# Aider vs OpenAI Codex

> Aider vs OpenAI Codex: Aider is our pick, leading for free plans and local models. They split on bring your own api key and where it runs. Verified October.

![OpenAI Codex logo](https://www.versusref.com/logos/openai-codex.png)

Aider (Original git-native terminal pair programmer; BYO key only, no paid tier; publishes its own polyglot LLM leaderboard (also oss_self_hosted)) and OpenAI Codex (Coding agent across CLI (Apache-2.0), IDE extension, Codex Cloud (cloud_agent) and ChatGPT desktop app; usage shared with ChatGPT Work. The standalone Codex app merged into the ChatGPT desktop app on 2026-07-09.) are AI coding agents platforms, priced from $0 + your model API bill and $0 + your model API bill respectively. Below: the bottom line, verified head-to-head facts, and real production costs.

AI coding agents platforms · 38 facts compared · all sourced · pricing verified Oct 2, 2026

## Bottom line

Aider takes four of seven use cases on openness and terminal focus. Its entire tool is free and open source under Apache-2.0, which wins Free Plans and Open Source, and it reaches more providers, including OpenAI, Anthropic, Gemini, Groq, LM Studio and xAI, which wins Local Models. Its CLI-first surfaces win Terminal Workflows. OpenAI Codex still leads where polish and governance matter: Beginners, with a free plan and paid plans from $8/mo, Enterprise, with SAML SSO, SOC 2 and audit logs, and VS Code, with native editor support. Teams that want a free, hackable agent should start with Aider.

## Verdict summary

| Use case | Winner | Why |
| --- | --- | --- |
| Beginners | OpenAI Codex | OpenAI Codex is the gentler on-ramp. |
| Enterprise | OpenAI Codex | OpenAI Codex has the fuller enterprise package. |
| Free Plans | Aider | Aider's whole tool is free and open source, with no plan limits; you bring your own API key, which it requires. |
| Local Models | Aider | Both run local models and both are Apache-2.0, with OpenAI Codex's license covering the Codex CLI. |
| Open Source | Aider | Both carry the Apache-2.0 license, but for OpenAI Codex it covers the Codex CLI, while Aider's whole tool is free and open source. |
| Terminal Workflows | Aider | Aider is a terminal tool first: its surfaces lead with the CLI, plus IDE use through watch-mode code comments. |
| VS Code | OpenAI Codex | Editor support decides this, and OpenAI Codex names VS Code, VS Code Insiders and Cursor, plus two more. |

## Aider vs OpenAI Codex: head-to-head facts

| Fact | Aider | OpenAI Codex | Verified |
| --- | --- | --- | --- |
| How usage is metered | Own API key ([source](https://aider.chat/)) | Time windows + per-token ([source](https://developers.openai.com/codex/pricing)) | Oct 2 |
| What the free plan allows | Entire tool free/OSS ([source](https://github.com/Aider-AI/aider)) | Free $0: 'GPT-6 Luna at Standard speed in the desktop app ([source](https://developers.openai.com/codex/pricing)) | Oct 2 |
| Cheapest paid plan (monthly) | n/a | $8 ([source](https://developers.openai.com/codex/pricing)) | Oct 2 |
| Top individual plan | n/a | $500 ([source](https://developers.openai.com/codex/pricing)) | Oct 2 |
| Usage included at entry tier | n/a | Plus ($20) ([source](https://developers.openai.com/codex/pricing)) | Oct 2 |
| Rate-limit window | n/a | per five-hour period + weekly limits may apply ([source](https://developers.openai.com/codex/pricing)) | Oct 2 |
| Bring your own API key | true (required) ([source](https://aider.chat/docs/llms.html)) | true ([source](https://developers.openai.com/codex/pricing)) | Oct 2 |
| Models available | n/a | GPT-6 Astra, GPT-6.1 Sol, GPT-6 Sol, GPT-6 Luna +6 more ([source](https://developers.openai.com/codex/pricing)) | Oct 2 |
| Pick the model per task | ✓  Yes ([source](https://aider.chat/docs/usage/modes.html)) | ✓  Yes ([source](https://learn.chatgpt.com/docs/models)) | Oct 2 |
| Runs local models | ✓  Yes ([source](https://aider.chat/docs/llms.html)) | ✓  Yes ([source](https://learn.chatgpt.com/docs/codex-manual.md)) | Oct 2 |
| Where it runs | CLI/terminal, IDE via watch-mode code comments +1 more ([source](https://aider.chat/)) | ChatGPT desktop app ([source](https://learn.chatgpt.com/docs/codex-manual.md)) | Oct 2 |
| Autonomous multi-file edits | ✓  true ([source](https://aider.chat/)) | ✓  Yes ([source](https://learn.chatgpt.com/docs/cloud.md)) | Oct 2 |
| Runs terminal commands | ✓  Yes ([source](https://aider.chat/docs/usage/commands.html)) | ✓  Yes ([source](https://learn.chatgpt.com/docs/agent-approvals-security.md)) | Oct 2 |
| Background / cloud agents | n/a | ✓  Yes ([source](https://learn.chatgpt.com/docs/cloud.md)) | Oct 2 |
| Opens PRs from issues | n/a | ✓  Yes ([source](https://learn.chatgpt.com/docs/codex-manual.md)) | Oct 2 |
| MCP support | n/a | ✓  Yes ([source](https://learn.chatgpt.com/docs/extend/mcp.md)) | Oct 2 |
| Trains on your code? | Analytics strictly opt-in ([source](https://aider.chat/docs/more/analytics.html)) | Business ([source](https://learn.chatgpt.com/docs/codex-manual.md)) | Oct 2 |
| Self-hosted / VPC deployment | ✓  Yes ([source](https://aider.chat/)) | ✓  Yes ([source](https://learn.chatgpt.com/docs/codex-manual.md)) | Oct 2 |
| License | Apache-2.0 ([source](https://github.com/Aider-AI/aider)) | Apache-2.0 (Codex CLI) ([source](https://github.com/openai/codex)) | Oct 2 |
| Supported model providers | OpenAI, Anthropic, Gemini, Groq, LM Studio, xAI +9 more ([source](https://aider.chat/docs/llms.html)) | OpenAI (ChatGPT sign-in or API key), Azure OpenAI +5 more ([source](https://learn.chatgpt.com/docs/codex-manual.md)) | Oct 2 |

