Free Tier Available 435+ Models OpenRouter Auto-Routing

EvolvixOS API

One API. 435+ AI models. Autonomous agents. Entity storage. Backend functions. Everything you need to build AI-powered applications — with a free tier and zero setup.

435+

AI Models

Providers

Free Models

~$0.0002

Per Call

Authentication

All API requests require an API key. Create one in your dashboard after signing up. Include it in the Authorization header:

Authorization: Bearer evx_live_xxxxxxxxxxxxxxxxxxxx

Your API key carries many privileges — keep it secret. Never expose it in client-side code.

Quick Start

Send your first AI request in 30 seconds:

curl -X POST https://evolvixos.com/platform/api/chat \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "message": "Write a Python function to check if a number is prime",
    "model": "openrouter/auto"
  }'

The openrouter/auto model automatically selects the best AI for your task — no need to choose between 435+ models.

Chat Completion

Send messages to any of the 435+ models through a single OpenAI-compatible endpoint.

POST /platform/api/chat

Send a chat message and get an AI response. Auto-routes to the best model.

Request

Parameter	Type	Required	Description
`message`	string	Yes	The user's message
`model`	string	No	Model ID (default: `openrouter/auto`)
`temperature`	float	No	0-1, default 0.7
`max_tokens`	int	No	Max response tokens, default 4096
`system`	string	No	System prompt

Example Response

{
  "response": "def is_prime(n):\n    if n < 2: return False\n    for i in range(2, int(n**0.5)+1):\n        if n % i == 0: return False\n    return True",
  "model": "deepseek/deepseek-v4-flash-0731",
  "provider": "openrouter",
  "tokens": 156,
  "cost": 0.000218,
  "latency_ms": 832
}

Model Playground

Test any model directly without creating an agent. Pure model chat — no builder prompt, no entity creation.

POST /platform/api/playground

Send a message to any model. Returns response + model metadata. Requires auth.

Request

Parameter	Type	Required	Description
`message`	string	Yes	The message to send
`model`	string	No	Model ID or `auto` (default)
`system_prompt`	string	No	System prompt for the model
`temperature`	float	No	0-1, default 0.7
`max_tokens`	int	No	Max response tokens, default 1000

Example

curl -X POST https://evolvixos.com/platform/api/playground \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "message": "Review this code: def fib(n): return fib(n-1)+fib(n-2)",
    "system_prompt": "You are a senior code reviewer.",
    "temperature": 0.3,
    "max_tokens": 1000
  }'

Response

{
  "response": "The function is missing a base case...",
  "model": "deepseek/deepseek-v4-flash-0731",
  "provider": "openrouter",
  "usage": {}
}

Demo (No Signup)

Try the platform without creating an account. 5 free requests per IP per 24 hours.

POST /platform/api/demo

Public endpoint, no auth required. Auto-routing only. Rate-limited.

Request

Parameter	Type	Required	Description
`message`	string	Yes	Message (max 1000 chars)
`system_prompt`	string	No	System prompt (max 500 chars)
`temperature`	float	No	0-1, default 0.7
`max_tokens`	int	No	Max 500

Example

curl -X POST https://evolvixos.com/platform/api/demo \
  -H "Content-Type: application/json" \
  -d '{"message": "Write a haiku about code"}'

Response

{
  "response": "Lines of logic flow...",
  "model": "nvidia/nemotron-3.5-lightning-30b-a3b",
  "provider": "nvidia",
  "demo": true,
  "remaining": 4,
  "limit": 5
}

Note: When rate limit is reached, returns 429 with a signup message.

List Models

GET /platform/api/models

List all 435+ available AI models (local + OpenRouter)

curl https://evolvixos.com/platform/api/models \
  -H "Authorization: Bearer YOUR_API_KEY"

Filter by category: chat, code, reasoning, vision, local, routing

Agents

Create autonomous AI agents that can execute multi-step workflows with tools.

