API Reference

Complete REST API documentation for NeuralChip platform

Getting Started

The NeuralChip API provides programmatic access to our AI acceleration platform. All API requests require authentication using an API key.

Base URL

https://api.neuralchip.ai

Authentication

Include your API key in the Authorization header:

Authorization: Bearer YOUR_API_KEY

Quick Start

Get started with our official SDKs in your preferred language

import neuralchip

# Initialize client
client = neuralchip.Client(api_key="YOUR_API_KEY")

# Run inference
result = client.inference(
    model_id="resnet50-fp16",
    input_data=image_data,
    batch_size=1,
    precision="fp16"
)

print(f"Result: {result.output}")
print(f"Latency: {result.latency_ms}ms")

API Endpoints

POST

/v1/inference

Execute inference on a deployed model

curl -X POST https://api.neuralchip.ai/v1/inference \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model_id": "resnet50-fp16",
    "input": {
      "data": "base64_encoded_image"
    },
    "options": {
      "batch_size": 1,
      "precision": "fp16"
    }
  }'

GET

/v1/models

List all deployed models

curl https://api.neuralchip.ai/v1/models \
  -H "Authorization: Bearer YOUR_API_KEY"

POST

/v1/models/deploy

Deploy a new model

curl -X POST https://api.neuralchip.ai/v1/models/deploy \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "model=@model.ncm" \
  -F "config=@config.json"

DELETE

/v1/models/{model_id}

Delete a deployed model

curl -X DELETE https://api.neuralchip.ai/v1/models/resnet50-fp16 \
  -H "Authorization: Bearer YOUR_API_KEY"

Rate Limits

1000

Requests per minute (Free tier)

10,000

Requests per minute (Pro tier)

Custom

Enterprise plans available