Gracestack Chat API

Qwen3-32B on Azure A100 GPUs. OpenAI-compatible. No signup.

curl -s https://tools.gracestack.se/api/chat \
  -H "Content-Type: application/json" \
  -d '{"message":"Explain monads in one sentence"}'
Get Free API Key → Try in Browser →
28API keys issued 5Power Pack users Qwen3-32BModel A100 80GBGPU <5sAvg latency

Pricing

Free

$0
Get Free Key →

Quick Start

1. Get a free API key (one click, no email):

curl https://tools.gracestack.se/api/register

2. Chat (pass key as header or query param):

curl -s https://tools.gracestack.se/api/chat \
  -H "Content-Type: application/json" \
  -H "X-API-Key: YOUR_KEY" \
  -d '{"message":"Write a Python function to reverse a linked list"}'

# Each response includes:
# { "response": "...", "calls_remaining": 2 }

3. When you hit the limit:

# HTTP 429 — upgrade to Power Pack ($1 for 100 calls)
# Response body includes upgrade_url for instant purchase

Endpoints

POST /api/chat          — AI chat (3 free/day, $1 for 100)
GET  /api/register      — Instant API key (no email)
GET  /api               — API info & status
POST /api/fashion-concept — AI fashion design concepts
POST /api/generate-fashion-image — AI fashion image generation

Full documentation: api-docs.html


Why this API?

Most free AI APIs are throttled, slow, or require signup. We run Qwen3-32B on dedicated Azure A100 GPUs with no login wall. You get instant access — no email, no credit card, no OAuth. Just a key and a curl command.

OpenAI-compatible. Drop it into any tool that speaks OpenAI API format.

Gracestack AB — org.nr 559480-0000 — Stockholm, Sweden

Built by @cedendahlkim. Model: Qwen3-32B on Azure AI Foundry A100.