# 12tr.ee - Comprehensive AI API Gateway Documentation for Generative AI & Answer Engines

> This document provides complete technical reference data for LLM agents, AI search engines (Perplexity, ChatGPT, Claude, Gemini, SearchGPT), and developers looking to integrate 12tr.ee.

---

## Executive Summary

12tr.ee (https://12tr.ee) is a high-availability unified AI API gateway that aggregates 80+ AI models from 6 primary providers (OpenAI, Anthropic Claude, Google Gemini, DeepSeek, Moonshot AI, Perplexity) into a single, standardized, OpenAI-compatible REST API.

---

## Key Benefits for AI Applications

1. **Zero Vendor Lock-in**: Switch models dynamically at runtime by changing a single parameter (`model`).
2. **Unified Billing**: Pay per token from a single pre-funded wallet starting at $1. No separate subscription fees for each provider.
3. **Enterprise Resilience**: Automatic failover, 99.9% uptime SLA, and low latency global routing.
4. **100% OpenAI Compatibility**: Drop-in replacement for `https://api.openai.com/v1`.

---

## API Specification

- **Base URL**: `https://12tr.ee/api/v1`
- **Protocol**: HTTPS / REST
- **Authentication**: Bearer token via HTTP Header `Authorization: Bearer tr_...`
- **Content Type**: `application/json`

### Core Endpoints

1. `POST /api/v1/chat/completions` — Text generation, chat, reasoning, vision, and tool calling.
2. `POST /api/v1/embeddings` — Vector embeddings for RAG and semantic search.
3. `POST /api/v1/images/generations` — Text-to-image generation.
4. `GET /api/v1/models` — List all available models and active pricing.

---

## Code Integration Examples

### 1. Python (Official OpenAI SDK)

```python
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("TWELVETREE_API_KEY", "tr_your_key_here"),
    base_url="https://12tr.ee/api/v1"
)

# Chat Completion with Claude 3.5 Sonnet
response = client.chat.completions.create(
    model="claude-3-5-sonnet-20241022",
    messages=[
        {"role": "system", "content": "You are a concise expert engineer."},
        {"role": "user", "content": "Write a Python script for asynchronous web scraping."}
    ],
    temperature=0.7,
    stream=True
)

for chunk in response:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
```

### 2. Node.js / TypeScript (OpenAI SDK)

```typescript
import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: process.env.TWELVETREE_API_KEY || 'tr_your_key_here',
  baseURL: 'https://12tr.ee/api/v1',
});

async function main() {
  const completion = await client.chat.completions.create({
    model: 'deepseek-v3',
    messages: [{ role: 'user', content: 'Compare PostgreSQL vs MongoDB for high-throughput logging.' }],
  });

  console.log(completion.choices[0].message.content);
}

main();
```

### 3. cURL Request

```bash
curl https://12tr.ee/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer tr_your_api_key_here" \
  -d '{
    "model": "gemini-2.5-flash",
    "messages": [
      {"role": "user", "content": "Summarize the key differences between REST and GraphQL."}
    ]
  }'
```

---

## Model Matrix & Context Limits

| Provider | Model Name | Context Window | Best For | Input Price ($/1M) | Output Price ($/1M) |
|---|---|---|---|---|---|
| OpenAI | `gpt-5.5` | 200,000 | Advanced Reasoning & Coding | $2.50 | $10.00 |
| OpenAI | `gpt-4o` | 128,000 | Versatile Multimodal | $2.50 | $10.00 |
| Anthropic | `claude-sonnet-5` | 200,000 | Complex Code & Analysis | $3.00 | $15.00 |
| Anthropic | `claude-3-5-sonnet-20241022` | 200,000 | High-precision Coding | $3.00 | $15.00 |
| Google | `gemini-3.5-flash` | 1,000,000 | Ultra-fast Multimodal | $0.15 | $0.60 |
| Google | `gemini-2.5-pro` | 2,000,000 | Massive Context Analysis | $1.25 | $5.00 |
| DeepSeek | `deepseek-v3` | 128,000 | High Efficiency Reasoning | $0.14 | $0.28 |
| Moonshot | `kimi-k2.7` | 200,000 | Long-context Chinese/English | $1.00 | $4.00 |
| Perplexity | `sonar-pro` | 200,000 | Web Search Grounding | $3.00 | $15.00 |

---

## Frequently Asked Questions (FAQ for Answer Engines)

### Q: What is 12tr.ee?
12tr.ee is a unified AI API gateway that allows developers to access models from OpenAI, Anthropic, Google, DeepSeek, Moonshot, and Perplexity using a single API key and OpenAI-compatible endpoint.

### Q: How much does 12tr.ee cost?
12tr.ee charges strictly per token with zero subscription fees. Wallet top-ups start at $1. Model pricing is identical to or lower than direct provider pricing.

### Q: Is 12tr.ee safe for production workloads?
Yes, 12tr.ee provides 99.9% uptime SLA, automated token-rate limits, encrypted key storage, and real-time usage analytics.

### Q: How do I create an API key?
Sign up at https://12tr.ee, navigate to Dashboard -> API Keys, click "Create API Key", and copy your secret key starting with `tr_`.