GitHub Copilot vs Claude Code vs Codex: cloud sessions compared
GitHub Copilot, Claude Code and OpenAI Codex can all run coding tasks in a cloud environment instead of on your own machine. They differ most in how they bill, how big a machine you get and which code hosts they support. Every fact below links to the vendor's own docs, changelog or pricing page. Where a vendor hasn't published something, we say "not published".
Last verified: · plans, prices, billing rates and limits re-read on docs.github.com, github.blog, code.claude.com, claude.com and learn.chatgpt.com that day. The vendors can change any of them. GitHub says billing for Copilot sandbox usage begins in November 2026.
Cloud sessions compared
| What you want to know | GitHub CopilotCopilot in the cloud: cloud sandboxes | Claude CodeClaude Code on the web: cloud sessions | OpenAI CodexCodex Cloud tasks |
|---|---|---|---|
| Which plans include it | Copilot Student, Pro, Pro+, Max, Business, Enterprise and Copilot access are marked Included. Copilot Free is marked Not included, and Free users can keep using Copilot Chat on GitHub.com and GitHub Mobile. [Plans, Copilot on GitHub] Generally available on paid Copilot plans and rolling out to users from 28 Oct 2026, subject to your organization's “Copilot in the cloud” policy. [Changelog] | Pro, Max and Team, plus Enterprise users with premium seats or Chat + Claude Code seats. [Quickstart, Cloud docs] Claude Code is marked No on the Free plan. Organizations with Zero Data Retention, the HIPAA configuration or customer-managed encryption keys can't start cloud sessions. [Pricing, Cloud docs] | The pricing page marks Codex cloud as available on ChatGPT Plus, Pro, Business and Enterprise / Education. The API-key column has no cloud features. [Pricing] Free and Go are not in that cloud row. Their cards mention the desktop app only. [Pricing] |
| Price and how usage is billed | Plan prices: Pro $10 a month, Pro+ $39, Max $100, Business $19 per granted seat, Enterprise $39 per granted seat. Student is free for verified students. Copilot access is $0 with GitHub Enterprise Cloud or $10 per user a month as Copilot Standalone. [Plans] Model use is billed in GitHub AI Credits ($0.01 each). The sandbox is billed separately in compute seconds, GiB-seconds of memory and GiB-months of snapshot storage (rates in the table below the comparison). [AI credits, Copilot on GitHub, Sandbox billing] Sandbox usage first draws from your GitHub plan's included compute (for example $18 a month on GitHub Pro, $300 on Enterprise Cloud). After that it is billed to your payment method, or blocked if you have none. GitHub says billing for sandbox usage begins in November 2026. [Included usage, Sandbox billing, Changelog] | Pro is $17 a month billed annually ($200 up front) or $20 monthly. Max is from $100 a month. Team Standard seat is $20 a month on annual billing or $25 monthly, and Premium seat is $100 annual or $125 monthly. Enterprise is $20 per seat a month billed annually plus usage at API rates, with a 20-seat minimum. [Pricing] Each session counts toward your plan's usage limits, and “there's no separate charge for the cloud VM.” Running tasks in parallel uses limits proportionately faster. [Quickstart, Cloud docs] Limits reset on a rolling five-hour window, with weekly limits on paid plans. After a limit, paid plans can turn on usage credits to keep working at standard API rates. [Pricing] | Plus is $20 a month. Pro starts at $100 a month, with $100, $200 and $500 plans. Business is $20 per user a month billed annually (2+ users) or $25 monthly. Enterprise and Edu: contact sales. [Pricing] Local messages and cloud chats share your plan's usage allowance, and weekly limits may also apply. The page says cloud tasks may use more of your allowance than local messages. [Pricing] Plus and Pro users who reach the limit can buy credits. Business, Enterprise and Edu plans with flexible pricing can buy workspace credits. No separate VM or compute charge is listed on the pricing page. [Pricing] |
| Where it runs | By default in a cloud sandbox: “an isolated Linux environment” that GitHub creates for the session and hosts. A snapshot is saved when it shuts down, so you can resume from another surface. [Sandboxes, Changelog] Other choices: a GitHub Actions runner, or a custom environment you register yourself. You pick between Cloud and Actions when the session starts. [Copilot on GitHub, Sandboxes] Sandbox size (vCPUs, memory, disk): not published. [Sandboxes] | A fresh Anthropic-managed VM for each session, running Ubuntu 24.04 on x86_64. Organizations can instead route sessions to a self-hosted environment on their own runners. [Environments, Quickstart] Size ceilings, which Anthropic says are approximate and may change: 4 vCPUs, 16 GB of RAM and 30 GB of disk. [Environments] After a few minutes idle the VM pauses with its files saved, and a paused VM can later be reclaimed. [Environments] | Each cloud task runs in its own VM with its own workspace. Default size by plan: Plus 2 vCPUs, 8 GiB memory, 8 GiB disk. Pro, Business and Enterprise 4 vCPUs, 16 GiB memory, 32 GiB disk. [Environments] Saved VM state is recoverable for up to seven days after you last start a turn or resume the task. Larger VMs are available for Enterprise by contacting OpenAI. [Environments] Operating system and base image on the current Cloud pages: not published. [Environments, Codex Cloud] |
