⚒️ Forge AI API

Zero-Cost AI Inference — Powered by Qwen3 30B

Forge AI provides production-ready NLP API endpoints backed by local LLM inference. No per-request costs, no data leaving the server, no compromises.

🌐 Live: https://rafael226.github.io/forge-ai-api/

---

🚀 Endpoints

All endpoints accept POST requests with JSON bodies. Authentication via Bearer token.

Base URL: Contact us for access — base URL is provided with your API key.

Authentication

Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

---

POST /api/summarize

Condense long text into a concise summary.

Parameter	Type	Required	Description
text	string	✅	The text to summarize
max_length	integer	❌	Max summary length in words (default: 150)

Request:

{
  "text": "Your long article or document text goes here...",
  "max_length": 100
}

Response:

{
  "summary": "A concise summary of the provided text...",
  "model": "qwen3-30b",
  "tokens_used": 87
}

---

POST /api/extract

Extract structured data from unstructured text.

Parameter	Type	Required	Description
text	string	✅	The text to extract from
fields	array	❌	Specific fields to extract (e.g., ["names", "dates", "amounts"])

Request:

{
  "text": "John Smith signed the contract on March 5th for $50,000.",
  "fields": ["names", "dates", "amounts"]
}

Response:

{
  "extracted": {
    "names": ["John Smith"],
    "dates": ["March 5th"],
    "amounts": ["$50,000"]
  }
}

---

POST /api/rewrite

Rewrite text in a different tone or style.

Parameter	Type	Required	Description
text	string	✅	The text to rewrite
style	string	❌	Target style: formal, casual, technical, simple (default: formal)
language	string	❌	Output language ISO code (default: en)

Request:

{
  "text": "The quarterly earnings exceeded expectations by a significant margin.",
  "style": "casual"
}

Response:

{
  "rewritten": "So the company absolutely crushed it this quarter — way better than anyone expected.",
  "original_length": 68,
  "new_length": 79
}

---

POST /api/sentiment

Analyze sentiment and emotional tone.

Parameter	Type	Required	Description
text	string	✅	The text to analyze

Request:

{
  "text": "This product is absolutely amazing, best purchase I've ever made!"
}

Response:

{
  "sentiment": "positive",
  "score": 0.94,
  "emotions": {
    "joy": 0.87,
    "surprise": 0.12,
    "anger": 0.01
  }
}

---

⚙️ Rate Limits

Tier	Requests/Day	Concurrent
Beta	1,000	5

Rate limit headers are included in every response:

X-RateLimit-Limit: 1000
X-RateLimit-Remaining: 997
X-RateLimit-Reset: 1708300800

---

🔒 Privacy & Security

• No data retention — inputs are processed and discarded
• Local inference — data never leaves the server
• Bearer token auth — all requests authenticated
• HTTPS only — encrypted in transit

---

🛠️ Error Codes

Code	Meaning
400	Invalid request body
401	Missing or invalid API key
429	Rate limit exceeded
500	Internal inference error

---

📬 Request Beta Access

Forge AI is in closed beta. To request access:

📧 Email: rafael@mbglaw.com.br

Include your use case and expected request volume. We'll reply with your API key and base URL.

---

About

Forge AI — Built by an AI agent and The Architect.

Powered by Qwen3 30B running on local hardware with zero inference cost.

© 2026 Forge AI. All rights reserved.