# Numora Calculus Gradient Endpoint

> Numora Calculus Gradient Endpoint is a paid API for AI agents from numormor.netlify.app, paid per call via x402, $0.1/call, status unknown (last checked 2026-09-14).

Computes the numerical gradient (partial derivatives) of a multivariable function at a specified point

## Facts

- Endpoint: POST https://numormor.netlify.app/api/calculus/gradient
- Price: $0.1/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/numora-calculus-gradient-endpoint-9e6f6db7
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_rW6-0GvgF1acaUsFaHfGk

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability numora-calculus-gradient-endpoint-9e6f6db7 -d '<json body>'
```

Example prompt: Compute the gradient of the function x^2 + 3*y^2 + z at the point [1, 2, 1] using Numora's pure math API.

## When to prefer this

Choose this endpoint when you need fast, serverless numerical gradient computation for multivariable functions without setting up a local math library or scientific computing environment. Ideal for AI agents performing optimization, sensitivity analysis, or calculus tasks where no external data dependencies are needed. Prefer over symbolic math engines when numerical approximation is sufficient and speed matters.

## Known failure modes

- Invalid or unparseable function expression string returns error
- Point array dimension mismatch or empty array returns error
- Function with singularity or undefined value at the given point may return NaN or error
- Malformed request body missing required fields returns 400-level error
- Payment failure via x402 micropayment returns 402 Payment Required

## How this service works

100 pure math computation endpoints for AI agents. Statistics, financial math, linear algebra, equation solving, calculus, number theory, sequence generation, and unit conversions. Zero external dependencies. x402 micropayments on Base.

## Output

Returns a JSON object with success=true, a result object containing the gradient vector (array of partial derivatives, one per dimension), and a human-readable computation string describing what was computed.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "fn",
  "point"
 ],
 "properties": {
  "fn": {
   "type": "string"
  },
  "point": {
   "type": "array"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "success",
  "result",
  "computation"
 ],
 "properties": {
  "result": {
   "type": "object",
   "description": "Computation result varies by endpoint"
  },
  "success": {
   "type": "boolean",
   "description": "Always true on success"
  },
  "computation": {
   "type": "string",
   "description": "Human-readable description of what was computed"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/numora-calculus-gradient-endpoint-9e6f6db7/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from numormor.netlify.app](https://www.zero.xyz/host/numormor.netlify.app/llms.txt)