API Reference

NeuronGate is fully compatible with the OpenAI API format. Point any OpenAI SDK at our base URL and you are ready to go. Pay with crypto, access every model.

Quick Start

Get an API key

Create an account and generate a key from the dashboard. Keys start with sk-ng-.

Fund your account

Deposit USDC, USDT, or ETH. Your balance is debited per-request at listed model prices.

Make your first request

bash

curl https://api.neurongate.io/v1/chat/completions \
  -H "Authorization: Bearer sk-ng-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4o",
    "messages": [
      {"role": "user", "content": "Hello, NeuronGate!"}
    ]
  }'

Same as OpenAI. NeuronGate implements the OpenAI-compatible chat completions API. If your code works with OpenAI, it works with NeuronGate. Just change the base URL and API key.

Authentication

All API requests require authentication. NeuronGate API keys follow the format sk-ng-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx. You can pass the key in two ways:

Authorization header (recommended)

Authorization: Bearer sk-ng-your-api-key

X-API-Key header

X-API-Key: sk-ng-your-api-key

curl https://api.neurongate.io/v1/chat/completions \
  -H "Authorization: Bearer sk-ng-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{"model": "openai/gpt-4o", "messages": [{"role": "user", "content": "Hi"}]}'

Chat Completions

POST/v1/chat/completions

Creates a chat completion. Compatible with the OpenAI chat completions API.

Request Body

Field	Type	Required	Description
model	string	Yes	Model identifier, e.g. "openai/gpt-4o", "anthropic/claude-sonnet-4", "meta-llama/llama-3-70b".
messages	array	Yes	Array of message objects. Each has a "role" (system \| user \| assistant) and "content" (string).
stream	boolean	No	If true, returns a stream of server-sent events. Default: false.
temperature	number	No	Sampling temperature between 0 and 2. Higher values produce more random output. Default: 1.
max_tokens	integer	No	Maximum number of tokens to generate. If omitted, the model decides.
top_p	number	No	Nucleus sampling. An alternative to temperature. Default: 1.
stop	string \| array	No	Up to 4 sequences where the model will stop generating further tokens.
frequency_penalty	number	No	Number between -2 and 2. Positive values penalise repeated tokens. Default: 0.
presence_penalty	number	No	Number between -2 and 2. Positive values penalise tokens already present. Default: 0.

Response

json

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1713000000,
  "model": "openai/gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 9,
    "total_tokens": 21
  }
}

Streaming

Set stream: true to receive server-sent events. Each event contains a delta object:

text

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1713000000,"model":"openai/gpt-4o","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1713000000,"model":"openai/gpt-4o","choices":[{"index":0,"delta":{"content":"!"},"finish_reason":null}]}

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","created":1713000000,"model":"openai/gpt-4o","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: [DONE]

Examples

curl https://api.neurongate.io/v1/chat/completions \
  -H "Authorization: Bearer sk-ng-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4o",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Explain quantum computing in one sentence."}
    ],
    "temperature": 0.7,
    "max_tokens": 100
  }'

List Models

GET/v1/models

Returns a list of all available models, including pricing and context window information.

Response

json

{
  "object": "list",
  "data": [
    {
      "id": "openai/gpt-4o",
      "object": "model",
      "created": 1713000000,
      "owned_by": "openai",
      "pricing": {
        "prompt": "0.0025",
        "completion": "0.0100"
      },
      "context_length": 128000
    },
    {
      "id": "anthropic/claude-sonnet-4",
      "object": "model",
      "created": 1713000000,
      "owned_by": "anthropic",
      "pricing": {
        "prompt": "0.0030",
        "completion": "0.0150"
      },
      "context_length": 200000
    }
  ]
}

Example

curl https://api.neurongate.io/v1/models \
  -H "Authorization: Bearer sk-ng-your-api-key"

Rate Limits

Rate limits are applied per API key. Limits depend on your account tier and can be viewed in the dashboard.

Limit Type	Default	Description
Requests/min	60	Maximum requests per minute per API key
Daily spend	$100	Maximum spend per day. Configurable in the dashboard.
Monthly spend	$1,000	Maximum spend per calendar month. Configurable in the dashboard.

When a rate limit is exceeded, the API returns a 429 status with a Retry-After header indicating when you can retry.

json

{
  "error": {
    "type": "rate_limit_exceeded",
    "message": "Rate limit exceeded. Please retry after 2 seconds.",
    "code": 429
  }
}

Error Codes

NeuronGate uses standard HTTP status codes. Errors return a consistent JSON body.

Code	Type	Description
400	bad_request	The request body is malformed or missing required fields.
401	unauthorized	Invalid or missing API key.
402	insufficient_funds	Your account balance is too low to process this request.
404	not_found	The requested model or resource does not exist.
429	rate_limit_exceeded	Too many requests or spend limit reached. Check Retry-After header.
500	internal_error	An unexpected error occurred on our side. Please retry.
502	upstream_error	The upstream model provider returned an error. Try again or use a different model.

Error Response Format

json

{
  "error": {
    "type": "unauthorized",
    "message": "Invalid API key. Please check your key and try again.",
    "code": 401
  }
}

SDKs & Libraries

NeuronGate is fully compatible with the OpenAI API. You do not need a custom SDK. Just use the official OpenAI library and point it at NeuronGate.

Python

bash

pip install openai

Node.js / TypeScript

bash

npm install openai

Python Setup

python

from openai import OpenAI

client = OpenAI(
    api_key="sk-ng-your-api-key",
    base_url="https://api.neurongate.io/v1",
)

# Use exactly like the OpenAI SDK
response = client.chat.completions.create(
    model="openai/gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)

# Streaming works the same way
stream = client.chat.completions.create(
    model="anthropic/claude-sonnet-4",
    messages=[{"role": "user", "content": "Tell me a story."}],
    stream=True,
)
for chunk in stream:
    content = chunk.choices[0].delta.content
    if content:
        print(content, end="", flush=True)

Node.js Setup

typescript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-ng-your-api-key",
  baseURL: "https://api.neurongate.io/v1",
});

// Use exactly like the OpenAI SDK
const response = await client.chat.completions.create({
  model: "openai/gpt-4o",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

// Streaming works the same way
const stream = await client.chat.completions.create({
  model: "meta-llama/llama-3-70b",
  messages: [{ role: "user", content: "Tell me a story." }],
  stream: true,
});
for await (const chunk of stream) {
  const content = chunk.choices[0]?.delta?.content;
  if (content) process.stdout.write(content);
}

Any OpenAI-compatible library works. LangChain, LlamaIndex, Vercel AI SDK, and other frameworks that support a custom base URL are all compatible. Just set the base URL to https://api.neurongate.io/v1 and provide your NeuronGate API key.