GET /platform/api/agents

List your agents

POST /platform/api/agents

Create a new agent with a name, model, and system prompt

POST /platform/api/orchestrate

Run an agent on a goal — it plans and executes multi-step tasks

curl -X POST https://evolvixos.com/platform/api/orchestrate \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "goal": "Research the latest trends in AI and write a summary"
  }'

Entities (Database)

Create JSON-schema-defined data tables with instant CRUD API.

POST /platform/api/entities

Create a new entity (table) with a JSON schema

GET /platform/api/entities/{name}/records

List records in an entity with pagination, filtering, sorting

curl -X POST https://evolvixos.com/platform/api/entities \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Task",
    "schema": {
      "properties": {
        "title": {"type": "string"},
        "status": {"type": "string", "enum": ["todo", "doing", "done"]},
        "priority": {"type": "string", "enum": ["low", "medium", "high"]}
      },
      "type": "object"
    }
  }'

Workflows

Automate tasks with scheduled or entity-triggered workflows.

GET /platform/api/workflows

List all workflows

POST /platform/api/workflows

Create a workflow with trigger + steps

Backend Functions

Deploy Python code as HTTP endpoints — no server management.

POST /platform/api/functions

Deploy a new backend function

GET /platform/api/fn/{name}

Execute a deployed function

File Storage

Upload and manage files with CDN-backed public URLs or private signed URLs.

POST /platform/api/files/upload

Upload a file and get a public URL

Streaming (Coming Soon)

Server-Sent Events (SSE) streaming for real-time responses. Currently in development.

# Planned API (not yet available)
curl -N https://evolvixos.com/platform/api/playground/stream \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"message":"Write a story","model":"auto"}'

# Response: SSE stream
# data: {"chunk": "Once"}
# data: {"chunk": " upon"}
# data: {"chunk": " a time"}
# data: [DONE]

Monitoring

GET /platform/api/monitor

Server health, CPU, RAM, GPU status

Rate Limits

Plan	Requests/min	Models	Agents	Price
Free	10	435+	1	€0/mo
Starter	30	435+	5	€9/mo
Pro	60	435+	25	€29/mo
Business	120	435+	Unlimited	€99/mo

Error Codes

Code	Meaning
400	Bad request — invalid parameters
401	Unauthorized — missing or invalid API key
403	Forbidden — insufficient permissions
404	Not found — resource doesn't exist
429	Rate limited — too many requests
500	Server error — try again or contact support

Python SDK

import requests

API_KEY = "evx_live_xxxxxxxxxxxx"
BASE = "https://evolvixos.com/platform/api"

# Chat completion
resp = requests.post(f"{BASE}/chat",
    headers={"Authorization": f"Bearer {API_KEY}"},
    json={"message": "What is 2+2?", "model": "openrouter/auto"}
)
print(resp.json()["response"])

# List models
models = requests.get(f"{BASE}/models",
    headers={"Authorization": f"Bearer {API_KEY}"}
)
print(f"{len(models.json()['models'])} models available")

JavaScript SDK

const API_KEY = "evx_live_xxxxxxxxxxxx";
const BASE = "https://evolvixos.com/platform/api";

// Chat completion
const resp = await fetch(`${BASE}/chat`, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${API_KEY}`,
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    message: "Write a hello world in Python",
    model: "openrouter/auto"
  })
});
const data = await resp.json();
console.log(data.response);

cURL Examples

# Chat with auto-routing
curl -X POST https://evolvixos.com/platform/api/chat \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"message": "Explain quantum computing"}'

# List all models
curl https://evolvixos.com/platform/api/models \
  -H "Authorization: Bearer $API_KEY"

# Create an agent
curl -X POST https://evolvixos.com/platform/api/agents \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"name": "Code Reviewer", "model": "openrouter/auto"}'

Ready to build?

Start free with 435+ AI models, autonomous agents, and one unified API.

Get Started Free →