AgentPulse
Data publication timestamp unavailable. Coverage and source policy →

OpenAI · Coding agent

Codex

The coding agent, underlying model, provider and subscription plan are separate entities. No model-specific result is transferred to this agent.

Official product information ↗ · Compare tools →

Codex

OpenAI · listed as a coding agent

Use Codex in the terminal, IDE extension or web. Useful to trial on an existing repository with a concrete feature and visible review.

How access is sold: ChatGPT subscriptions include access; ChatGPT Work and Codex share usage. API billing is separate.

Official product and billing information ↗

What developers have reported

1 firsthand and 1 secondhand accounts in the October guide. The sample is selected and not representative.

Firsthand account · Simon Willison · 2026-10-09

A Django feature shipped after a second round of review

Codex voice mode · GPT-6 Astra High

Willison reports building newsletter models, migrations, imports, archive pages and search integration with Codex voice mode, using GPT-6 Astra High. He then reviewed the pull request, changed a subprocess-based import to an API-based import, and refined the display before deploying.

What this does not establish: One experienced developer and one Django feature. He describes roughly half an hour by voice plus further typed work; this is not a timing benchmark or a general result for every Codex model.

Read the original account ↗ · Full report context

Secondhand historical report · Simon Willison, quoting Thibault Sottiaux · 2026-07-16

An older destructive-action incident shows why agent permissions matter

Codex with full-access execution · GPT-5.6

Willison collected an OpenAI engineering statement describing reports of unintended file deletion involving GPT-5.6, full-access execution and temporary-directory handling. It illustrates a failure mode worth isolating when an agent can modify your files.

What this does not establish: A July report about an older model, relaying an engineering statement. It does not establish a current failure rate, an unresolved current bug, or that another provider is immune.

Read the original account ↗ · Full report context

Checking published report updates…

Official subscriptions

Listed currency: USD · Monthly billing. Region is unverified unless specified per offer. Annual discounts are excluded. These are published amounts, not a local checkout quote; confirm region, taxes and availability with the provider. Subscription allowance and API token billing are different quantities.

Tool / planMonthly priceDocumented allowance and caveatsProvenance
Codex
ChatGPT Free

Region: unverified

$0.00 / month

Desktop GPT-6 Luna at Standard speed, subject to rollout. Limit/access source ↗

Comparable task capacity: unknown.

Official pricing ↗

Source verified

Codex
ChatGPT Go

Region: unverified

$8.00 / month

Desktop GPT-6 Luna at Standard speed, subject to rollout. Limit/access source ↗

Comparable task capacity: unknown.

Official pricing ↗

Source verified

Codex
ChatGPT Plus

Region: unverified

$20.00 / month

Codex web, CLI and IDE extension. ChatGPT Work and Codex share usage; API billing is separate. Limit/access source ↗

Comparable task capacity: unknown.

Official pricing ↗

Source verified

Codex
ChatGPT Pro $100

Region: unverified

$100.00 / month

Everything in Plus. Usage depends on task/model; check account limits. API billing is separate. Limit/access source ↗

Comparable task capacity: unknown.

Official pricing ↗

Source verified

Codex
ChatGPT Pro $200

Region: unverified

$200.00 / month

Everything in Plus. Usage depends on task/model; check account limits. API billing is separate. Limit/access source ↗

Comparable task capacity: unknown.

Official pricing ↗

Source verified

Codex
ChatGPT Pro $500

Region: unverified

$500.00 / month

Everything in Plus, with Ultrafast access. Usage depends on task/model; API billing is separate. Limit/access source ↗

Comparable task capacity: unknown.

Official pricing ↗

Source verified

How to use this evidence

These are selected, attributed accounts with the author’s stated tool configuration and limits. They do not establish a general success rate or prove that a current version behaves the same way.

Read the research context → · Review the evidence rules →

Releases and platform support

Release-by-release compatibility has not been verified in this edition. For current platform support, use the official product documentation above.