API Documentation

Base URL

https://api.sistematis.ai/v1

SISTEMATIS AI API is compatible with OpenAI API format. You can use existing OpenAI SDKs by changing the baseURL and apiKey.

All requests must use HTTPS and include the Authorization: Bearer YOUR_API_KEY header.

Authentication

API Keys

Get your API Key from the dashboard. Each key has the same access as your account plan.

curl https://api.sistematis.ai/v1/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer YOUR_API_KEY" \ -d '{
    "model": "sistematis-fast-v7",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

⚠️

Security Tips

• Don't share API Key publicly or commit to repository
• Use environment variables to store keys
• Rotate keys regularly through dashboard

Chat Completions

POST/chat/completions

Create a chat completion with the selected AI model.

Request Body

Parameter	Type	Required	Description
model	string	Yes	Model ID (sistematis-flex-v7, sistematis-super-v7, sistematis-fast-v7)
messages	array	Yes	Array of message objects
temperature	number	No	0.0 - 1.0 (default: 1.0)
max_tokens	integer	No	Maximum tokens in response
stream	boolean	No	Enable streaming (default: false)

Example Response

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "created": 1234567890,
  "model": "sistematis-fast-v7",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Hello! How can I help you today?"
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 8,
    "total_tokens": 18
  }
}

Anthropic Messages API

POST/messages

SISTEMATIS AI provides native Anthropic Messages API compatibility. Use this endpoint with Claude Code, the Anthropic SDK, or any Anthropic-compatible client.

Authentication

Use the x-api-key header (Anthropic standard) or Authorization: Bearer header:

x-api-key: YOUR_API_KEY

Request Body

Parameter	Type	Required	Description
model	string	Yes	Anthropic model name or SISTEMATIS alias (claude-sonnet-4, claude-opus-4, etc.)
messages	array	Yes	Array of message objects (Anthropic format)
system	string/array	No	System prompt (string or array of content blocks)
max_tokens	integer	No	Maximum tokens in response
stream	boolean	No	Enable SSE streaming (default: false)
thinking	object	No	Extended thinking: {type: 'enabled', budget_tokens: N}
tools	array	No	Function/tool definitions (Anthropic format)

Model Mapping

Anthropic model names are automatically mapped to SISTEMATIS models:

Anthropic Model	SISTEMATIS Model
claude-opus-4-7, claude-opus-4, claude-3-opus*	`sistematis-super-v7` (glm-5.1)
claude-sonnet-4-6, claude-sonnet-4, claude-3-5-sonnet*	`sistematis-flex-v7` (glm-4.7)
claude-haiku-4-5, claude-haiku-4, claude-3-5-haiku*	`sistematis-fast-v7` (glm-4.5-air)

Unknown model names default to sistematis-super-v7.

Claude Code Setup

Set these environment variables to use Claude Code with SISTEMATIS AI:

export ANTHROPIC_BASE_URL="https://api.sistematis.ai"
export ANTHROPIC_API_KEY="YOUR_API_KEY"
claude

Models

GET/models

List all available models.

Available Models

sistematis-super-v7

BASICSTANDARDPLUSPROMAXULTRA

Latest flagship model, ideal for complex tasks

sistematis-flex-v7

BASICSTANDARDPLUSPROMAXULTRA

High performance for most use cases

sistematis-fast-v7

BASICSTANDARDPLUSPROMAXULTRA

Fast and efficient for simple tasks

Rate Limits

Rate limits based on your subscription plan. Quota resets every 5 hours and weekly (Monday 00:00 WIB):

Plan	Requests / 5 Hours	Requests / Week
BASIC	60	300
STANDARD	100	500
PLUS	150	750
PRO	360	1,800
MAX	720	3,600
ULTRA	1,440	7,200

⏱️ Reset Schedule

5h Quota: Resets every 5 hours (rolling window)
Weekly Quota: Resets every Monday at 00:00 WIB

Response headers will include rate limit info:

X-RateLimit-Limit-5h→Limit 5h
X-RateLimit-Remaining-5h→Remaining 5h quota
X-RateLimit-Limit-Weekly→Weekly limit
X-RateLimit-Remaining-Weekly→Remaining weekly quota

⚡

Quota Multiplier

Some models consume more quota per request:

• super-v7 (glm-5.1): 3x during peak hours (14:00-18:00 WIB), 2x off-peak
• flex-v7 and fast-v7: 1x quota at all times

Example: 1 super-v7 request during peak = 3 requests deducted from your quota.

Errors

Code	Description
401	Invalid or missing API key
403	No active subscription
429	Rate limit exceeded (5h or weekly quota)
400	Bad request (invalid parameters)
404	Model not found
500	Internal server error

Anthropic API Error Format

When using the Anthropic Messages API endpoint, errors follow the Anthropic format with error types like authentication_error, invalid_request_error, rate_limit_error, forbidden, and api_error.

{
  "type": "error",
  "error": {
    "type": "authentication_error",
    "message": "Invalid API key"
  }
}

Code Examples

Python (OpenAI SDK)

from openai import OpenAI
client = OpenAI( api_key="YOUR_API_KEY", base_url="https://api.sistematis.ai/v1")
# Basic chatresponse = client.chat.completions.create( model="sistematis-fast-v7", messages=[{"role": "system", "content": "You are a helpful assistant."},{"role": "user", "content": "Hello!"}] )
print(response.choices[0].message.content)

⚡

Node.js (OpenAI SDK)

import OpenAI from 'openai';
const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.sistematis.ai/v1'
});
const response = await client.chat.completions.create({
  model: 'sistematis-fast-v7',
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'Hello!' }
  ]
});

⌨️

cURL

curl https://api.sistematis.ai/v1/chat/completions \ -H "Authorization: Bearer YOUR_API_KEY"

Ready to Start?

Get your API key and start building with SISTEMATIS AI.

Get Started View Pricing