Claude Code and Codex CLI, fact by fact
| Fact | Claude Code | Codex CLI |
|---|---|---|
| StarsClaude Code has 21,483 more stars (1.2×). | 149,849Verified 8 Oct 2026 | 128,366Verified 8 Oct 2026 |
| Newest commitBoth committed on the same day. | 8 Oct 20260 days old when we read itVerified 8 Oct 2026 | 8 Oct 20260 days old when we read itVerified 8 Oct 2026 |
| ContributorsCodex CLI has 420 more contributors (8.4×). | 57Verified 8 Oct 2026 | 477Verified 8 Oct 2026 |
| License | not tracked for Claude Code | Apache-2.0Verified 8 Oct 2026 |
| Latest stable releaseBoth released on the same day. | v2.1.294published 8 Oct 2026Verified 8 Oct 2026 | rust-v0.161.0published 7 Oct 2026Verified 8 Oct 2026 |
| npm downloadsCodex CLI has 10,827,038 more npm downloads a week (1.7×). | 14,786,283 a week@anthropic-ai/claude-codeVerified 8 Oct 2026 | 25,613,321 a week@openai/codexVerified 8 Oct 2026 |
| Homebrew installs | not tracked for Claude Code | 104,545 in 30 dayscodexVerified 8 Oct 2026 |
| Repository | anthropics/claude-codeTypeScriptVerified 8 Oct 2026 | openai/codexRustVerified 8 Oct 2026 |
What we know about Claude Code
Claude Code runs only Anthropic models: every alias — default, best, fable, sonnet, opus, haiku and opusplan — resolves to a Claude model, and changing the base URL moves where the request goes without changing which model answers it.
“ANTHROPIC_BASE_URL changes where requests are sent, not which model answers them.”
Plan a change with Opus and execute it with Sonnet inside one session, by setting the model to `opusplan`.
“Special mode that uses opus during plan mode, then switches to sonnet for execution”
Run the agent on infrastructure your employer already approved: the model setting accepts an Amazon Bedrock inference profile ARN, a Microsoft Foundry deployment name, or a Google Cloud Agent Platform version name.
“Amazon Bedrock: an inference profile ARN”
Work one long task without losing history: `sonnet[1m]` gives a 1 million token context window, and auto-compaction runs below it.
“Uses Sonnet with a 1 million token context window for long sessions”
You cannot audit, fork or patch the agent: the repository publishes the changelog, plugins and examples, not the CLI source, under an all-rights-reserved licence. GitHub Copilot CLI is the only other tool in this set that does the same.
“© Anthropic PBC. All rights reserved. Use is subject to Anthropic's [Commercial Terms of Service](https://www.anthropic.com/legal/commercial-terms).”
Subscribers report the plan limit arriving far earlier than the plan implies: the repository's most-commented open issue carries 1,487 comments and 724 reactions and has stayed open since 2026-01-03.
“[BUG] Instantly hitting usage limits with Max subscription”
On API-key billing the cost is per token, and Anthropic's own enterprise figure is $150-250 per developer per month.
“Across enterprise deployments, the average cost is around $13 per developer per active day and $150-250 per developer per month, with costs remaining below $30 per active day for 90% of users.”
A developer who must run a local or self-hosted model should choose goose or Crush; both accept an Ollama endpoint.
“Local model runner supporting Qwen, Llama, DeepSeek, and other open-source models.”
What Claude Code costs
Claude Pro costs $17 per month on the annual plan, $200 billed up front, or $20 per month billed monthly; Max starts at $100 per month.
“Per month with annual subscription discount ($200 billed up front). $20 if billed monthly.”
Pro and Max subscribers do not pay per token for Claude Code; the usage sits inside the subscription.
“Claude Max and Pro subscribers have usage included in their subscription, so the session cost figure isn’t relevant for billing purposes.”
What we know about Codex CLI
Codex CLI is the only agent in this set that confines itself in an OS-enforced sandbox on first run, with network access off and writes limited to the working directory.
“By default, the agent runs with network access turned off. Locally, Codex uses an OS-enforced sandbox that limits what it can touch (typically to the current workspace), plus an approval policy that controls when it must stop and ask you before acting.”
