ai-synapse 4.0.8

Free multi-provider AI SDK — drop-in OpenAI & Anthropic compatibility with 27 free providers

AI Synapse — Free Multi-Provider AI SDK

Stop paying for AI inference. Drop-in from ai_engine import OpenAI — routes through 27+ free providers with automatic failover and intelligent routing.

---

Free Providers

No API Key Required (Truly Free)

Provider	Model	Endpoint
Pollinations	openai	text.pollinations.ai/openai
Hermes	Hermes-3-Llama	hermes.ai.unturf.com/v1
G4F Groq	llama-3.3-70b	g4f.space/api/groq
G4F Gemini	gemini-2.5-flash	g4f.space/api/gemini
G4F NVIDIA	nemotron-3	g4f.space/api/nvidia
OpenCode Zen	north-mini-code	opencode.ai/zen/v1

Free Tier APIs (Signup Required)

Provider	Free Tier	Signup
Groq	30 RPM, 14,400 RPD	console.groq.com
OpenRouter	23 free models	openrouter.ai
Gemini	5-30 RPM	aistudio.google.com
NVIDIA	40 RPM	build.nvidia.com
Cerebras	30 RPM	cloud.cerebras.ai
Cloudflare	10K neurons/day	dash.cloudflare.com
GitHub	Varies	github.com/marketplace
Vercel	$5/month free	vercel.com
Cohere	20 RPM, 1K/month	cohere.com
Mistral	1 RPS, 500K tokens/min	console.mistral.ai
HuggingFace	$0.10/month	huggingface.co
Kilo	Auto free routing	app.kilo.ai

Custom Providers (Your Keys)

Provider	Models	Signup
hcnsec	Various	api.hcnsec.cn
LLM7	Various	llm7.io
PaxSenix	Various	api.paxsenix.org

Self-Hosted Options

Provider	Setup	Models
GPT4Free	docker run -p 8080:8080 hlohaus789/g4f	GPT-4o, Claude, Gemini
Ollama	curl -fsSL https://ollama.com/install.sh | sh	Llama, Mistral, etc.

---

Quick Start

Option 1: Free Tier APIs (Recommended)

# 1. Copy environment template
cp .env.example .env

# 2. Get free API keys (see guide below)
# 3. Add keys to .env file
# 4. Start server
python server.py

Option 2: Self-Hosted (No API Keys Needed)

# Start g4f server
docker run -d -p 8080:8080 hlohaus789/g4f

# Start AI Engine
python server.py

---

For Developers

OpenAI SDK Compatible

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:8000/v1",
    api_key="dummy"  # Not needed for free providers
)

# Chat completion
response = client.chat.completions.create(
    model="gpt-4",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

# Streaming
stream = client.chat.completions.create(
    model="gpt-4",
    messages=[{"role": "user", "content": "Tell me a story"}],
    stream=True
)
for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

cURL

curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-4", "messages": [{"role": "user", "content": "Hello!"}]}'

JavaScript

import OpenAI from 'openai';

const client = new OpenAI({
    baseURL: 'http://localhost:8000/v1',
    apiKey: 'dummy'
});

const response = await client.chat.completions.create({
    model: 'gpt-4',
    messages: [{ role: 'user', content: 'Hello!' }]
});

---

Features

Core

• OpenAI-compatible API with streaming
• Automatic provider failover
• Intelligent key rotation
• Response caching with TTL

Intelligence

• Task-based model selection
• Cost optimization
• Latency tracking
• A/B testing

Enterprise

• Multi-tenancy with quotas
• RBAC (Admin/User/Viewer)
• Audit logging
• Billing tracking

Platform

• Plugin system
• Workflow engine
• CLI tool
• Docker deployment

---

API Endpoints

Endpoint	Method	Description
/v1/chat/completions	POST	Chat completions (OpenAI-compatible, supports stream: true)
/v1/models	GET/POST	List all models
/api/providers	GET	List providers
/api/health/{name}/ping	POST	Live health ping for a provider
/api/capabilities	GET	Provider/model capabilities (vision, etc.)
/api/status	GET	Engine status
/api/statistics	GET	Usage statistics
/health	GET	Health check
/metrics	GET	Prometheus metrics
/docs	GET	Swagger UI (interactive API explorer)
/redoc	GET	ReDoc API documentation

Rate Limit Headers

All API responses include:

• X-RateLimit-Limit — Max requests per minute
• X-RateLimit-Remaining — Remaining requests in current window

---

Documentation

• API Reference
• User Guide
• Deployment Guide
• Security Guide
• Provider Setup

---

Contributing

See CONTRIBUTING.md for guidelines.

---

License

MIT License - See LICENSE