Unified AI Endpoint

AI Text Generation API

Access powerful AI models like Gemini, GPT, Claude, Llama, and more through a single unified endpoint.

Quick Start

Choose your preferred endpoint format:

                    POST 
                    https://nexus.drexus.xyz/v1/text/generate
                

Authentication

Include your API key as a Bearer token in the Authorization header.

Authorization: Bearer YOUR_API_KEY

Need a key? Get one from your dashboard

Real-Time Streaming

Set "stream": true to receive text chunks.

Conversation Memory

Use "userid" to maintain context.

Image Vision

Send images via URL or base64 in the "images" parameter.

Generous Limits

1000 requests/day on free tier with full access to all models.

Request Parameters

Recommended Easiest for new integrations

model

Required

Model ID (e.g., gemini-2.5-flash)

prompt

Conditional

Your text prompt (required if messages not used)

userid

Optional

Unique ID for conversation history

systemInstruction

Optional

System behavior/persona

images

Optional

Image URLs or base64 for vision

stream

Optional

Enable streaming (default: false)

Usage Examples

curl -X POST https://nexus.drexus.xyz/v1/text/generate \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2.5-flash",
    "prompt": "Explain quantum computing simply",
    "userid": "user123"
  }'

import requests

url = "https://nexus.drexus.xyz/v1/text/generate"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}
data = {
    "model": "gemini-2.5-flash",
    "prompt": "Explain quantum computing simply",
    "userid": "user123"
}

response = requests.post(url, json=data, headers=headers)
print(response.json())

const response = await fetch('https://nexus.drexus.xyz/v1/text/generate', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.JSON.stringify({
    model: 'gemini-2.5-flash',
    prompt: 'Explain quantum computing simply',
    userid: 'user123'
  })
});

const data = await response.json();
console.log(data);

curl -X POST https://nexus.drexus.xyz/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Explain quantum computing simply"}
    ],
    "temperature": 0.7,
    "max_tokens": 1024
  }'

import requests

url = "https://nexus.drexus.xyz/v1/chat/completions"
headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}
data = {
    "model": "gpt-4",
    "messages": [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain quantum computing simply"}
    ],
    "temperature": 0.7,
    "max_tokens": 1024
}

response = requests.post(url, json=data, headers=headers)
print(response.json())

const response = await fetch('https://nexus.drexus.xyz/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'gpt-4',
    messages: [
      { role: 'system', content: 'You are a helpful assistant.' },
      { role: 'user', content: 'Explain quantum computing simply' }
    ],
    temperature: 0.7,
    max_tokens: 1024
  })
});

const data = await response.json();
console.log(data);

Response Format

{
  "success": true,
  "model": "gemini-2.5-flash",
  "completion": "Quantum computing is a revolutionary...",
  "userid": "user123",
  "usageRemaining": 499
}

Available Models

Explore our extensive library of models

Provider	Model ID	Description	Features
Anthropic	`claude-opus-4-5-20251101`	Most capable Claude model with advanced reasoning.	Requires Key
Meta AI	`llama-4-maverick-17b-128e-instruct`	New instruction-tuned Llama 4 model.	Requires Key
Meta AI	`llama-3.2-90b-vision-instruct`	Vision model with image support (base64 and URL).	Vision Requires Key
Meta AI	`llama-3.1-405b-instruct`	Largest, most powerful Llama 3.1 model.	Requires Key
Meta AI	`llama-3.3-70b-instruct`	High-performance instruction-tuned model.	Requires Key
Mistral AI	`mistral-small-24b-instruct`	Efficient and capable new model from Mistral.	Requires Key
Mistral AI	`mixtral-8x22b`	Mixture-of-experts model for efficiency.	Requires Key
Alibaba	`qwen3-235b-a22b`	Latest large-scale Qwen model.	Requires Key
Alibaba	`qwen2.5-coder-32b`	Specialized for code generation.	Code Requires Key
Google	`gemini-2.5-flash`	Latest fast and capable Gemini model.	Vision Requires Key
Google	`gemini-2.5-flash-lite`	Lightweight latest fast model.	Requires Key
Google	`gemini-2.0-flash`	Fast and efficient model.	Requires Key
Google	`gemini-2.0-flash-lite`	Lightweight version of 2.0 flash.	Requires Key
Google	`gemma-7b`	Lightweight Gemma 7B model.	Requires Key
Google	`gemma-2-9b`	Next-gen Gemma 2 9B model.	Requires Key
OpenAI	`gpt-4`	Advanced reasoning and creativity.	Requires Key
OpenAI	`gpt-4o-mini`	Fast and efficient GPT-4 optimized model.	Requires Key
OpenAI	`gpt-5-mini`	Next-generation compact GPT-5 model.	Requires Key
OpenAI	`gpt-5-nano`	Ultra-lightweight GPT-5 variant.	Requires Key
xAI	`grok-3`	Advanced reasoning and humor-capable model.	Requires Key
xAI	`grok-3-mini`	Compact version of Grok-3 for faster responses.	Requires Key
DeepSeek AI	`deepseek-r1`	Advanced reasoning capabilities.	Requires Key
DeepSeek AI	`deepseek-v3.1`	Advanced model with thinking mode.	Requires Key
Open Source	`gpt-oss-120b`	Large open-source model.	Requires Key
Open Source	`gpt-oss-20b`	Smaller open-source model.	Requires Key
Phind	`phind-90b`	Programming-focused model.	Code No Stream
Moonshot AI	`kimi-k2`	Kimi K2 - Advanced reasoning model via Ollama Cloud.	Requires Key
MiniMax	`minimax-m2`	MiniMax M2 - Powerful multilingual model via Ollama Cloud.	Requires Key
Google (Ollama)	`gemini-3-flash-preview`	Gemini 3 Flash Preview via Ollama Cloud.	Requires Key
NVIDIA (Ollama)	`nemotron-3-nano`	Nemotron 3 Nano - Efficient NVIDIA model via Ollama Cloud.	Requires Key
Zhipu AI	`glm-4.6`	GLM 4.6 - ChatGLM advanced model via Ollama Cloud.	Requires Key
Mistral AI	`mistral-small-latest`	Mistral Small - Fast and efficient model for everyday tasks.	Requires Key
Mistral AI	`mistral-medium-latest`	Mistral Medium - Balanced performance and quality.	Requires Key
Mistral AI	`mistral-large-latest`	Mistral Large - Most capable model for complex tasks.	Requires Key
Mistral AI	`codestral-latest`	Codestral - Specialized for code generation and understanding.	Code Requires Key
Mistral AI	`mistral-large-pixtral-2411`	Pixtral Large - Vision-enabled large model.	Vision Requires Key
Mistral AI	`open-mistral-7b`	Open Mistral 7B - Lightweight open-source model.	Requires Key
Mistral AI	`ministral-8b-latest`	Ministral 8B - Compact yet powerful model.	Requires Key
Mistral AI Labs	`labs-mistral-small-creative`	Mistral Small Creative - Optimized for creative writing.	Creative Requires Key
Mistral AI	`magistral-small-latest`	Magistral Small - Advanced reasoning capabilities.	Reasoning Requires Key
Mistral AI	`magistral-medium-latest`	Magistral Medium - Enhanced reasoning with larger context.	Reasoning Requires Key
Mistral AI	`mistral-tiny-latest`	Mistral Tiny - Ultra-fast responses for simple tasks.	Fast Requires Key