IQIUU API

Access proprietary intelligence models built on Recursive Memory Architecture (RMA), Topological Intelligence Geometry (TIG), and World Model Substrate (WMS).

This is not another LLM wrapper. IQIUU models implement true cognitive computing — persistent memory, mode-decomposed reasoning, and latent world simulation. The API follows REST conventions and returns JSON.

Key capabilities

• Recursive Memory — Models maintain and evolve persistent context across conversations via RMA.
• Cognitive Modes — Switch between analytical, creative, strategic, and empathetic reasoning on the fly.
• World Simulation — Query internal world models for prediction and counterfactual analysis.
• Eigenintelligence — Embeddings decomposed along cognitive eigenvectors, not just semantic similarity.

Authentication

All API requests require a Bearer token in the Authorization header. API keys are scoped per project and can be managed from your IQIUU dashboard.

Base URL

https://api.iqiuu.com/v1

Example request

curl https://api.iqiuu.com/v1/chat/completions \
  -H "Authorization: Bearer iq_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "iqiuu-void-1",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Models

IQIUU offers a family of models optimized for different use cases, from frontier reasoning to cost-effective inference.

Chat Completions

Generate model responses given a conversation history. Supports persistent memory, cognitive mode selection, and streaming.

Request body

Response

{
  "id": "iq-chat-8f3a9b2c",
  "object": "chat.completion",
  "model": "iqiuu-void-1",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I assist you?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 8,
    "total_tokens": 20
  },
  "memory_updates": []
}

Code examples

import iqiuu

client = iqiuu.Client(api_key="iq_your_api_key")

response = client.chat.completions.create(
    model="iqiuu-void-1",
    messages=[
        {"role": "system", "content": "You are a strategic advisor."},
        {"role": "user", "content": "Analyze the market landscape for AI infrastructure."}
    ],
    cognitive_mode="strategic",
    memory=True,
    temperature=0.7
)

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

import IQIUU from '@iqiuu/sdk';

const client = new IQIUU({ apiKey: 'iq_your_api_key' });

const response = await client.chat.completions.create({
  model: 'iqiuu-void-1',
  messages: [
    { role: 'system', content: 'You are a strategic advisor.' },
    { role: 'user', content: 'Analyze the market landscape for AI infrastructure.' }
  ],
  cognitive_mode: 'strategic',
  memory: true,
  temperature: 0.7
});

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

curl https://api.iqiuu.com/v1/chat/completions \
  -H "Authorization: Bearer iq_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "iqiuu-void-1",
    "messages": [
      {"role": "system", "content": "You are a strategic advisor."},
      {"role": "user", "content": "Analyze the market landscape for AI infrastructure."}
    ],
    "cognitive_mode": "strategic",
    "memory": true,
    "temperature": 0.7
  }'

Memory

The Memory API provides access to RMA-powered persistent context. Memories are automatically extracted from conversations when memory: true is set, or can be managed explicitly.

List memories

Returns all persistent memories associated with your API key.

{
  "object": "list",
  "data": [
    {
      "id": "mem_a1b2c3d4",
      "content": "User prefers concise, data-driven responses",
      "source": "auto",
      "created_at": 1756684800,
      "relevance_score": 0.94
    }
  ]
}

Create memory

Delete memory

Permanently deletes a memory by ID. This action cannot be undone.

Embeddings

IQIUU embeddings go beyond semantic similarity. Vectors are decomposed along cognitive eigenvectors, capturing reasoning modality, not just meaning.

Planned specification

• 4096 dimensions — high-fidelity representation space
• Mode-decomposed — separate analytical, creative, and strategic subspaces
• Cross-modal — unified embeddings for text, code, and structured data

World Models

Query IQIUU's internal world models for simulation and prediction. Built on World Model Substrate (WMS), these endpoints expose latent causal reasoning over complex systems.

Planned endpoints

Run counterfactual simulations over a described scenario. Returns probabilistic outcome distributions.

Generate predictions for future states of a described system. Leverages latent world model inference for multi-step causal forecasting.

Rate Limits

Rate limits are applied per API key and reset daily at midnight UTC.

Pricing

Token-based pricing. Input and output tokens are billed at the same rate. Usage is tracked in real time on your dashboard.

SDKs

Official client libraries for the IQIUU API. All SDKs provide typed interfaces, automatic retries, and streaming support.