API Reference

API Overview

The NeuronEdge API is organized around REST. Our API accepts JSON-encoded request bodies, returns JSON-encoded responses, and uses standard HTTP response codes and authentication.

Base URL

text

https://api.neuronedge.ai

Authentication

All API requests require authentication via Bearer token in the Authorization header. API keys are prefixed with ne_ to distinguish them from provider keys.

http

Authorization: Bearer ne_live_your_api_key
X-Provider-API-Key: sk-your-provider-key

Learn more about authentication →

Request Headers

Header	Required	Description
Authorization	Yes	NeuronEdge API key (ne_...)
X-Provider-API-Key	Yes	Your LLM provider API key
X-NeuronEdge-Policy	No	Policy ID to override default
X-NeuronEdge-Format	No	Redaction format: token, hash, synthetic
X-NeuronEdge-Mode	No	Detection mode: real-time, balanced, thorough
X-NeuronEdge-Entities	No	Comma-separated entity types to detect

Response Headers

Header	Description
X-Request-ID	Unique request identifier (ULID format)
X-NeuronEdge-Entities-Detected	Number of PII entities detected
X-NeuronEdge-Detection-Time-Ms	Detection processing time in milliseconds
X-RateLimit-Limit	Your rate limit ceiling
X-RateLimit-Remaining	Remaining requests in current window
X-RateLimit-Reset	Unix timestamp when limit resets

Endpoints

POST/v1/{provider}/chat/completions

Send chat completion requests with automatic PII redaction

GET/api/policies

List all policies for your organization

POST/api/policies

Create a new PII detection policy

GET/api/keys

List all API keys for your organization

GET/health

Health check endpoint (no auth required)

Supported Providers

NeuronEdge supports 17 LLM providers through the /v1/{provider}/chat/completions endpoint:

openaianthropicgoogleazurecohereperplexitygroqmistraltogetherfireworksanyscaledeepinfrahuggingfacereplicatebedrockbasetenai21

See provider-specific configuration →