aivax-request.sh

active

# Dynamic Model Gateway Request
curl -X POST https://inference.aivax.net/v1/chat/completions \
  -H "Authorization: Bearer sua_api_key" \
  -d '{
    "model": "claude-opus-4.7",
    "messages": [{"role": "user", "content": "Olá!"}]
  }'

Model Provider Anthropic

Latency 540ms

Throughput 90 t/s

# Connect web tools and enforce JSON Schema
{
  "model": "meu-agente:v1",
  "tools": ["web_search", "image_generation"],
  "response_format": {
    "type": "json_object"
  }
}

web_search

image_generation

Response JSON (Healed & Validated)

{
  "summary": "Latest AI updates...",
  "status": "success"
}

? What is the rate limit and SLA?

Vector Store Lookup (aivax-kb-04)

rate_limits.pdf 96% score

"The free tier API limit is 100 req/min. Enterprise plans support unlimited throughput."

pricing_plans.pdf 89% score

"Enterprise plans start at $499/mo and include dedicated support and custom limits."

service_sla.pdf 74% score

"We guarantee a 99.9% uptime SLA for all paying enterprise customers."

Gateway Security Shield

Checking...

System Prompt Protection

Real-time Operations Audit Log

curl -X POST https://inference.aivax.net/v1/chat/completions \
  -H "Authorization: sua_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meu-agente:50c3",
    "messages": [
      {"role": "user", "content": "Olá!"}
    ]
  }'

$0

25%

15

$39

5%

$399

0%