| Environment and setup | Cloud sandboxes clone your repositories in, and you can personalize them through a dotfiles repository. They don't support custom compute, setup steps written for GitHub Actions, or self-hosted runners. [Sandboxes, Copilot on GitHub] The copilot-setup-steps.yml file, larger or self-hosted runners and Windows apply to Actions sessions only. GitHub says that if you rely on them you need the Actions environment. [Actions setup, Changelog] You can register your own computer or VM as an environment with the Copilot CLI's --environment-host option. [Changelog] List of tools preinstalled in a sandbox: not published. [Sandboxes] | An environment is a saved configuration of network access, environment variables and a setup script. The script runs as root on Ubuntu 24.04. You can type it in the dialog or load a file of up to 64 KB. [Environments] Anthropic snapshots the filesystem after setup and reuses it. The cache is rebuilt when you change the script or allowed hosts and after roughly seven days, and it isn't cached if setup takes longer than about five minutes. [Environments] Preinstalled languages include Python, Node.js, Ruby, PHP, Java, Go, Rust and C/C++, plus Docker, PostgreSQL 16 and Redis 7. Replacing the base image entirely isn't supported yet. [Environments] | You make an environment by choosing GitHub repositories. Codex inspects them, installs dependencies, tests the workflow, and you review the setup and select Publish. [Environments, Codex Cloud] The tested setup is saved as an Install script and a Start skill. A new task starts from the published environment's prepared filesystem, while an existing task keeps its own files. [Environments] Environments can be private or shared with your Enterprise workspace. Not yet supported in cloud environments: computer and browser use. [Environments] |
| Parallel tasks | You can run several sessions in parallel in the cloud. Each session works on one branch at a time and opens one pull request per task. [Sandboxes, Copilot on GitHub] Number of simultaneous sessions: not published. [Sandboxes, Copilot on GitHub] | Each task gets its own session and its own branch, and you don't wait for one to finish before starting another. [Quickstart, Cloud docs] No per-user cap is stated. A scheduled-task page mentions an organization-level limit on cloud sessions running at once but gives no number. [Scheduled tasks] Parallel tasks use your plan's limits faster. [Cloud docs] | Tasks start from a published environment and keep their own working state, with a separate workspace for each task. [Codex Cloud, Environments] Number of simultaneous tasks: not published. [Codex Cloud, Environments] |
| Pull request and branch workflow | You need write access to a repository, otherwise the session is read-only. [Copilot on GitHub, Changelog] The cloud agent can push to one branch only: the pull request's branch if you mention it on an existing PR, otherwise a new copilot/ branch. Branch protections and required checks still apply. [Risks] Its draft pull requests must be reviewed and merged by a human. Workflows don't run until someone with write access clicks Approve and run, unless you change that. Commits are signed. [Risks] | When Claude reaches a stopping point it pushes its branch to GitHub. You review the diff and can create the PR from claude.ai/code, and the session stays open for more edits. [Quickstart, Cloud docs] Optional Auto-fix watches a pull request and pushes fixes for CI failures and review comments. It needs the Claude GitHub App. [Quickstart, Cloud docs] The GitHub proxy rejects branch deletions and pushes of anything that isn't a branch, such as a tag. Branch naming for interactive sessions: not published. Scheduled tasks use claude/-prefixed branches. [Environments, Scheduled tasks] | You review the changed files and test results, ask for follow-ups, then commit or open a pull request when ready. [Codex Cloud, Environments] Branch naming, push restrictions and merge rules for cloud tasks: not published on the current Cloud pages. [Codex Cloud, Environments] |
