Skip to main content

​
Overview

SambaNova provides ultra-fast AI inference powered by their Reconfigurable Dataflow architecture, optimized for production workloads. Key Features:
  • Dataflow-optimized AI acceleration
  • Sub-100ms latency
  • OpenAI-compatible API
  • Enterprise-grade reliability
Official Documentation: SambaNova Docs

​
Authentication

SambaNova uses Bearer token authentication with Open AI-compatible format. Lava Forward Token: 
${LAVA_SECRET_KEY}.${CONNECTION_SECRET}.${PRODUCT_SECRET}
For BYOK: ${TOKEN}.${YOUR_SAMBANOVA_KEY}
ModelContextDescription
Meta-Llama-3.3-70B-Instruct128KLlama 3.3 flagship
Llama-3.2-3B-Instruct128KFast, efficient model
Endpoint: https://api.sambanova.ai/v1/chat/completions Usage Tracking: data.usage (OpenAI format)

​
Quick Start

const response = await fetch(
  `https://api.lavapayments.com/v1/forward?u=${encodeURIComponent('https://api.sambanova.ai/v1/chat/completions')}`,
  {
    method: 'POST',
    headers: {
      'Authorization': `Bearer ${process.env.LAVA_FORWARD_TOKEN}`,
      'Content-Type': 'application/json'
    },
    body: JSON.stringify({
      model: 'Meta-Llama-3.3-70B-Instruct',
      messages: [{role: 'user', content: 'Hello!'}]
    })
  }
);

const data = await response.json();
console.log('Usage:', data.usage.total_tokens);

​
BYOK Support

✅ Supported - Get API key from SambaNova Cloud

​
Resources