Point an agent at a repository you do not trust: in the default `workspace-write` mode Codex edits inside the working directory and must ask before touching anything outside it.
“Codex asks for approval to edit files outside the workspace or to run commands that require network access.”
Use a ChatGPT plan you already pay for instead of a second subscription, on Free, Go, Plus, Pro, Business, Edu or Enterprise.
“ChatGPT Work and Codex are included in your ChatGPT Free, Go, Plus, Pro, Business, Edu, or Enterprise plan”
Stop a team from disabling its own guard rails: an administrator can forbid `approval_policy = "never"` and `sandbox_mode = "danger-full-access"` in a requirements file.
“requirements.toml (for example, disallowing approval_policy = "never" or”
Subscription spend is unpredictable: the most-commented open issue, 630 comments since 2026-03-13, is that Codex burns the plan budget too fast, and a second reports the 5-hour budget gone in 2-3 prompts.
“Codex (gpt-5.5, Plus plan) — rate-limit cost per token jumped ~10-20x since June 16, draining the 5h budget in 2-3 prompts”
The agent cannot install a dependency until you edit the config, because the default sandbox keeps the network off.
“For the ChatGPT desktop app, Codex CLI, or IDE extension, the default workspace-write sandbox mode keeps network access turned off unless you enable it in your configuration:”
Windows is the weakest platform: an open issue with 106 comments reports the app freezing on Windows 11 Pro on hardware with resources to spare.
“Codex App frequently freezes/stutters on Windows 11 Pro despite sufficient system resources”
A developer who wants to run a local Ollama model should choose Crush or goose; Codex signs in with a ChatGPT account or an OpenAI API key.
“Run `codex` and select **Sign in with ChatGPT**. We recommend signing into your ChatGPT account to use Codex as part of your Plus, Pro, Business, Edu, or Enterprise plan.”
What Codex CLI costs
ChatGPT plans that include Codex run $0 for Free, $8 a month for Go, $20 a month for Plus, and from $100 a month for Pro.
“Plus · Power a few focused coding sessions each week. · $20 /month”
The Business plan is $20 per user per month for 2 or more users billed annually, and $25 per user per month billed monthly.
“*2+ users, billed annually. $25 per user per month when billed monthly.”
Questions people ask
- Are Claude Code and Codex CLI still maintained?
- Claude Code committed to anthropics/claude-code (main) on 8 Oct 2026. Codex CLI committed to openai/codex (main) on 8 Oct 2026. Both readings come from the default branch of each repository, on the date shown beside them.
- What do Claude Code and Codex CLI cost?
- Claude Code: Claude Pro costs $17 per month on the annual plan, $200 billed up front, or $20 per month billed monthly; Max starts at $100 per month. Pro and Max subscribers do not pay per token for Claude Code; the usage sits inside the subscription. Codex CLI: ChatGPT plans that include Codex run $0 for Free, $8 a month for Go, $20 a month for Plus, and from $100 a month for Pro. The Business plan is $20 per user per month for 2 or more users billed annually, and $25 per user per month billed monthly. Every figure here is quoted from the vendor's own page and linked beside the claim.
- Is Claude Code or Codex CLI open source?
- We have not read a licence for Claude Code. Codex CLI's repository openai/codex reports the Apache-2.0 licence. We read the licence GitHub reports for the repository, which is not the same question as whether the hosted product is free.
How we check this page
- Machine facts. Stars, contributors, the newest commit on the default branch, the licence GitHub reports and the latest stable release come from the GitHub API, and download counts from npm, PyPI, Homebrew and the VS Code Marketplace. Each value carries the day it was last confirmed, never the day this page was built. The line under each label is arithmetic on those two values.
- Judgments. Every claim about what a tool suits, what it is bad at and what it costs is quoted from a page we read, and that page is linked beside the claim. Where there is no link, we wrote no claim.
- Index status. Both Claude Code and Codex CLI carry claims we read, quoted and linked. So this page is offered to search engines.
Related comparisons
Pairs we can answer for come first.