| Internet access and secrets | A firewall is on by default with a recommended allowlist. Organization and repository owners can customize or disable it. It doesn't apply to MCP servers or setup-step processes. [Firewall] Secrets and variables live in a dedicated Agents section at repository or organization level. In a cloud sandbox only secrets are available, not variables, and values are masked in logs. Names starting COPILOT_MCP_ are for MCP servers only. [Secrets] | Each environment has one of four network levels: None, Trusted (the default), Full or Custom. GitHub, enabled MCP connectors and the Anthropic API bypass the allowlist. [Environments, Cloud docs] Environment variables can be read by anyone who can use the environment. Network secrets stay outside the VM and a proxy adds them to requests for the hosts you list. GitHub credentials also stay outside the VM. [Environments, Cloud docs] | Per environment you can allow all public internet, allow package-manager domains, or add specific domains. A Tailscale VPN gives access to private networks. OIDC lets a task get short-lived credentials for cloud resources. The default for a new environment: not stated on the current page. [Environments] Environment variables are passed straight to programs. HTTP secrets are different: the task sees a placeholder and the proxy swaps in the real value for the allowed HTTPS domains. [Environments] |
| Supported repositories | “Copilot only works with repositories hosted on GitHub.” [Copilot on GitHub] A sandbox session can span repositories owned by one organization. An Actions session is limited to a single repository. [Copilot on GitHub] | Cloning in Anthropic-hosted environments and pull request creation require GitHub. GitHub Enterprise Server is supported on Team and Enterprise plans. [Cloud docs] GitLab, Bitbucket and other hosts can be sent as a local bundle, but the session can't push results back to that remote. [Cloud docs] Private repositories need the Claude GitHub App. The web UI can add several repositories to one session, while claude --cloud works with one repository at a time. [Quickstart, Cloud docs] | You choose GitHub repositories when you create an environment. [Environments, Codex Cloud] The Cloud environments page lists GitLab and self-hosted GitHub Enterprise Server as not currently supported in cloud environments, and on the roadmap. [Environments] A separate GitLab page describes a beta, available on all ChatGPT plans, that reviews merge requests. With a project environment it can also run GitLab-triggered coding tasks, including pushing updates to a merge request branch. OpenAI's pages don't explain how this fits with the Cloud environments page. [GitLab beta] |
| Stated limits | Actions sessions: 59 minutes at most. Cloud sandboxes: “no one-hour limit on total running session time.” [Copilot on GitHub, Changelog] Chat data is kept 28 days for Actions sessions and for the life of the account for sandbox sessions. [Copilot on GitHub] Parallel-session cap and sandbox size: not published. [Sandboxes, Copilot on GitHub] | No maximum session length is published. A foreground command waits 2 minutes by default (up to 10), then moves to the background for up to 30 more minutes. [Environments] Cloud sessions share rate limits with all other Claude usage. A bundled local repository must be under 100 MB. If your organization uses IP allowlisting, hosted cloud sessions fail unless Anthropic exempts them. [Cloud docs] | Usage is limited by five-hour and weekly windows. Pro plans currently have no five-hour limit. The plan estimates on the pricing page are for local messages, and cloud tasks may use more. [Pricing] Saved VM state lasts up to seven days. Maximum task length and number of simultaneous tasks: not published. [Environments] |
The key differences in plain English
- Billing is the biggest split. Copilot meters its sandbox by the second for compute and memory and by the month for snapshot storage, on top of AI credits for model use. Claude Code and Codex draw on plan usage, and neither lists a separate VM charge. [Docs: Billing for cloud and local sandboxes · Docs: Usage-based billing for individuals · Claude Code docs: Get started with Claude Code in the cloud · OpenAI Codex docs: Pricing]
- Only two publish a machine size. Codex lists default VM sizes by plan, and Claude Code lists approximate ceilings. GitHub doesn't publish a sandbox size. [OpenAI Codex docs: Cloud environments · Claude Code docs: Configure cloud environments · Docs: About cloud sandboxes for GitHub Copilot]
- All three start from GitHub. Copilot works only with GitHub repositories. Claude Code needs GitHub for cloning and pull requests in its hosted environments. Codex builds environments from GitHub repositories, and its GitLab support is a beta with conflicting wording across OpenAI's pages. [Docs: GitHub Copilot on GitHub.com and GitHub Mobile · Claude Code docs: Use Claude Code in the cloud · OpenAI Codex docs: Cloud environments · OpenAI Codex docs: Codex in GitLab (beta)]
