NeXeonAI - AI Without Limits

Introduction

Welcome to the NeXeonAI API documentation. Our platform provides a unified, high-performance interface for accessing the world's most advanced Large Language Models (LLMs) from OpenAI, Anthropic, Google Gemini, DeepSeek, xAI, and OpenRouter.

Designed for developers, the API supports multiple formats: OpenAI Chat Completions, OpenAI Responses API (GPT-5+), and Anthropic Messages API. You can integrate it into existing applications with just a few lines of code.

Base URL

https://api.nexeonai.com/v1

Supported Providers

OpenAI, Anthropic, Google Gemini, DeepSeek, xAI, OpenRouter

Authentication

The API uses API keys for authentication. You can create and manage your API keys in the Dashboard.

Authentication is performed via the HTTP Authorization header. Provide your API key as a Bearer token. For Anthropic SDK compatibility, you can also use the x-api-key header.

Bearer Token (OpenAI-style)

bash

curl https://api.nexeonai.com/v1/models \
  -H "Authorization: Bearer nex-sk-..."

x-api-key (Anthropic-style)

bash

curl https://api.nexeonai.com/v1/messages \
  -H "x-api-key: nex-sk-..."

List Models

Lists the currently available models across all supported providers, including OpenAI GPT-5 series, Anthropic Claude, DeepSeek, and more.

GET/models

json

{
  "object": "list",
  "data": [
    {
      "id": "gpt-5.2-chat-latest",
      "object": "model",
      "created": 1736841600,
      "owned_by": "openai"
    },
    {
      "id": "claude-3-5-sonnet-20241022",
      "object": "model",
      "created": 1729555200,
      "owned_by": "anthropic"
    },
    {
      "id": "gemini-2.5-pro",
      "object": "model",
      "created": 1735689600,
      "owned_by": "google"
    },
    {
      "id": "deepseek-chat",
      "object": "model",
      "created": 1704067200,
      "owned_by": "deepseek"
    },
    {
      "id": "grok-3",
      "object": "model",
      "created": 1735689600,
      "owned_by": "xai"
    }
  ]
}

Chat Completions

Creates a model response for the given chat conversation. This is the primary endpoint for interacting with LLMs using the OpenAI format. Compatible with all models across all providers.

POST/chat/completions

Request Body

Parameter	Type	Description
model*	string	ID of the model to use (e.g., "gpt-5.2-chat-latest", "claude-3-5-sonnet-20241022").
messages*	array	A list of messages comprising the conversation so far.
temperature	number	Sampling temperature between 0 and 2.
max_tokens	number	Maximum tokens to generate. Use max_completion_tokens for GPT-5+ models.
stream	boolean	If set, partial message deltas will be sent.

Example

bash

curl https://api.nexeonai.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $API_KEY" \
  -d '{
    "model": "gpt-5.2-chat-latest",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello!"}
    ]
  }'

Responses API

The Responses API is OpenAI's new API primitive for GPT-5 and newer reasoning models. It provides better performance, built-in tools, and multi-turn conversation support.

Recommended for GPT-5+: The Responses API provides 3% better reasoning performance and up to 80% improved cache utilization compared to Chat Completions.

POST/responses

Request Body

Parameter	Type	Description
model*	string	ID of the model (e.g., "gpt-5", "gpt-5.2-chat-latest").
input*	string \| array	The input to generate a response for. Can be a string or message array.
instructions	string	System-level instructions for the model.
max_output_tokens	number	Maximum tokens to generate in the response.
tools	array	Built-in tools like web_search, file_search, code_interpreter.
stream	boolean	If set, response events will be streamed.
store	boolean	Whether to store the response for multi-turn conversations.
previous_response_id	string	ID of a previous response for multi-turn context.

Simple Example

bash

curl https://api.nexeonai.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $API_KEY" \
  -d '{
    "model": "gpt-5",
    "instructions": "You are a helpful assistant.",
    "input": "Hello!"
  }'

With Built-in Tools

bash

curl https://api.nexeonai.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $API_KEY" \
  -d '{
    "model": "gpt-5",
    "input": "What is the weather in Tokyo right now?",
    "tools": [{"type": "web_search"}]
  }'

Response Format

json

{
  "id": "resp_nex-abc123...",
  "object": "response",
  "created_at": 1736841600,
  "model": "gpt-5-2025-01-07",
  "output": [
    {
      "id": "msg_nex-xyz789...",
      "type": "message",
      "status": "completed",
      "content": [
        {
          "type": "output_text",
          "text": "Hello! How can I help you today?"
        }
      ],
      "role": "assistant"
    }
  ],
  "usage": {
    "input_tokens": 15,
    "output_tokens": 10
  }
}

Messages API

The Messages API provides Anthropic SDK compatibility, allowing you to use the Claude API format with any supported model including OpenAI and DeepSeek.

POST/messages

Request Body

Parameter	Type	Description
model*	string	ID of the model (works with any provider).
messages*	array	Messages in Anthropic format with role and content.
max_tokens*	number	Maximum tokens to generate.
system	string	System prompt (separate from messages).
temperature	number	Sampling temperature.
stream	boolean	If set, response will be streamed.

Example with Claude

bash

curl https://api.nexeonai.com/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: $API_KEY" \
  -d '{
    "model": "claude-3-5-sonnet-20241022",
    "max_tokens": 1024,
    "system": "You are a helpful assistant.",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Example with GPT-5 (Cross-Compatible)

bash

curl https://api.nexeonai.com/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: $API_KEY" \
  -d '{
    "model": "gpt-5.2-chat-latest",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Explain quantum computing."}
    ]
  }'

Response Format

json

{
  "id": "msg_nex-abc123...",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "Hello! How can I assist you today?"
    }
  ],
  "model": "claude-3-5-sonnet-20241022",
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 12,
    "output_tokens": 10
  }
}

Streaming

NeXeonAI supports streaming responses for Chat Completions, Responses API, and Messages API. When stream is set to true, the API will send server-sent events (SSE) containing partial message deltas.

SDK Usage

If you are using the official OpenAI or Anthropic SDKs, streaming is handled automatically when you pass stream=True.

Python Example (OpenAI SDK)

python

from openai import OpenAI

client = OpenAI(
    api_key="nex-sk-...",
    base_url="https://api.nexeonai.com/v1"
)

stream = client.chat.completions.create(
    model="gpt-5.2-chat-latest",
    messages=[{"role": "user", "content": "Hello!"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

Python Example (Anthropic SDK)

python

from anthropic import Anthropic

client = Anthropic(
    api_key="nex-sk-...",
    base_url="https://api.nexeonai.com"
)

with client.messages.stream(
    model="claude-3-5-sonnet-20241022",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello!"}]
) as stream:
    for text in stream.text_stream:
        print(text, end="")

Errors

The API uses standard HTTP response codes to indicate the success or failure of an API request.

Code	Description
200	Success
400	Bad Request - Invalid request body or parameters
401	Unauthorized - Invalid or missing API key
402	Payment Required - Insufficient credits in wallet
403	Forbidden - API key lacks required permissions
404	Not Found - Model or resource not found
429	Rate Limit Exceeded - Too many requests
500	Internal Server Error
502	Bad Gateway - Upstream provider error
503	Service Unavailable - No active provider keys available

Error Response Format

json

{
  "error": {
    "type": "invalid_request_error",
    "message": "Model 'unknown-model' is not available",
    "param": "model",
    "code": "model_not_found"
  }
}