One Space.The smartest Agents, better-value plans.

  • Cloud collaboration
  • 100% full-power Agents
  • No setup required
GPT-6 Astra is now availableGPT-6 Astra is included in every Share planOfficial pricing · 55% offTry it now

Use trusted Agent harnesses in one cloud Workspace, or bring your Share and Flex to other Agent products through the Developer API.

Start usingLearn about Agents

Available Agent harnesses and models

CodexGPT-5.6Claude CodeClaudeGrokGrok 4.5OpenCodeGPT-5.5

What is Agent.Space?

Model plans + a cloud Agent Workspace

Agent.Space has two parts: dependable model capacity and a persistent place where that capacity becomes finished work.

01UP TO 50% OFF

Model plans

A simpler way to subscribe to models

Use Agent.Space Share for fixed GPT capacity and Agent.Space Flex for metered access to Kimi, GLM, MiniMax, DeepSeek, Claude, and Grok. Plans, allowance, billing, and Developer API access stay in one place.

See pricing
02ALWAYS ONMULTI-DEVICE

Cloud Agent Workspace

An always-on Workspace for Agents

Codex, Claude Code, and other Agents keep running in the cloud. Sessions, files, previews, and team context remain together so work can continue at any time.

Explore the Workspace

01 / Model subscriptions

Model subscription plans

Choose fixed GPT capacity with Agent.Space Share, or pay only for measured model usage with Agent.Space Flex. Both live alongside the same billing and cloud Workspace.

New model

GPT-6 Astra is now available

GPT-6 Astra is included in every Share plan

Try it now
Referral reward

Free ChatGPT Plus for 3 Weeks

Invite friends and both get ChatGPT Plus. Each reward activates for 7 days after each person completes any payment.

View referral reward
New model

GPT-6 Astra is now available

GPT-6 Astra is included in every Share plan

Try it now

Choice 1

ShareOfficial GPT subscriptionAllowance synced with the official plan

55% OFF
ChatGPT

Plus

Learning, small fixes, and lighter workflows
$209/mbilled annually
Choose ChatGPT Plus
GPT-6 Astra
Now available
Weekly allowance
1xChatGPT PlusOfficial plan allowance
You saveUp to 98% OFF
$417/mSame allowanceOfficial API
Plan benefits
  • Independent account—no shared login
  • Code, debug and review with Codex
  • 24/7 cloud computer, ready when you are
  • Your own API key and model API access
  • Use your local Codex client
  • Keep project files and conversations
  • Parallel conversations and task queues
  • MCP plugins and custom Skills
  • No 5-hour usage limit
First-purchase Bonus$5
Universal balance
55% OFF
ChatGPT

Plus 2x

Everyday development and regular projects
$4018/mbilled annually
Choose ChatGPT Plus 2x
GPT-6 Astra
Now available
Weekly allowance
2xChatGPT PlusOfficial plan allowance
You saveUp to 98% OFF
$835/mSame allowanceOfficial API
Plan benefits
  • Independent account—no shared login
  • Code, debug and review with Codex
  • 24/7 cloud computer, ready when you are
  • Your own API key and model API access
  • Use your local Codex client
  • Keep project files and conversations
  • Parallel conversations and task queues
  • MCP plugins and custom Skills
  • No 5-hour usage limit
First-purchase Bonus$10
Universal balance
Most popular55% OFF
ChatGPT

Pro 5x

Active projects and heavier engineering work
$10045/mbilled annually
Choose ChatGPT Pro 5x
GPT-6 Astra
Now available
Weekly allowance
5xChatGPT PlusOfficial plan allowance
You saveUp to 98% OFF
$2087/mSame allowanceOfficial API
Plan benefits
  • Independent account—no shared login
  • Code, debug and review with Codex
  • 24/7 cloud computer, ready when you are
  • Your own API key and model API access
  • Use your local Codex client
  • Keep project files and conversations
  • Parallel conversations and task queues
  • MCP plugins and custom Skills
  • No 5-hour usage limit
First-purchase Bonus$10
Universal balance
Limited seats10% OFF
ChatGPT

Pro 20x

Power users, long tasks, and intensive work
$200180/mbilled annually

Selling out soonOpenAI has closed new Pro 20x subscriptions. Agent.Space still has a few seats, and purchases made now stay active.

