DEVELOPER PLATFORM API v2.0

Build Enterprise AI Applications with VoyageAi REST API

High-speed inference API powering Nemotron 3 Ultra 550B, Llama 3.1 8B, DeepSeek Coder, Mistral 7B & Gemma 7B.

API Authentication

All REST API requests require a Bearer Token in the HTTP Authorization header:

Authorization: Bearer voyage_sk_your_api_key_here

Projects & API Keys Console

API keys require a Project with attached Billing. Projects limit: 2/month. API keys limit: 4/project/month.

Active Developer Projects

Create projects, attach billing, and manage API access credentials.

PROJECT ID	PROJECT NAME	BILLING STATUS	API KEYS	ACTIONS
No active projects. Click "New Project Wizard" to start.

Quickstart Code Examples

curl -X POST "https://chat.voyageai.online/api/llm/chat" \
  -H "Authorization: Bearer voyage_sk_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/nemotron-3-ultra-550b-a55b",
    "messages": [
      {"role": "user", "content": "Write a Python script to scan open network ports."}
    ],
    "enable_thinking": true,
    "reasoning_budget": 2048
  }'

const response = await fetch("https://chat.voyageai.online/api/llm/chat", {
  method: "POST",
  headers: {
    "Authorization": "Bearer voyage_sk_your_api_key",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    model: "meta/llama-3.1-8b-instruct",
    messages: [{ role: "user", content: "Create an Express JS REST server." }]
  })
});

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

import requests

url = "https://chat.voyageai.online/api/llm/chat"
headers = {
    "Authorization": "Bearer voyage_sk_your_api_key",
    "Content-Type": "application/json"
}
payload = {
    "model": "deepseek-ai/deepseek-coder-6.7b-instruct",
    "messages": [{"role": "user", "content": "Write a C++ binary search algorithm."}]
}

response = requests.post(url, json=payload, headers=headers)
print(response.json()["content"])

Endpoint Reference

POST /api/llm/chat

Generate AI completions with model catalog selection and optional reasoning log.

Request Body (JSON)

Field	Type	Description
`messages`	Array	List of message objects `[{"role": "user", "content": "..."}]`
`model`	String	Model ID (e.g., `nvidia/nemotron-3-ultra-550b-a55b`)
`enable_thinking`	Boolean	Enable Nemotron 3 Ultra reasoning chain

POST /api/llm/generate_stream

Real-time Server-Sent Events (SSE) streaming endpoint for Desktop and Web UIs.

GET /api/llm/models

Retrieve the catalog of all available AI models filtered by subscription tier.