Tenzro Cortex
Universal AI inference API providing access to a library of models from all major providers. Deploy custom models, optimize costs automatically, and scale infinitely.
Capabilities
Text Generation
Generate high-quality text with a library of models from all major providers
- Code generation
- Creative writing
- Documentation
- Translations
Multimodal AI
Analyze images, videos, and documents with advanced vision models
- Image analysis
- Document OCR
- Visual Q&A
- Chart extraction
Image Generation
Create stunning images with Imagen 3, GPT Image 1, and Stable Diffusion
- Photorealistic images
- Art generation
- Logo design
- Product shots
Video Generation
Generate high-quality videos with Veo 2 and other top models
- Short clips
- Animations
- Product demos
- Social content
Audio Generation
Create music, sound effects, and speech with Lyria and advanced audio models
- Music composition
- Voice synthesis
- Sound effects
- Podcasts
Live API
Real-time conversational AI with streaming responses
- Voice conversations
- Real-time chat
- Live assistance
- Interactive AI
Text Generation
Generate high-quality text content with access to a library language models from all major providers. Perfect for code generation, creative writing, documentation, and translations.
Supported Models
- • Gemini 2.5 Pro with Deep Think (Google)
- • Gemini 2.5 Flash (Google)
- • Gemini 2.0 Flash (Google)
- • Claude 4 Sonnet (Anthropic)
- • Llama 3.1 405B (Meta)
- • Custom fine-tuned models
Key Features
- • Streaming responses for real-time UX
- • Function calling capabilities
- • Intelligent model routing
- • Built-in prompt optimization
- • Cost tracking and analytics
- • Rate limiting and caching
// Generate text with Gemini 2.5 Pro
const response = await fetch('https://api.tenzro.com/cortex/generate', {
method: 'POST',
headers: {
'X-API-Key': 'sk_your_key_here',
'Content-Type': 'application/json'
},
body: JSON.stringify({
prompt: "Write a Python function to calculate fibonacci numbers",
model: "gemini-2.5-pro",
max_tokens: 2048,
temperature: 0.7,
thinking_budget: 1000,
show_thinking: true,
system_prompt: "You are a helpful coding assistant",
stream: true // Enable streaming
})
});
// Handle streaming response
const reader = response.body.getReader();
while (true) {
const { done, value } = await reader.read();
if (done) break;
const chunk = new TextDecoder().decode(value);
const lines = chunk.split('\n').filter(line => line.trim());
for (const line of lines) {
if (line.startsWith('data: ')) {
const data = JSON.parse(line.slice(6));
if (data.content) {
console.log(data.content); // Stream content to UI
}
}
}
}
Multimodal AI
Analyze images, videos, and documents with advanced vision models. Extract text, understand content, and answer questions about visual data with enterprise-grade accuracy.
Image Analysis
Understand and describe images
Document OCR
Extract text from documents
Visual Q&A
Ask questions about images
// Analyze an image with Gemini 2.5 Pro
const formData = new FormData();
formData.append('image', imageFile);
formData.append('prompt', 'Describe this image in detail and identify all objects');
formData.append('model', 'gemini-2.5-pro');
formData.append('max_tokens', '1000');
const response = await fetch('https://api.tenzro.com/cortex/analyze/image', {
method: 'POST',
headers: {
'X-API-Key': 'sk_your_key_here'
},
body: formData
});
const result = await response.json();
console.log(result.description);
// Document OCR with Gemini 2.0 Flash
const ocrResponse = await fetch('https://api.tenzro.com/cortex/analyze/document', {
method: 'POST',
headers: {
'X-API-Key': 'sk_your_key_here',
'Content-Type': 'application/json'
},
body: JSON.stringify({
image_url: "https://example.com/document.pdf",
model: "gemini-2.0-flash",
extract_text: true,
extract_tables: true
})
});
const ocrData = await ocrResponse.json();
console.log(ocrData.extracted_text);
Live API
Build real-time conversational AI applications with WebSocket connections. Support for voice input/output, streaming responses, and interactive AI assistants.
Voice Conversations
Real-time voice input and speech synthesis for natural conversations
Interactive Chat
Low-latency text conversations with streaming responses
// Initialize a live session with Gemini 2.0 Flash
const session = await fetch('https://api.tenzro.com/cortex/live/session', {
method: 'POST',
headers: {
'X-API-Key': 'sk_your_key_here',
'Content-Type': 'application/json'
},
body: JSON.stringify({
model: "gemini-2.0-flash",
response_modalities: ["TEXT", "AUDIO"],
voice: "alloy",
instructions: "You are a helpful AI assistant."
})
});
const sessionData = await session.json();
// Connect to WebSocket
const ws = new WebSocket(
`wss://api.tenzro.com/cortex/live/ws/${sessionData.id}?api_key=sk_your_key_here`
);
ws.onopen = () => {
console.log('Connected to live session');
// Send a message
ws.send(JSON.stringify({
type: 'conversation.item.create',
item: {
type: 'message',
role: 'user',
content: [{ type: 'input_text', text: 'Hello, how can you help me?' }]
}
}));
// Generate response
ws.send(JSON.stringify({ type: 'response.create' }));
};
ws.onmessage = (event) => {
const message = JSON.parse(event.data);
switch (message.type) {
case 'response.text.delta':
// Handle streaming text
console.log('Text chunk:', message.delta);
break;
case 'response.audio.delta':
// Handle streaming audio
playAudioChunk(message.delta);
break;
case 'response.done':
console.log('Response complete');
break;
}
};
Quick Examples
// Generate text with Gemini 2.5 Pro
const response = await fetch('https://api.tenzro.com/cortex/generate', {
method: 'POST',
headers: {
'X-API-Key': 'sk_your_key_here',
'Content-Type': 'application/json'
},
body: JSON.stringify({
prompt: "Write a Python function to calculate fibonacci numbers",
model: "gemini-2.5-pro",
max_tokens: 2048,
temperature: 0.7,
thinking_budget: 1000,
show_thinking: true,
system_prompt: "You are a helpful coding assistant"
})
});
const data = await response.json();
console.log(data.content);
console.log('Thinking trace:', data.thinking_trace);
Key Features
Multi-Provider Access
- Unified API for Google, Anthropic, Meta, and more
- Intelligent model selection based on your requirements
- Automatic failover when providers are unavailable
- Cost optimization across different providers
Enterprise Features
- Built-in rate limiting and caching for better performance
- Function calling for complex AI workflows
- Real-time streaming for interactive applications
- Advanced security and compliance features
Need help? Check out our Quick Start guide or contact support