Choose ChatGPT Pro 20x
GPT-6 Astra
Now available
Weekly allowance
20xChatGPT PlusOfficial plan allowance
You saveUp to 98% OFF
$8348/mSame allowanceOfficial API
Plan benefits
  • Independent account—no shared login
  • Code, debug and review with Codex
  • 24/7 cloud computer, ready when you are
  • Your own API key and model API access
  • Use your local Codex client
  • Keep project files and conversations
  • Parallel conversations and task queues
  • MCP plugins and custom Skills
  • No 5-hour usage limit
First-purchase Bonus$10
Universal balance

Coming soon

More official subscriptions, shared

SuperGrok and Claude Code group plans are in preparation. Preview the benefits and projected prices now.

Coming soon67% OFF
xAI · Grok

SuperGrok

Grok 4 with far higher limits, Imagine and early access
$3010/mprojected, final on launch
Opening soon
Grok 4
Now available
Plan benefits
  • Grok 4 flagship with much higher usage limits
  • Grok Imagine image and video generation
  • Real-time X and web search
  • Early access to new models and features
  • Independent account, no shared login
  • Your own API key and model API access
Coming soon50% OFF
Anthropic · Claude Pro

Claude Code

The terminal coding agent, with Pro usage shared through the group
$2010/mprojected, final on launch
Opening soon
Claude Opus 5
Claude Code ready
Plan benefits
  • Claude Code takes over your repo end to end
  • Claude Pro usage with Opus models
  • Use your local Claude Code client
  • MCP plugins and custom Skills
  • Keep project files and conversations
  • Independent account, no shared login

Annual plans are charged upfront while allowance resets in full every 7 days. First-purchase Bonus is promotional Flex valid for 30 days. Purchased Flex does not expire.

  • Resources matched automatically

    Clear capacity levels based on official Codex allowances.

  • Allowance stays isolated

    The platform keeps allowance and access boundaries separate.

  • 7-day cycles, clear rules

    Allowance resets in full every 7 days. Unused allowance does not roll over.

  • Independent account and Workspace

    Plans, Agents, files, and collaboration stay in one place.

Choice 2

FlexUniversal balance, pay as you go

Use Kimi, GLM, MiniMax, DeepSeek, Claude, and Grok in Agent.Space or through the Developer API with one independent balance. Purchased Flex does not expire and is charged only for measured model usage.

Top up Flex
  • Kimi
  • GLM
  • MiniMax
  • DeepSeek
  • Claude
  • Grok

Flex model pricing

USD / 1M tokens
Loading model prices…
Top up Flex

02 / Developer API

Use your Agent.Space allowance in any Agent product

Your Agent.Space allowance includes Share for OpenAI models and Flex for other available models. Use it in Agent.Space, Codex, Claude Code, OpenCode, Hermes, and other Agent products you already work with.

View my API Key

Your Agent.Space allowance includes

Share + Flex

Share

OpenAI models

Included with your Share plan.

Flex

Other available models

A flexible balance you can top up as needed.

Use it in the Agent products you already know

Built inAgent.Space
Codex
Claude Code
OpenCode
Hermes
Your Agent product

Use it directly in Agent.Space. For other products, connect your Developer API once and keep working there.

GPT Image 2 uses Share first, then Flex when no plan is available or its allowance is exhausted. Other models use their listed funding source.

View plansConfigure Developer API

03 / Agent clients

Use Agent.Space models in the client you already love

Download Codex, Claude Code, or OpenCode and point it at the Agent.Space Developer API. One API key brings your Share and Flex allowance, and every available model, into the terminal and editor you already work in.

  • Codex

    OpenAI · Coding agent for terminal and IDE

    OpenAI's official coding agent with a CLI, IDE extensions, and a desktop app. It connects over the OpenAI Responses protocol and runs the OpenAI models in your Share allowance.

    • macOS
    • Linux
    • Windows
    Install · macOS / Linux
    curl -fsSL https://chatgpt.com/codex/install.sh | sh
    Download from official site

  • Claude Code

    Anthropic · Terminal coding agent

    Anthropic's official coding agent, speaking native Anthropic Messages. Point its base URL at Agent.Space to run Claude models from your Flex balance.

