Does Greptile have a free tier?

The verified plans list a Starter tier as Free, but the product's listed limits state no free tier is offered and the entry paid price is Pro at $30/seat/month. Both statements appear on the fact sheet.

Where can each tool run?

Codex runs on web, mac, win, linux, CLI, and a VS Code extension. Greptile lists web and CLI as platforms, and its limits state review functionality is available only through the web platform with no IDE plugin.

Which Git providers are supported?

Codex lists GitHub for its cloud code review on pull requests. Greptile lists GitHub and GitLab integrations for ingesting and reviewing code.

Codex vs Greptile: How They Actually Differ

Codex is a coding agent that runs in your terminal, IDE, and cloud with a free tier; Greptile is a paid code reviewer that reads the whole repo before commenting on pull requests. Pick Codex for one agent across surfaces; pick Greptile for whole-repo PR review.

Compiled 2026-08-24 from our catalogue entries for Codex and Greptile.

The short answer

Pick Codex if: You want a coding agent that works across CLI, IDE, desktop, and cloud with a free tier, and you are fine being limited to OpenAI's GPT models.
Pick Greptile if: You want a paid PR review tool that reads your whole repository rather than only the changed lines and posts comments on GitHub or GitLab pull requests.
Cheapest way in: Codex free tier at $0/month. Greptile's verified plans list a Starter tier as Free, though the product's listed limits say no free tier is offered and the starting paid price is Pro at $30/seat/month. Both statements appear on the fact sheet.
What we could not compare: Codex Business and Enterprise pricing is not published. Greptile Enterprise is listed as Custom. Public repos and docs are not listed for either. Detailed parity for hooks and sub-agents is not on file.

Codex is OpenAI's coding agent. It runs the same agent on a CLI, an IDE extension (VS Code), a desktop app, and a cloud environment, so work started in one surface can continue in another. It reads the AGENTS.md instructions file, supports MCP tools, spins up cloud code reviews on GitHub pull requests that comment inline and propose fixes, and runs on OpenAI's GPT models, with GPT-5.5 listed as the recommended frontier model. Pricing is freemium: a free tier and paid plans from $8/month up to $200/month, plus a pay-per-token API option.

Greptile is an AI code reviewer that comments on pull requests by understanding the whole codebase, not just the diff. Its edge is whole-repo context: it reasons about cross-file relationships and project conventions, then posts comments on PRs in connected Git hosts (GitHub and GitLab). It is listed as paid, with a verified Pro plan at $30/seat/month, and reviews run through the web platform only. Where Codex is a general coding agent that also reviews PRs, Greptile is a single-purpose PR review tool rather than an in-editor coding assistant.

Side by side

Every cell is a field on our catalogue entry for that tool, copied as recorded. Rows where the two differ come first; blank fields say so rather than being filled in.

	Codex	Greptile
Pricing model	Freemium	Paid
Starts at	Free — $0 /month	Pro — $30 /seat/month
Runs on	web, mac, win, linux, cli, vscode-ext	web, cli
Category	AI Coding Agents	AI Coding Agents
Public source code	No public repo listed	No public repo listed
Public docs	Not listed	Not listed

Public source code: From the repository link on each catalogue entry, not a licence audit.

What each one costs

Headline plans copied from our own verified pricing pages — Codex read 2026-08-21, Greptile read 2026-08-21. Follow either link below for the full tier breakdown and its source.

	Codex	Greptile
Entry plan	Free — $0 /month	Starter — Free
Plan 2	Go — $8 /month	Pro — $30 /seat/month
Plan 3	Plus — $20 /month	Enterprise — Custom pricing

Where Codex is the better fit

One agent across CLI, IDE, desktop, and cloud — work moves between surfaces.
Free tier at $0/month, paid plans up to $200/month, plus a pay-per-token API option.
Cloud GitHub PR review that catches real bugs and proposes fixes inline.
Reads the AGENTS.md standard and supports MCP tools.
Included with ChatGPT plans from the free tier up through Pro.

Full Codex entry · Codex pricing, verified

Where Greptile is the better fit

Analyzes the entire repository context rather than only the changed lines in a PR.
Posts review comments directly on pull requests in the connected Git host.
Integrates with GitHub and GitLab to ingest and review code.
Uses large language models to reason about cross-file relationships and project conventions during review.

Full Greptile entry · Greptile pricing, verified

Which one should you pick?

Solo founder on a tight budget

Codex

Free tier at $0/month, a coding agent that works across CLI, IDE, desktop, and cloud, and PR review is included as one capability.

