Does Codex let me use non-OpenAI models like Claude or Gemini?

No. Codex is locked to OpenAI's GPT models out of the box, with no Claude or Gemini support listed.

Which is cheaper to start?

Both have a $0 entry. Codex Free is $0/month flat. Ellipsis Managed SaaS is $0 base plus usage (tokens at cost, $0.142 / vCPU-hour, $0.024 / GB-hour, 20% platform fee).

Codex vs Ellipsis: How They Actually Differ

Codex fits a solo founder who wants one coding agent across terminal, IDE, and cloud, with GitHub PR review on GPT-5. Ellipsis fits a GitHub-only team that wants automatic PR review with committed code fixes. Pick by where you want the agent to live: everywhere (Codex) or inside pull requests only (Ellipsis).

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

The short answer

Pick Codex if: You want one agent that runs across CLI, IDE, desktop, and cloud, with GitHub PR review built in and inclusion in ChatGPT plans from Free through Pro.
Pick Ellipsis if: Your team's workflow lives inside GitHub pull requests and you want an automated reviewer that can also commit fixes and write PR descriptions.
Cheapest way in: Codex Free at $0/month flat. Ellipsis Managed SaaS at $0 base plus usage: tokens at cost, $0.142 / vCPU-hour, $0.024 / GB-hour, plus a 20% platform fee.
What we could not compare: Codex Business and Enterprise pricing is not published, and Ellipsis's support plans ($5,000, $7,500, and $15,000 per month) are not tied to product tiers. We do not have a comparable enterprise number on file for either.

Both Codex and Ellipsis sit in the AI Coding Agents category, but they are shaped for different jobs. Codex is a general coding agent that moves between CLI, IDE, desktop, and cloud and can also review GitHub pull requests. Ellipsis is a GitHub-native reviewer that comments on and fixes pull requests, and has no editor or CLI surface of its own.

Pricing reflects the split. Codex publishes fixed monthly tiers from Free at $0 up through Pro 20x at $200/month, with Business and Enterprise not published. Ellipsis sells Managed SaaS at $0 base plus usage charges, offers a Your AWS Account deployment option, and lists three support plans starting at $5,000/month.

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	Ellipsis
Pricing model	Freemium	Paid
Starts at	Free — $0 /month	Managed SaaS — $0 base + usage (tokens at cost, $0.142 / vCPU-hour, $0.024 / GB-hour, 20% platform fee)
Runs on	web, mac, win, linux, cli, vscode-ext	web
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, Ellipsis read 2026-08-22. Follow either link below for the full tier breakdown and its source.

	Codex	Ellipsis
Entry plan	Free — $0 /month	Managed SaaS — $0 base + usage (tokens at cost, $0.142 / vCPU-hour, $0.024 / GB-hour, 20% platform fee)
Plan 2	Go — $8 /month	Your AWS Account — $0 base + usage + AWS costs (20% platform fee; CPU, memory, and tokens billed by AWS)
Plan 3	Plus — $20 /month	Standard support — $5,000 / month
Plan 4	Pro 5x — $100 /month	Advanced support — $7,500 / month
Plan 5	Pro 20x — $200 /month	Premier support — $15,000 / month

Where Codex is the better fit

Runs one agent across CLI, IDE, desktop, and cloud, so work moves between surfaces
Cloud code review on a GitHub PR that catches bugs and proposes fixes
Reads the shared AGENTS.md standard and supports MCP tools, and is included with ChatGPT plans from Free through Pro

Full Codex entry · Codex pricing, verified

Where Ellipsis is the better fit

Functions as a GitHub App that automatically reviews every pull request
Can generate and commit code fixes directly to a PR in response to review feedback
Reviews cover code style, potential bugs, and architectural concerns, and can produce PR descriptions generated from code diffs

Full Ellipsis entry · Ellipsis pricing, verified

Which one should you pick?

Solo developer switching between terminal, IDE, and cloud

Codex

It runs one agent across CLI, IDE, desktop, and cloud on OpenAI's GPT models and reviews GitHub pull requests in the same flow.

Small GitHub-only team that wants PR review with auto-committed fixes

Ellipsis

It is a GitHub App that reviews every PR for style, bugs, and architecture and can commit fixes and write PR descriptions on its own.

Founder already on a ChatGPT plan who wants coding included

Codex

Codex is included with ChatGPT plans from the free tier up through Pro, so there is no separate coding subscription to manage.

Frequently asked questions

Can Ellipsis work outside GitHub?: No. The fact sheet says it supports only GitHub, with no integration for GitLab, Bitbucket, or other Git platforms.
Does Codex let me use non-OpenAI models like Claude or Gemini?: No. Codex is locked to OpenAI's GPT models out of the box, with no Claude or Gemini support listed.
Which is cheaper to start?: Both have a $0 entry. Codex Free is $0/month flat. Ellipsis Managed SaaS is $0 base plus usage (tokens at cost, $0.142 / vCPU-hour, $0.024 / GB-hour, 20% platform fee).

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/ellipsis — 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.

## Ellipsis (/tools/ellipsis)
Tagline: AI agent that reviews every PR — comments on style, bugs, and architecture inside GitHub.
Category: AI Coding Agents
Pricing model: paid
Starts at: Managed SaaS — $0 base + usage (tokens at cost, $0.142 / vCPU-hour, $0.024 / GB-hour, 20% platform fee)
Platforms: web
Public repo: none listed
Docs: none listed
Verified plans (read 2026-08-22): Managed SaaS $0 base + usage (tokens at cost, $0.142 / vCPU-hour, $0.024 / GB-hour, 20% platform fee) | Your AWS Account $0 base + usage + AWS costs (20% platform fee; CPU, memory, and tokens billed by AWS) | Standard support $5,000 / month | Advanced support $7,500 / month | Premier support $15,000 / month
Strengths on file: Functions as a GitHub App that automatically reviews pull requests.; Can generate and commit code fixes directly to a pull request in response to review feedback.; Reviews cover code style, potential bugs, and architectural concerns.; Can produce pull request descriptions generated from code diffs.
Limits on file: Supports only GitHub, with no integration for GitLab, Bitbucket, or other Git platforms.; No IDE extension or CLI is offered; interaction is limited to the GitHub web interface.; Free tier imposes usage limits consistent with its freemium pricing.
Ellipsis is an AI code-review agent that reviews every pull request inside GitHub. It runs as a GitHub App that reviews pull requests automatically.
Its reviews cover code style, potential bugs, and architectural concerns, and it can go further than commenting: it can generate and commit code fixes directly to a pull request in response to feedback, and produce pull request descriptions from code diffs.
It fits teams that work in GitHub and want automated PR review and fixes. Caveats: it supports only GitHub, with no integration for GitLab, Bitbucket, or other Git platforms; there is no IDE extension or CLI, so interaction is limited to the GitHub web interface; and the free tier imposes usage limits.
Among code-review tools, it is a GitHub-native agent that both comments and commits fixes rather than a standalone editor or CLI reviewer.

Change log

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