    • macOS
    • Linux
    • Windows
    Install · macOS / Linux
    curl -fsSL https://claude.ai/install.sh | bash
    Download from official site

  • OpenCode

    Open source · Terminal coding agent

    An open-source terminal agent with custom providers, compatible with both OpenAI and Anthropic protocols. One config unlocks every model available on Agent.Space.

    • macOS
    • Linux
    • Windows
    Install · macOS / Linux
    curl -fsSL https://opencode.ai/install | bash
    Download from official site

Why connect through Agent.Space

  • One key

    One API key, many model providers

    OpenAI, Anthropic, DeepSeek, and more share a single key and endpoint. Switch models without switching accounts.

  • Two protocols

    OpenAI Responses and Anthropic Messages

    Connect over each client's native protocol. No proxies and no client patches: configure once and keep working.

  • Clear billing

    Share and Flex stay separate

    The model you call decides which allowance pays, and every request is visible in Request history.

  • Your choice

    Swap clients any time

    Codex today, Claude Code tomorrow. Your key and allowance stay the same, so your workflow never breaks.

The template already includes the endpoint and selected model. Replace <your-api-key>, then keep the config file local and never commit or share it.

04 / Cloud Workspace

One cloud Workspace for every leading Agent

Codex, Claude Code, and other leading Agents share one cloud Workspace. Files, context, and progress persist so individuals can start immediately and teams can take over at any time.

New chat

Which Agent should we start with?

Multiple Agents and teammates share one Workspace to move real work forward together.

Import local conversations
Codex — describe what you want to build, fix, or review…

Each Session keeps its Agent, files, and context in the same Workspace, so people and Agents can hand work off without starting over.

People and Agents, moving work forward together

01

Multiple Agents move the work forward

Codex, Claude Code, OpenCode, and other Agents can take on separate tasks while sharing the same files and project context.

02

Everyone sees the same working context

Invited teammates can see the same Sessions, files, and progress without repeatedly explaining what has already happened.

03

Change people or Agents without restarting

Context, code, results, and Previews stay in the Workspace, ready for the next teammate or Agent to continue.

04

Work, access, and progress stay clear

Roles, permissions, task status, and usage are visible in one place, so everyone knows who owns the next step.

05 / Security and trust

Your work stays
in your Workspace

Your Workspace is separate from everyone else's. Only people you invite can see its files and tasks.

We use this content only while Agents do the work you ask for—not for advertising.

01

Independent runtime

Every Workspace runs independently

Projects, files, and Sessions run in an isolated Workspace environment, separate from other work.

02

No shared accounts

No account or password exchange

The platform manages service access and resource matching; users never share upstream accounts or login credentials.

03

Team permissions

Only invited members can join

Invite people into the Workspace and control their access with clear roles and permissions.

04

Export anytime

Take your files and results with you

Code, files, and results stay in ordinary directories and standard formats, ready to export when needed.

You control who can access the Workspace, how work runs, and when the project leaves.

06 / FAQ

Straight answers before you start

The essentials about Agent.Space Share, allowance, Flex, and collaboration.

Agent.Space Blog

Notes for building with AI Agents

Practical guides, product updates, and field notes for putting cloud Agents to work.

Blog

Why Codex Quota Runs Out Faster: Rates, Cache, and Rework

Diagnose faster Astra quota consumption by separating allowance, model rates, cache reads and writes, repeated calls, and the cost of getting one accepted result.

Read article

Beyond the Pelican Test: How to Check Coding Agent Regressions

Build a small, repeatable evaluation from real coding work. Control the starting state, grade accepted results, and distinguish a bad run from a useful regression signal.

Read article

Get More from GPT-6 Astra: Simplify AGENTS.md and Skills

Turn OpenAI's Astra guidance into a practical instruction audit. Copy a prompt that finds excessive reading, repeated checks, conflicts, and unnecessary pauses.

Read article

Start in one Space

Bring your next task to Agent.Space

Choose an Agent, keep the project in the cloud, and collaborate without losing context.

Get started