API Reference

The VexNode API is organized around REST. All requests and responses use JSON. Authentication is via Bearer token in the Authorization header.

Base URL

https://api.vexnode.ai/v1

Authentication

Include your API key in the Authorization header of every request:

http

Authorization: Bearer vx-your-api-key

Endpoints

Method	Endpoint	Description
POST	/v1/compute	Submit a new compute job to the network
GET	/v1/jobs/:id	Retrieve status and results of a specific job
GET	/v1/usage	Get current billing period usage and cost breakdown
POST	/v1/inference	Run real-time inference (OpenAI-compatible chat completions endpoint)

Example: Create Compute Job

Request

cURL

curl -X POST https://api.vexnode.ai/v1/compute \
  -H "Authorization: Bearer vx-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/Llama-3-70B",
    "gpu_type": "A100-80GB",
    "input": {
      "prompt": "Explain quantum computing",
      "max_tokens": 512
    }
  }'

Response

200 OK

{
  "id": "job_abc123def456",
  "object": "compute.job",
  "status": "running",
  "model": "meta-llama/Llama-3-70B",
  "gpu_type": "A100-80GB",
  "created_at": "2026-03-18T12:00:00Z",
  "estimated_cost": 0.0032,
  "output": null
}

Example: Get Job Status

cURL

curl https://api.vexnode.ai/v1/jobs/job_abc123def456 \
  -H "Authorization: Bearer vx-your-api-key"

200 OK

{
  "id": "job_abc123def456",
  "object": "compute.job",
  "status": "completed",
  "model": "meta-llama/Llama-3-70B",
  "gpu_type": "A100-80GB",
  "created_at": "2026-03-18T12:00:00Z",
  "completed_at": "2026-03-18T12:00:04Z",
  "duration_ms": 3842,
  "cost": 0.0028,
  "output": {
    "text": "Quantum computing uses quantum bits (qubits)...",
    "tokens_used": 487
  }
}