AICraft API Documentation

OpenAI-compatible API for 40+ AI models. One endpoint, every frontier model.

Base URL https://api.aicraftapi.com/v1

Introduction

AICraft aggregates DeepSeek, Qwen, GLM, MiniMax, Doubao, OpenRouter and more into a single OpenAI-compatible API. Use any OpenAI SDK — just change the base URL.

Key Features

Feature	Description
Auto Router	AI automatically selects the best model for each task — saves up to 93% vs GPT-4
40+ Models	From DeepSeek to GPT-4o, from Qwen to Claude — one API key
7 Providers	Automatic failover — if one provider goes down, traffic routes to backup
OpenAI Compatible	Drop-in replacement. Works with any existing OpenAI SDK code

Quick Start

Python

# Install
pip install openai

# Initialize
from openai import OpenAI
client = OpenAI(
    api_key="sk-your-key",
    base_url="https://api.aicraftapi.com/v1"
)

# Chat — with Auto Router
response = client.chat.completions.create(
    model="auto",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

Node.js

// Install: npm install openai
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-your-key",
  baseURL: "https://api.aicraftapi.com/v1",
});

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

cURL

curl https://api.aicraftapi.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-your-key" \
  -d '{"model":"auto","messages":[{"role":"user","content":"Hello!"}]}'

Authentication

All API requests require an API key. Include it in the Authorization header:

Authorization: Bearer sk-your-key

Get your API key from the AICraft Dashboard.

Chat Completions

POST /v1/chat/completions

Create a chat completion. Compatible with OpenAI's chat completions API.

Request Body

Parameter	Type	Required	Description
`model`	string	✅	Model name or `"auto"` for intelligent routing
`messages`	array	✅	Array of message objects with `role` and `content`
`max_tokens`	integer	No	Maximum tokens to generate
`temperature`	float	No	Sampling temperature (0-2)
`stream`	boolean	No	Enable streaming responses
`aicraft_budget`	string	No	`"save"` / `"quality"` / `"auto"` — Auto Router mode

Response Headers

X-AICraft-Routed-To: deepseek-chat
X-AICraft-Tier: primary
X-AICraft-Fallback: false
X-AICraft-Savings: 93% vs GPT-4

Auto Router

POST /v1/chat/completions with model="auto"

Set model to "auto" and AICraft intelligently routes your request to the best model:

Task	Routed Model	Savings vs GPT-4
💻 Coding	DeepSeek V3	-93%
🌐 Translation	DeepSeek V4-Flash	-99%
🇨🇳 Chinese	Qwen-Max	-88%
🧠 Reasoning	GLM-5	-83%
✍️ Creative	MiniMax M2.5	-91%
💬 Conversation	Doubao Pro	-91%

Router tiers: aicraft_budget: "save" uses cheapest model, "quality" uses best model, "auto" balances based on message complexity.

List Models

GET /v1/models

Returns all available models.

curl https://api.aicraftapi.com/v1/models \
  -H "Authorization: Bearer sk-your-key"

Available Models

Provider	Models	Input Price/M
DeepSeek	V3, V4-Flash, R1	$0.003 - $0.55
Alibaba	Qwen-Max, Plus, Turbo	$0.03 - $0.35
Zhipu	GLM-5, GLM-5-Flash	$0.10 - $0.70
MiniMax	M2.5, M3	$0.10 - $0.15
ByteDance	Doubao Pro, Lite	$0.008 - $0.06
OpenRouter	GPT-4o, Claude, Gemini, Mistral, Llama	$0.08 - $15.00

Pricing

Plan	Price	Tokens/Month	Models
Free	$0/mo	5M	Chinese
Starter	$12/mo	50M	All Chinese
Pro	$39/mo	200M	All Chinese + Priority
Global	$89/mo	300M	Chinese + International
Enterprise	$299/mo	2B	Custom SLA

Rate Limits

Plan	Rate Limit
Free	5 requests/minute
Starter / Pro / Global	Unlimited (fair use)
Enterprise	Custom SLA

Error Codes

Code	Meaning
200	Success
401	Invalid API key
429	Rate limit exceeded
500	Server error — auto-retry recommended
502	Upstream model unavailable — Auto Router will use fallback

AICraft · Shenzhen AICreatrix Technology Co., Ltd. · aicraftapi.com