Skip to main content
Platform Features

The Complete AI Platform

Everything you need to harness AI effectively—without the complexity, without the vendor lock-in, and without compromising your data.

Model Access

The Right Models for Every Need

From essential AI models to 100+ options via our AOSentry gateway, choose the plan that fits your needs.

Solo Models

All Plans

Latest models from top providers, included on Solo, Pro, and Teams plans.

OpenAI

GPT-5.1 GPT-5 GPT-5 Nano

Anthropic

Claude Sonnet 4.5 Claude Haiku 4.5 Claude Sonnet 4 Claude Sonnet 3.7 Claude Sonnet 3.5 v2 Claude Haiku 3.5

Google

Gemini Flash Latest Gemini Flash-Lite Latest Gemini Live 2.5 Flash Gemini 2.5 Flash Lite Gemini 2.5 Flash

xAI

Grok 4.1 Fast Grok 4.1 Fast (Non-Reasoning)

Pro Models

Pro+

Premium models including Claude Opus, Codex, and Mistral family. Available on Pro and Teams plans.

OpenAI

GPT-5.1 Codex GPT-5.1 Codex mini GPT-5-Codex

Anthropic

Claude Opus 4.5 Claude Opus 4.1 Claude Opus 4

Google

Gemini 3 Pro Preview Gemini 2.5 Flash Image Gemini 2.5 Pro

Mistral

Mistral Medium 3.1 Devstral Medium Devstral Small Mistral Medium Mistral Medium 3 Magistral Medium Magistral Small Codestral Mistral Large Pixtral Large Ministral 8B Ministral 3B Mistral Small Pixtral 12B Mistral Nemo Mixtral 8x22B Mixtral 8x7B Mistral 7B

xAI

Grok 4 Fast Grok 4

Teams Models via AOSentry Gateway

Teams+

Full model catalog including reasoning models (o-series), Cohere, legacy models, and embeddings. Available exclusively via AOSentry gateway.

OpenAI

GPT-5.1 Chat GPT-5 Chat GPT-5 Mini o3-pro o3 o4-mini o3-mini o1-pro o1 o1-preview o1-mini Codex Mini GPT-4.1 GPT-4.1 mini GPT-4.1 nano GPT-4o GPT-4o mini GPT-4 GPT-4 Turbo GPT-3.5-turbo o3-deep-research o4-mini-deep-research

Google

Gemini 2.0 Flash Gemini 2.0 Flash Lite Gemini 1.5 Flash-8B Gemini 1.5 Flash Gemini 1.5 Pro Gemini Embedding 001

Cohere

Command A Translate Command A Reasoning Command A Vision Command A Command R+ Command R Command R7B

xAI

Grok Code Fast 1 Grok 3 Fast Grok 3 Grok 3 Mini Fast Grok 3 Mini Grok 2 Grok 2 Vision Grok Beta Grok Vision Beta

Embeddings

text-embedding-3-large text-embedding-3-small text-embedding-ada-002

AOSentry Gateway provides intelligent routing, cost optimization, fallback handling, and unified access to 90+ models for Teams and Enterprise plans.

Enterprise

Open-Weight Models on US Infrastructure

For Enterprise customers, we run open-weight models on US-based infrastructure. Your data never leaves American soil and is never sent to foreign servers. The model weights are publicly auditable—you can verify exactly what code is running.

Unlike closed APIs where you trust a black box, open weights mean complete transparency. It's like using Linux—developed globally, but running on your hardware under your control.

Self-hosted inference on your GPUs
Custom fine-tuning for your use cases
Air-gapped deployment option
Cryptographically verified weights

Available Open-Weight Models

DeepSeek R1

State-of-the-art reasoning

MIT
Qwen 3 (up to 235B)

Multilingual powerhouse

Apache 2.0
Llama 4

Meta's latest open model

Llama License
Mistral Large

European frontier model

Apache 2.0
Kimi K2

Advanced reasoning

MIT
Phi-4

Microsoft's efficient model

MIT

All models run on US infrastructure under your control

Core Capabilities

Built for Real Work

Beyond chat—a complete platform for AI-powered productivity.

All Plans

Multi-Model Access

Standard models included with Solo, premium models with Pro. Teams and Enterprise get 100+ models via AOSentry gateway with intelligent routing.

Pro+

File Search (RAG)

Upload documents and search across them with citations. AOCodex retrieves relevant context automatically, grounding AI responses in your actual business information.

Pro+

Web Search Integration

Real-time web search built directly into the conversation. Get current information, verify facts, and research topics without leaving the platform.

All Plans

Multimodal Capabilities

Analyze images, extract text with OCR, process documents, and work with visual content. Upload screenshots, photos, PDFs, and more for AI-powered analysis.

All Plans

Artifacts & Generative UI

Go beyond text. Generate interactive charts, diagrams, code previews, and visual outputs directly in the conversation. Export to multiple formats.

Pro+

Simple Memory

Customizable memory that persists key information across conversations. Define what the AI should remember about your preferences and context.

Teams & Enterprise

14 Permission Categories

Granular role-based access control lets you define exactly what each user can do. Available on Teams and Enterprise plans.

Prompts

Use, create, share globally

Agents

Use, create, share globally

Memories

Use, create, update, read, opt-out

Projects

Use, create, update, share

Teams

Use, create, update, share

Web Search

Enable/disable per role

Code Interpreter

Enable/disable per role

Multi-Conversation

Enable/disable per role

File Search

Document search within uploads

File Citations

Source attribution for responses

People Picker

View users, groups, roles

Marketplace

Access shared agent library

Bookmarks

Save important conversations

Temporary Chat

Ephemeral sessions

Enterprise admins can create custom roles combining any permissions, assign to users or groups, and enforce organization-wide policies.

Authentication

SSO & Identity Integration

Connect AOCodex to your existing identity infrastructure. Support for enterprise authentication standards out of the box.

SAML 2.0
OIDC
LDAP
Active Directory
Google
GitHub
Microsoft
+ More

Enterprise Features

  • Automatic user provisioning (SCIM)
  • Group sync with Entra ID
  • Two-factor authentication (2FA)
  • Session management
  • Complete audit logging
  • IP allowlisting
Coming Soon

Engram Advanced Memory

Go beyond simple memory with Engram—a cognitive memory system that learns, connects ideas, and understands context over time. While simple memory lets you store key facts, Engram builds a knowledge graph that makes AOCodex genuinely smarter about you and your work.

Dual Memory Architecture

Short-term working memory for immediate context, long-term memory for persistent knowledge—just like human cognition.

Semantic Concept Graph

Ideas don't exist in isolation. Engram builds a knowledge graph linking related concepts, projects, and contexts.

Natural Forgetting

Irrelevant information fades naturally over time, keeping memory focused and useful—not cluttered.

AI That Actually Remembers

Context that persists across conversations. Knowledge that compounds over time.

Project A
Clients
Research
Docs
On the Roadmap

Coming Soon

We're constantly building. Here's what's next.

Coming Soon

Code Interpreter

Execute Python code directly in conversations. Data analysis, visualization, file processing, and more—without leaving AOCodex.

Coming Soon

Custom Workflows

Build automated AI workflows with triggers, conditions, and actions. Connect to external tools and create powerful automations.

Experience the Platform

Start free and explore everything AOCodex has to offer.