- Pull requests are handled differently. Copilot opens a draft pull request from a copilot/ branch that a human must merge. Claude Code pushes a branch and lets you create the pull request. Codex has you commit or open a pull request, and its branch rules aren't published. [Docs: Risks and mitigations for GitHub Copilot cloud agent · Claude Code docs: Get started with Claude Code in the cloud · OpenAI Codex docs: Codex Cloud]
- Network and secrets controls differ in shape. Copilot has a default-on firewall, Claude Code has four network levels, and Codex has per-environment domain controls plus a VPN and OIDC. [Docs: Customizing or disabling the firewall for GitHub Copilot · Claude Code docs: Configure cloud environments · OpenAI Codex docs: Cloud environments]
What Copilot sandboxes cost
GitHub now publishes its sandbox rates, so you can price a session. Sandbox compute and memory draw from the compute included in your GitHub plan first, then bill to your payment method. In GitHub's worked example, 600 seconds with 4 GiB of memory costs $0.0216. [Docs: Billing for cloud and local sandboxes]
| Meter | Unit | Price | Per hour (our arithmetic) | What it measures |
|---|---|---|---|---|
| Compute | Compute second | $0.000024 | $0.0864 for each hour | Charged while a session is running. Not charged while it is stopped. [Sandbox billing] |
| Memory | GiB second | $0.000003 | $0.0108 for each GiB for an hour | Charged on memory allocated to the session, not memory in use. [Sandbox billing] |
| Storage | GiB month | $0.005 | — | Snapshot of a stopped session, from the stop until it is deleted. [Sandbox billing] |
| GitHub plan | Included compute per month |
|---|---|
| GitHub Free | $12 |
| GitHub Pro | $18 |
| GitHub Free for organizations | $12 |
| GitHub Team | $18 |
| GitHub Enterprise Cloud | $300 |
This is separate from your Copilot plan's AI credits, which pay for model use. See our Copilot Fusion guide for plan prices and credit allowances. [Docs: GitHub Copilot on GitHub.com and GitHub Mobile · Docs: Usage-based billing for individuals]
Which one should you pick?
This section only restates the sourced facts above. It isn't a ranking.
- Everything you work on is on GitHub, and you want one place to start sessions from. Copilot lists github.com, GitHub Mobile, the CLI, the Copilot app, VS Code, and Slack or Teams as start points, and its sandbox sessions can span repositories in one organization. Check the new sandbox meters first: from November they draw down your GitHub plan's included compute and then bill. [GitHub changelog: New connected Copilot cloud experience (28 Oct 2026) · Docs: GitHub Copilot on GitHub.com and GitHub Mobile · Docs: Billing for cloud and local sandboxes]
- You want cloud work to come out of a plan's usage limits, with no separate VM bill. Claude Code says there is no separate charge for the cloud VM, and Codex's pricing page lists none. Both draw on plan usage that you can see running down, so parallel tasks use it faster. Copilot is the only one of the three with published per-second compute, memory and storage rates. [Claude Code docs: Get started with Claude Code in the cloud · Claude Code docs: Use Claude Code in the cloud · OpenAI Codex docs: Pricing · Docs: Billing for cloud and local sandboxes]
- You need to know the VM size before you start. Codex publishes default sizes by plan, from 2 vCPUs and 8 GiB on Plus to 4 vCPUs and 16 GiB on Pro, Business and Enterprise. Claude Code publishes approximate ceilings of 4 vCPUs, 16 GB and 30 GB. GitHub does not publish a sandbox size. [OpenAI Codex docs: Cloud environments · Claude Code docs: Configure cloud environments · Docs: About cloud sandboxes for GitHub Copilot]
- You need tight control over network and secrets. Claude Code has four network levels and keeps network secrets and GitHub credentials outside the VM. Codex adds a Tailscale VPN and OIDC credentials, and swaps placeholders for HTTP secrets at the proxy. Copilot has a default-on firewall and Agents secrets, but its firewall doesn't cover MCP servers or setup steps. [Claude Code docs: Configure cloud environments · OpenAI Codex docs: Cloud environments · Docs: Customizing or disabling the firewall for GitHub Copilot · Docs: Configure secrets and variables for Copilot cloud agent]
- Your code isn't on GitHub. Copilot works only with GitHub repositories. Claude Code can take a local bundle of a GitLab or Bitbucket repository but can't push results back, though it supports GitHub Enterprise Server on Team and Enterprise. Codex is the only one of the three whose docs describe any GitLab coding work (a beta that can push to a merge request branch), yet its Cloud environments page lists GitLab as not yet supported. Check with OpenAI before relying on it. [Docs: GitHub Copilot on GitHub.com and GitHub Mobile · Claude Code docs: Use Claude Code in the cloud · OpenAI Codex docs: Codex in GitLab (beta) · OpenAI Codex docs: Cloud environments]
What the vendors don't publish
We didn't find these on the official pages listed under Sources, so we haven't guessed them.
