ChatGPT (Work und Codex)
AI assistant from OpenAI with subagent workflows
ChatGPT is OpenAI's AI assistant; ChatGPT Work is an agent that completes tasks across apps and files, and Codex is the coding agent. ChatGPT Work and Codex can run subagent workflows by spawning specialized agents in parallel, for example on a direct request in chat or as instructed by AGENTS.md or skills. Custom agents are defined as TOML files with a name, description and instructions; built-in types are default, worker and explorer. ChatGPT agent mode itself, by contrast, is described by OpenAI as a single unified agentic system. Plans are Free, Go, Plus, Pro, Business, and Enterprise and Edu.
Good fit if
Focus: Users and teams who want to split research, office or coding tasks in ChatGPT across parallel agents
- your project is about Software development with parallel agents, Codebase exploration and reviews or Tasks across apps and files
- people without programming skills should work with it (4/5 for use without developers)
- your team is just getting started (skill level: Beginner to Intermediate)
- you want to get started quickly (learning curve: flat)
Key figures
- Usable without developers
- 4/5
- Scalability
- 5/5
- Integrations
- 5/5
- Versioning
- 2/5
- Observability
- 3/5
Editorial rating on a scale from 1 to 5. Methodology
Fact sheet
- Category
- AI assistants
- Type
- AI assistant from OpenAI with subagent workflows
- Licence
- Proprietär
- Pricing
- Freemium / EnterpriseFree $0 and Go $8/month (Codex and Work limited to the desktop app). Plus $20/month. Pro from $100/month (tiers of $100, $200 and $500). Business $20 per user per month billed annually for 2+ users, $25 billed monthly. Enterprise and Edu on request. ChatGPT Work and Codex share usage limits and credits.
- Deployment
- Cloud, Desktop, Mobile
- Models
- OpenAI
- Compliance
- SOC 2, ISO 27001, GDPR
- RAG
- Yes
- Multi-Agent
- Yes
- SSO, roles (RBAC)
- SSO yes, RBAC yes
Key features
- Subagent workflows in ChatGPT Work and Codex
- Custom agents as TOML files
- ChatGPT Work for tasks across apps and files
- Codex in the desktop app, CLI and IDE
- Plugins for Slack, Google Drive, SharePoint and more
Typical use cases
- Software development with parallel agents
- Codebase exploration and reviews
- Tasks across apps and files
- Research and analysis
Market notes
Changes to ChatGPT (Work und Codex) by email
We let you know when the status, pricing or license of ChatGPT (Work und Codex) changes, together with the weekly market notes.
Implementation
Get ChatGPT (Work und Codex) implemented
Free for you. Partners only pay for requests they accept.
Alternatives
Similar systems
Similar in category, features or use cases.
- DeveloperOpenAI Agents SDKThe OpenAI Agents SDK is a lightweight framework for agents and multi-agent workflows in Python and TypeScript. It relies on a few primitives: agents with tools, handoffs to delegate to other agents, guardrails to validate inputs and outputs, and sessions as memory. Tracing is built in, MCP servers can be connected directly, and besides the OpenAI Responses API other model providers are supported. OpenAI describes the SDK as the production-ready evolution of Swarm. In addition, the Responses API offers its own multi-agent feature (beta), where a model starts subagents in parallel and combines their results.View profile
- AI assistantsClaudeClaude is Anthropic's AI assistant for web, desktop and mobile, complemented by the coding tool Claude Code. The Research feature follows an orchestrator-worker pattern: a lead agent plans the research and spawns subagents that explore different aspects in parallel. In Claude Code the main session delegates tasks to subagents with their own context window, tools and permissions; the experimental agent teams coordinate several Claude Code instances through a shared task list and direct messaging. Claude targets individuals, teams and enterprises; there is a free plan plus Pro, Max, Team and Enterprise.View profile
- AI assistantsGrok BotGrok Bot is a beta product from SpaceXAI (xAI), available since August 11, 2026, in which each bot uses its own cloud computer, signs into the user's tools and completes multi-step jobs. Several bots run in parallel with their own jobs; they can independently message each other, share context in threads and pass work between themselves in group chats. Bots remember conversations and can save demonstrated workflows as routines that run on a schedule. Access is available to SuperGrok, SuperGrok Plus and SuperGrok Heavy subscribers, Cursor Pro, Pro+ and Ultra, and Cursor Teams; Enterprise via waitlist. For developers, the xAI API additionally offers the beta feature Multi-agent Research, in which a leader agent coordinates 4 or 16 agents.View profile
- AI assistantsPerplexity ComputerPerplexity Computer is an agent from Perplexity, introduced in February 2026, that completes multi-step tasks in an isolated compute environment with a file system, browser and tool integrations. It breaks a task into subtasks and creates sub-agents that work asynchronously; models from different providers are used depending on the subtask, and users can also pick models for subagents themselves. Personal Computer extends this on the Mac with local files and local computer use, and there is also a Slack integration. Computer is available in Pro, Max, Enterprise Pro and Enterprise Max and is billed through credits.View profile