## Aider vs OpenAI Codex pricing: true cost at 3 usage tiers

Real monthly cost at 3 developer profiles: hobbyist (~5 h/week), full-time developer (~25 h/week of daily agent use), team of 5. Most vendors do not publish how much usage a plan covers, so the full-time row spans the cheapest to the top individual plan unless the vendor publishes its own guidance for daily users. Bring-your-own-key and open-source agents show the model bill you pay the provider, never $0.

| Volume | Buyer | Aider | OpenAI Codex | Note |
| --- | --- | --- | --- | --- |
| ~5 h/week of agent use | Hobbyist | Free + your model API bill | Free with your own key; plans $8-$500/mo | Side projects and evenings. Priced at each vendor's cheapest paid plan (annual billing where offered), the tier every vendor sells for light use. |
| ~25 h/week, daily multi-file agent tasks | Full-time developer | Free + your model API bill | Free with your own key; plans $8-$500/mo | Daily agent use. Most vendors do not publish how much usage a plan covers, so this shows the span from the cheapest to the top individual plan; where a vendor publishes its own guidance for daily agent users, that figure is used instead. |
| 5 seats | Team of 5 | Free + your model API bill | $125/mo | Priced from each vendor's own team plan: per-seat prices x 5, flat team plans as published. A tool with no published team price shows that rather than a guess. |

## Aider vs OpenAI Codex: verdicts by use case

### Beginners → OpenAI Codex

OpenAI Codex is the gentler on-ramp. Its free plan includes GPT-6 Luna at Standard speed in the desktop app, and its cheapest paid plan is $8/mo, with usage tied to plans such as Plus. Aider is free and open source, but it requires your own API key and meters through it, so the bill depends on your provider rather than a fixed plan. Aider does offer checkpoints and rollback, which OpenAI Codex does not publish. Aider runs in the terminal, while OpenAI Codex runs in the ChatGPT desktop app.

### Enterprise → OpenAI Codex

OpenAI Codex has the fuller enterprise package. On training, Aider only states that analytics are strictly opt-in, while OpenAI Codex lists a Business-tier policy. Both offer self-hosted deployment, though OpenAI Codex's is vendor claimed. OpenAI Codex adds SAML SSO and MFA on Business, SOC 2 and admin audit logs, none of which Aider publishes. Neither publishes a zero data retention option. For a security review that expects SSO, audit logs and a compliance record, OpenAI Codex is the safer pick.