- Copilot: sandbox size. GitHub doesn't say how many vCPUs, how much memory or how much disk a cloud sandbox gets. The billing page prices a “compute second”, while the sandbox concept page labels the same meter “vCPU second”, so the unit isn't clear either. [Docs: Billing for cloud and local sandboxes · Docs: About cloud sandboxes for GitHub Copilot]
- Copilot: the exact start of sandbox billing. The changelog says billing for sandbox usage begins in November 2026. No day is given on the pages we checked. The rates themselves are published. [GitHub changelog: New connected Copilot cloud experience (28 Oct 2026) · Docs: Billing for cloud and local sandboxes]
- Copilot: how many sessions at once, and what is preinstalled. Docs say you can run several sessions in parallel but give no number. We found no list of tools preinstalled in a sandbox. [Docs: About cloud sandboxes for GitHub Copilot · Docs: GitHub Copilot on GitHub.com and GitHub Mobile]
- Claude Code: a parallel-session number. There is no per-user cap in the cloud docs, and the scheduled-task page mentions an organization-level limit without a number. No maximum session length is published either. Plan usage per session isn't stated, because Anthropic says there is no fixed message count. [Claude Code docs: Use Claude Code in the cloud · Claude Code docs: Automate work with scheduled tasks · Claude: Plans and pricing]
- Codex: operating system, task length and concurrency. The current Cloud pages give VM sizes but don't name the operating system or image, a maximum task length, or a number of simultaneous tasks. They also don't state the default internet setting for a new environment, or branch naming and push rules. [OpenAI Codex docs: Cloud environments · OpenAI Codex docs: Codex Cloud]
- Codex: how much allowance a cloud task uses. The pricing page gives local-message estimates per five hours and says cloud tasks may use more. It gives no per-task figure for cloud tasks. It also doesn't list Codex cloud for the Free and Go plans. [OpenAI Codex docs: Pricing]
Sources
Every fact on this page comes from the official pages below, opened on .
- GitHub changelog: New connected Copilot cloud experience (28 Oct 2026), opened 30 Oct 2026
- Docs: Plans for GitHub Copilot, opened 30 Oct 2026
- Docs: GitHub Copilot on GitHub.com and GitHub Mobile, opened 30 Oct 2026
- Docs: About cloud sandboxes for GitHub Copilot, opened 30 Oct 2026
- Docs: Billing for cloud and local sandboxes, opened 30 Oct 2026
- Docs: Product usage included with each plan, opened 30 Oct 2026
- Docs: Customizing or disabling the firewall for GitHub Copilot, opened 30 Oct 2026
- Docs: Configure secrets and variables for Copilot cloud agent, opened 30 Oct 2026
- Docs: Configure the development environment for agents on GitHub Actions, opened 30 Oct 2026
- Docs: Risks and mitigations for GitHub Copilot cloud agent, opened 30 Oct 2026
- Docs: Usage-based billing for individuals, opened 30 Oct 2026
- Claude Code docs: Use Claude Code in the cloud, opened 30 Oct 2026
- Claude Code docs: Configure cloud environments, opened 30 Oct 2026
- Claude Code docs: Get started with Claude Code in the cloud, opened 30 Oct 2026
- Claude: Plans and pricing, opened 30 Oct 2026
- Claude Code docs: Automate work with scheduled tasks, opened 30 Oct 2026
- OpenAI Codex docs: Codex Cloud, opened 30 Oct 2026
- OpenAI Codex docs: Cloud environments, opened 30 Oct 2026
- OpenAI Codex docs: Pricing, opened 30 Oct 2026
- OpenAI Codex docs: Codex in GitLab (beta), opened 30 Oct 2026
FAQ
Has GitHub started billing for Copilot cloud sandboxes?
