Go
$8/mo
Limits GPT-6 Luna at Standard speed in the desktop app (lightweight tasks). Caps not published.Source: developers.openai.com · checked 2026-10-16
Codex pricing, usage limits and free plan (Oct 2026)
OpenAI · 4 paid plans tracked · from $8/mo · last checked 2026-10-16
Is Codex free?
Free tier
Free $0: GPT-6 Luna at Standard speed in the desktop app, 'subject to rollout'. No image generation on Free.Source: developers.openai.com · checked 2026-10-16
Codex plans, prices and usage limits
Plus
$20/mo
Limits Estimated local messages per 5 hours: GPT-6 Astra 5-45; GPT-6.1 Sol 15-160; GPT-6 Sol 15-150; GPT-6 Luna 350-3,000. Weekly limits may also apply. Shared with ChatGPT Work.Source: developers.openai.com · checked 2026-10-16
Pro ($100/$200/$500)
$100/mo
$100, $200 or $500/mo
Limits 'Pro plans currently have no five-hour limit'; weekly allowances vary by tier (not published). Ultrafast mode on Pro $500 only.Source: developers.openai.com · checked 2026-10-16
API key
API token pricing
Limits Pay per token; no cloud features (GitHub code review, Slack).Source: developers.openai.com · checked 2026-10-16
How Codex's limits reset
| Plan | Price | Periods the vendor mentions |
|---|---|---|
| Free | $0 | Not stated |
| Go | $8/mo | Not stated |
| Plus | $20/mo | 5-hourWeekly |
| Pro ($100/$200/$500) | $100/mo | 5-hourWeekly |
| API key | API token pricing | Not stated |
- Plus Weekly limits may also apply.
- Pro ($100/$200/$500) 'Pro plans currently have no five-hour limit'; weekly allowances vary by tier (not published).
Quoted from the sources above. Allowance periods are the time words each vendor uses in its limits ("weekly", "five-hour", "per month").
Notes
- Fast mode uses 2.5x included usage; Ultrafast 8x. Image generations use limits ~3-5x faster.
- Voice in desktop billed at $0.05/min from Codex budget.
Flags & uncertainty
OpenAI calls the per-5-hour numbers 'estimates', not fixed limits.
Codex price and limit history
No price, limit or free-tier change logged for Codex yet. The detector checks its pricing pages daily; get an alert when it moves.
Codex news
Curated from official Codex posts, changelogs and status pages. Pricing and limit moves are highlighted.
- Codex CLI 0.163: searchable /config, mid-response steering, parallel read-only tools
The release also adds a leader key in /keymap and a /daemon restart, and turns on Daybreak by default for eligible accounts.
Source: github.com - Outage: elevated errors across ChatGPT, Codex and the OpenAI API
OpenAI's status page listed most components as affected, including Conversations, Codex, Responses and the Agents API, before reporting full recovery.
Source: status.openai.com - OpenAI ships GPT-6.1 Sol at one-fifth of Astra's API price
OpenAI pitches GPT-6.1 Sol as near-Astra intelligence for coding, computer use and professional work at a fifth of Astra's standard input and output token prices.
Source: openai.com - OpenAI DevDay 2026: 20+ announcements across ChatGPT, Codex and the API
OpenAI's recap gathers its DevDay launches, covering GPT-6 Astra, ChatGPT, Codex, the APIs, security and builder tools.
Source: openai.com - OpenAI introduces GPT-6 Sol and GPT-6 Luna
Two GPT-6 models for everyday work that trade capability against cost differently.
Source: openai.com - GPT-6 brings better prompt caching to cut API latency and cost
OpenAI cites higher cache hit rates, new diagnostics, explicit breakpoints and new controls.
Source: openai.comCurrent Codex plans & limits - OpenAI launches the Agents API, built on the Codex harness
A managed service for building cloud agents, with orchestration, long-running sessions and tool use.
Source: openai.com - OpenAI launches GPT-6 Astra, its most capable model
OpenAI calls GPT-6 Astra its most intelligent and aligned model yet, state of the art in computer use, coding, cybersecurity and science.
Source: openai.com - OpenAI previews an Ultrafast API tier: GPT-5.6 Sol at up to 14× speed
Powered by Cerebras, the new service tier delivers up to 750 output tokens per second.
Source: openai.com - OpenAI cuts GPT-5.6 Luna and Terra prices
OpenAI announced lower GPT-5.6 pricing for its Luna and Terra models.
Source: openai.comCurrent Codex plans & limits
Compare Codex
Codex pricing questions
Is Codex free?
Yes. Free $0: GPT-6 Luna at Standard speed in the desktop app, 'subject to rollout'. No image generation on Free.
How much does Codex cost?
Codex has 4 paid plans: Go $8/mo; Plus $20/mo; Pro ($100/$200/$500) $100/mo; API key API token pricing. Cheapest: $8/mo. Checked 2026-10-16.
What are Codex's usage limits?
Go: GPT-6 Luna at Standard speed in the desktop app (lightweight tasks). Caps not published. Plus: Estimated local messages per 5 hours: GPT-6 Astra 5-45; GPT-6.1 Sol 15-160; GPT-6 Sol 15-150; GPT-6 Luna 350-3,000. Weekly limits may also apply. Shared with ChatGPT Work. Pro ($100/$200/$500): 'Pro plans currently have no five-hour limit'; weekly allowances vary by tier (not published). Ultrafast mode on Pro $500 only. API key: Pay per token; no cloud features (GitHub code review, Slack). OpenAI calls the per-5-hour numbers 'estimates', not fixed limits.
When do Codex usage limits reset?
Plus: Weekly limits may also apply. Pro ($100/$200/$500): 'Pro plans currently have no five-hour limit'; weekly allowances vary by tier (not published).
Has Codex's pricing changed recently?
No change is logged for Codex yet. Prices were last checked 2026-10-16.
Free to cite. All data is CC BY 4.0: quote, embed or republish it with a link to AI Plan Tracker. Raw data: tools.json · changes.json. Spotted an error? Every fact links to its source and the date we checked it.