decide within a defined time limit, you get a default you set instead of an error.

Log in or read the API docs

A Real-World Example

Say you run a deployment platform. A user has a few repositories connected and names a new deployment "blog". You want to guess which repo it's for to provide a slightly better first-time UX.

In rapid.dance you create a query called repo-selector with one line of instructions (pick the repo this deployment most likely belongs to; leave it blank if unsure) and one output field, selected_repo.

The API your code calls is then simply:

POST https://api.rapid.dance/demo/repo-selector
Authorization: Bearer rq_…

{
  "repos": ["myexample/myblog", "myexample/waitlist-api"],
  "deployment_name": "blog"
}

HTTP/2 200 OK
X-Rapid-Latency-Ms: 121

{
  "selected_repo": "myexample/myblog"
}

The response is constrained to the fields you define. There's no prompt in your codebase and nothing to parse other than JSON.

Time-Bound Fallback

Every query has a time limit you specify so that slow decisions don't hamper your own app's experience. You provide a fallback value for when this happens.

Built for Rapid Development

• Manage queries in the app or via LLM/API. All you need to specify are plain-English instructions and the shape of the output.
• Playground for testing. Paste some sample input and check the answer in-app.
• Call-only keys. Create API keys that can only execute queries, and POST from any tech stack.
• Logged. Every call is kept for 90 days with its input (unless sensitive), output, timing, and price.

Pricing

A flat price per request.

Log in API docs