GitHub says billing for cloud sandbox usage begins in November 2026, and the exact day isn't published on the pages we checked. The rates are published: $0.000024 per compute second, $0.000003 per GiB-second of memory and $0.005 per GiB-month of snapshot storage. Usage first draws from the compute included in your GitHub plan. [GitHub changelog: New connected Copilot cloud experience (28 Oct 2026) · Docs: Billing for cloud and local sandboxes · Docs: Product usage included with each plan]
Do Claude Code cloud sessions cost extra?
Anthropic says each session counts toward your plan's usage limits and there is no separate charge for the cloud VM. Cloud sessions share rate limits with the rest of your Claude usage, so running tasks in parallel uses them faster. On paid plans you can turn on usage credits to keep working after a limit, billed at standard API rates. [Claude Code docs: Get started with Claude Code in the cloud · Claude Code docs: Use Claude Code in the cloud · Claude: Plans and pricing]
Which plans can use Codex cloud tasks?
OpenAI's pricing page marks Codex cloud as available on ChatGPT Plus, Pro, Business and Enterprise / Education, and not on an API key. Free and Go aren't in that row, and their cards mention the desktop app only. [OpenAI Codex docs: Pricing]
Can any of them work on GitLab or Bitbucket repositories?
Not fully. Copilot only works with repositories hosted on GitHub. Claude Code can start from a local bundle of a GitLab or Bitbucket repository but can't push back to it. Codex has a GitLab beta that can push updates to a merge request branch when you create a project environment, but its Cloud environments page lists GitLab and self-hosted GitHub Enterprise Server as not currently supported. [Docs: GitHub Copilot on GitHub.com and GitHub Mobile · Claude Code docs: Use Claude Code in the cloud · OpenAI Codex docs: Codex in GitLab (beta) · OpenAI Codex docs: Cloud environments]
How many cloud tasks can I run at once?
All three allow several in parallel and none publishes a number for individual users. Claude Code mentions an organization-level limit on simultaneous cloud sessions without a figure. For Claude Code, parallel tasks also use your plan limits faster. [Docs: About cloud sandboxes for GitHub Copilot · Claude Code docs: Get started with Claude Code in the cloud · Claude Code docs: Automate work with scheduled tasks · OpenAI Codex docs: Codex Cloud]
Do cloud sessions have internet access by default?
Copilot runs behind a firewall that is on by default with a recommended allowlist. Claude Code's default network level is Trusted, which allows listed domains only. For Codex, the current environment page lets you allow all public internet, package-manager domains or specific domains, and doesn't state the default for a new environment. [Docs: Customizing or disabling the firewall for GitHub Copilot · Claude Code docs: Configure cloud environments · OpenAI Codex docs: Cloud environments]
Which one publishes the VM size?
Codex publishes default sizes by plan (Plus: 2 vCPUs, 8 GiB memory, 8 GiB disk; Pro, Business and Enterprise: 4 vCPUs, 16 GiB, 32 GiB). Claude Code publishes approximate ceilings of 4 vCPUs, 16 GB of RAM and 30 GB of disk. GitHub doesn't publish a sandbox size. [OpenAI Codex docs: Cloud environments · Claude Code docs: Configure cloud environments · Docs: About cloud sandboxes for GitHub Copilot]
Related
- GitHub Copilot, Claude Code and OpenAI Codex: our reviews, tiers and plans.
- Copilot Fusion vs picking models: plan prices and AI credit allowances.
- Run coding agents on your own cloud bill: per-token billing through AWS, Google Cloud or Azure.
- AI subscriptions: what $20 a month gets you across tools.
- AI usage limits: what each plan includes and what happens at the limit.