Enchant AI - Unified Frontier AI API Gateway

Welcome to Developer Console

Your account is active. Use your API keys to query frontier models or test live requests in AI Playground.

Input (Prompt)

Tokens in prompt & context

Output (Generated)

Tokens generated by AI models

Cache Read (Hit)

Tokens served with fast cache

Quota Usage 500,000 remaining

0 / 500,000

Quick Connect Snippet

Standard OpenAI SDK configuration.

from openai import OpenAI

client = OpenAI(
    base_url="https://testapi.enchant.id/v1",
    api_key="sk-enchant-your-key-here"
)

response = client.chat.completions.create(
    model="auto",
    messages=[{"role": "user", "content": "Hello Enchant AI!"}]
)
print(response.choices[0].message.content)

API Key Management

Generate isolated API keys with custom quota limits for your applications & sub-agents.

Key Name	Secret Key	Quota Limit	Created	Actions

Available Models & Cost Multipliers

Standardized OpenAI compatible endpoints.

Model Identifier	Provider	Capabilities	Latency	Multiplier
auto SMART ROUTER	Enchant Router	Multimodal Text Vision Video Code	<5ms + Stream	1x - 2x
deepseek-v4-flash	DeepSeek	Text Only Code & Debug Reasoning	~140ms	1x Token
deepseek-v4-flash-vision-exp	DeepSeek	Vision Input Text OCR	~190ms	1.25x Token
glm-5.3-flash	Zhipu AI	Text Only Multilingual Tools	~120ms	1x Token
qwen3.8-flash	Alibaba Cloud	Text Only Math & Logic Code	~150ms	1x Token
hy3	Hailuo AI	Video Prompt Text Creative	~210ms	2x Token

Developer Integration & Agent Frameworks

Connect sub-agents, autonomous swarms, Cursor, Cline, and SDKs.

MULTI-AGENT & SWARMS Hermes Agent / OpenRouter / AutoGen

Hermes Agent / OpenRouter Compatible Setup

You can connect autonomous sub-agent swarms. The gateway will automatically manage sub-agent concurrency with isolated quotas and load balance across upstream keys.

# Environment Variables for Hermes / AutoGen / CrewAI
OPENAI_BASE_URL="https://testapi.enchant.id/v1"
OPENAI_API_KEY="sk-enchant-your-key"
DEFAULT_MODEL="auto"  # Automatically uses code model for sub-agent coders & vision for image analyzers

Cursor IDE / Cline (VS Code Extension)

In Cursor or Cline settings, select OpenAI Compatible:

Base URL / Override

https://testapi.enchant.id/v1

Model Name

auto (or deepseek-v4-flash)

Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    base_url="https://testapi.enchant.id/v1",
    api_key="sk-enchant-your-api-key"
)

response = client.chat.completions.create(
    model="auto",
    messages=[{"role": "user", "content": "Explain async await in Python with an example."}]
)

print(response.choices[0].message.content)

Smart Adaptive Key Pool & Latency Health

Real-time EMA latency scoring and auto-failover status across upstream keys.

Active Upstream Cluster: b.ai Multi-Key Cluster

Dynamic routing automatically directs queries to the lowest latency key.

Slot	Key Preview	Avg Latency (EMA)	Total Calls	Error Count	Health Status	Actions

Registered Users & Quotas

Manage token allowances, roles, and account permissions.

User	Role	Quota Total	Used	Status	Actions

Real-Time Traffic Audit Logs

Live audit stream of all completions requests with model, latency, and upstream key slot.

Time	User	Upstream Slot	Model Routed	Multiplier	Latency	Status

One Unified API For Frontier AI Models

Frontier Model Roster & Smart Router

auto

deepseek-v4-flash

deepseek-v4-flash-vision-exp

glm-5.3-flash

qwen3.8-flash

hy3

Enterprise Gateway Architecture

Adaptive Latency Balancer

Multi-Agent & Swarms Ready

Zero Data Logging & Privacy

Transparent API Plans

Developer Free

Pro Builder

Enterprise

Drop-in Integration in 30 Seconds

Developer Portal

Welcome to Developer Console

Quick Connect Snippet

API Key Management

AI Playground & Multimodal Tester

Execution Parameters

Available Models & Cost Multipliers

Developer Integration & Agent Frameworks

Hermes Agent / OpenRouter Compatible Setup

Cursor IDE / Cline (VS Code Extension)

Python (OpenAI SDK)

Visual Traffic Analytics & Charts

Hourly Request Volume (Throughput)

Model Distribution Breakdown

Smart Adaptive Key Pool & Latency Health

Active Upstream Cluster: b.ai Multi-Key Cluster

Registered Users & Quotas

Model Multipliers & Rate Limiting

Model Cost Multipliers

Global Broadcast Announcement Banner

Real-Time Traffic Audit Logs

Create New API Key

Edit User Account

Add Master API Key to Cluster Pool

One Unified API For
Frontier AI Models