Small team that lives in pull requests

Greptile

Whole-repo review context, direct PR comments in GitHub or GitLab, and a single purpose-built reviewer at $30/seat/month.

Team that wants both writing help and review

Codex

It is an agent that writes code across surfaces and also runs cloud GitHub PR reviews with inline fixes, available from a free tier upward.

Frequently asked questions

Does Greptile have a free tier?: The verified plans list a Starter tier as Free, but the product's listed limits state no free tier is offered and the entry paid price is Pro at $30/seat/month. Both statements appear on the fact sheet.
Does Codex support non-OpenAI models like Claude or Gemini?: No. Codex is locked to OpenAI's GPT models, with GPT-5.5 listed as the recommended frontier model.
Where can each tool run?: Codex runs on web, mac, win, linux, CLI, and a VS Code extension. Greptile lists web and CLI as platforms, and its limits state review functionality is available only through the web platform with no IDE plugin.
Which Git providers are supported?: Codex lists GitHub for its cloud code review on pull requests. Greptile lists GitHub and GitLab integrations for ingesting and reviewing code.

What we compared

This page states nothing that is not in the two catalogue entries below. The exact text used to write it is reproduced here so you can check our reading, and both tools link through to their own pages and to the vendor.

/tools/codex — checked 2026-07-02 · official site
/tools/greptile — checked 2026-06-13 · official site

Show the source text

## Codex (/tools/codex)
Tagline: OpenAI's coding agent — works in the terminal, IDE, and cloud, reviews GitHub pull requests, and runs on GPT-5 models.
Category: AI Coding Agents
Pricing model: freemium
Starts at: Free — $0 /month
Platforms: web, mac, win, linux, cli, vscode-ext
Public repo: none listed
Docs: none listed
Verified plans (read 2026-08-21): Free $0 /month | Go $8 /month | Plus $20 /month | Pro 5x $100 /month | Pro 20x $200 /month | Business / Enterprise Not published | API Key Pay only for the tokens Codex uses, based on API pricing
Strengths on file: Runs one agent across CLI, IDE, desktop, and cloud — work moves between surfaces.; Strong GitHub integration: a cloud code review on a pull request that catches real bugs and proposes fixes.; Reads the shared AGENTS.md standard and supports MCP tools.; Included with ChatGPT plans, from the free tier up through Pro.
Limits on file: Locked to OpenAI's GPT models — no Claude or Gemini out of the box.; Fewer built-in customization primitives (hooks, sub-agents) than some rivals.
Codex is OpenAI's agentic coding tool. It runs the same agent across a terminal CLI, an IDE extension, a desktop app, and a cloud environment, so work started in one surface can continue in another. It reads the shared AGENTS.md instructions file, speaks the Model Context Protocol (MCP), and can spin up a cloud code review on a GitHub pull request that comments inline and proposes fixes. Codex runs on OpenAI's GPT models — currently GPT-5.5 as the recommended frontier model — and is included with ChatGPT plans, from the free tier up through Pro.

## Greptile (/tools/greptile)
Tagline: AI-powered code review that comments on PRs by understanding the entire codebase, not just the diff.
Category: AI Coding Agents
Pricing model: paid
Starts at: Pro — $30 /seat/month
Platforms: web, cli
Public repo: none listed
Docs: none listed
Verified plans (read 2026-08-21): Starter Free | Pro $30 /seat/month | Enterprise Custom pricing
Strengths on file: Analyzes the entire repository context rather than only the changed lines in a pull request.; Posts review comments directly on pull requests in the connected Git host.; Integrates with GitHub (and GitLab) repositories to ingest and review code.; Uses large language models to reason about cross-file relationships and project conventions during review.
Limits on file: No free tier is offered; access requires a paid plan.; Review functionality is only available through the web platform, with no IDE plugin or CLI client.; Code must be hosted on a supported Git provider, creating dependency on that integration.
Greptile is an AI code reviewer that comments on pull requests by reading the whole codebase, not just the diff.
Its edge is whole-repo context: it analyzes the entire repository rather than only the changed lines, reasoning about cross-file relationships and project conventions, and posts its comments straight onto PRs in your Git host (GitHub and GitLab).
It's for teams that want reviews aware of the broader codebase, not line-by-line diff checks. Caveats: there's no free tier — it's paid only — review runs only through the web platform with no IDE plugin or CLI, and your code has to live on a supported Git provider.
It's a PR-review tool like CodeRabbit, distinct from the in-editor assistants.

Change log

2026-08-24 — First published, compiled from the catalogue entries for Codex and Greptile.