### Free Plans → Aider

Aider's whole tool is free and open source, with no plan limits; you bring your own API key, which it requires. Paired with its local model support, that means real agent work without any subscription. OpenAI Codex's free plan is narrower: GPT-6 Luna at Standard speed in the desktop app. OpenAI Codex also accepts your own key and runs local models, and its cheapest paid plan is $8/mo if you outgrow the free tier. For unrestricted free use, Aider goes further.

### Local Models → Aider

Both run local models and both are Apache-2.0, with OpenAI Codex's license covering the Codex CLI. The difference is provider breadth: Aider names OpenAI, Anthropic, Gemini, Groq, LM Studio and xAI, plus nine more, while OpenAI Codex lists OpenAI through ChatGPT sign-in or API key and Azure OpenAI, plus five more. Aider explicitly names a local runner in LM Studio. Both accept your own API key, and Aider is built around it. Aider is the more flexible local setup.

### Open Source → Aider

Both carry the Apache-2.0 license, but for OpenAI Codex it covers the Codex CLI, while Aider's whole tool is free and open source. Aider also reaches more providers: OpenAI, Anthropic, Gemini, Groq, LM Studio and xAI, plus nine more, against OpenAI and Azure OpenAI plus five more. Both run local models. Aider has 49,300 GitHub stars and no paid or hosted offering, while OpenAI Codex has 127,600 stars and sells paid plans from $8/mo. On license scope and provider reach, Aider edges ahead.

### Terminal Workflows → Aider

Aider is a terminal tool first: its surfaces lead with the CLI, plus IDE use through watch-mode code comments. OpenAI Codex's listed surface is the ChatGPT desktop app. Both run terminal commands. OpenAI Codex does add background agents and MCP support, which Aider does not publish, and both load project rules, with Aider using CONVENTIONS.md files and OpenAI Codex using nested AGENTS.md files. Where the agent runs matters most for shell users, which gives Aider the edge.

### VS Code → OpenAI Codex

Editor support decides this, and OpenAI Codex names VS Code, VS Code Insiders and Cursor, plus two more. Aider reaches IDEs only through watch-mode code comments. Both make autonomous multi-file edits. Aider does offer checkpoints and rollback plus codebase indexing, which OpenAI Codex does not publish, so it is stronger on undo and context. OpenAI Codex ties its usage to plans such as Plus. Native VS Code support matters most here, so OpenAI Codex edges ahead.

## Aider vs OpenAI Codex: common questions

### Is Aider cheaper than OpenAI Codex?

Aider's entire tool is free and open source, but it requires your own API key, so you pay your model provider directly. OpenAI Codex has a free plan with GPT-6 Luna at Standard speed in the desktop app, and its cheapest paid plan is $8/mo. Which costs less depends on your API usage with Aider versus a fixed OpenAI Codex plan.

### Aider vs OpenAI Codex: which is better for beginners?

OpenAI Codex is the gentler start. Its free plan includes GPT-6 Luna at Standard speed in the desktop app, and paid plans start at $8/mo. Aider is free and open source but requires your own API key, so costs depend on your provider. Aider does offer checkpoints and rollback, which OpenAI Codex does not publish.

### Is Aider or OpenAI Codex better for enterprise teams?

OpenAI Codex offers SAML SSO and MFA on Business, SOC 2, admin audit logs, enterprise data residency controls and a contact-sales enterprise plan. Aider does not publish these, though it offers self-hosted deployment.

### Which model providers do Aider and OpenAI Codex support?

Aider supports OpenAI, Anthropic, Gemini, Groq, LM Studio and xAI, plus nine more. OpenAI Codex supports OpenAI through ChatGPT sign-in or API key and Azure OpenAI, plus five more.

### Do Aider and OpenAI Codex run local models?

Yes, both run local models, and both let you pick the model per task.

### How is usage metered in Aider vs OpenAI Codex?

Aider meters through your own API key, which it requires. OpenAI Codex uses time windows plus per-token metering, with limits per five-hour period and possible weekly limits.

### What does OpenAI Codex cost for a team?

OpenAI Codex's team plan is $25/user/mo, and an enterprise plan is available through sales. Its top individual plan is $500/mo.

### Does Aider have a hosted version?

No. Aider has no paid or hosted offering; the entire tool is free and open source under Apache-2.0.

### Which models does OpenAI Codex offer?

OpenAI Codex offers GPT-6 Astra, GPT-6.1 Sol, GPT-6 Sol and GPT-6 Luna, plus six more, and recommends GPT-6.1 Sol when available to your account.

Source: https://www.versusref.com/coding-agents/aider-vs-openai-codex/