Codex vs Claude Code cost
Same $20 entry price, very different limits and cache economics.
Data verified 2026-10-13 from official pricing pages.
OpenAI Codex
| Plan | Price (monthly) | Notes | Status |
|---|---|---|---|
| Free / Go | $0 | Limited Codex access (Go price not shown on official page text) | verified |
| Plus | $20/mo | Codex on web, CLI, IDE, iOS | verified |
| Pro 100 | $100/mo | No 5-hour limit | verified |
| Pro 200 | $200/mo | More usage than Pro 100 (source: help.openai.com/en/articles/9793128) | verified |
| Pro 500 | $500/mo | Highest usage; Ultrafast mode | verified |
| Business (Standard seat) | $25/mo | $20/mo annual; source openai.com/api/pricing (business page) | verified |
Source: https://learn.chatgpt.com/docs/pricing · Last verified 2026-10-13
Plus: rolling 5-hour window plus possible weekly limits. OpenAI's estimate for Plus is 15-160 local GPT-6.1 Sol messages, 5-45 GPT-6 Astra, or 350-3,000 GPT-6 Luna messages per 5 hours. Pro plans currently have no 5-hour limit (weekly limits may apply). Credits can extend usage; Codex CLI can also run on an API key at API prices.
Claude Code
| Plan | Price (monthly) | Notes | Status |
|---|---|---|---|
| Free | $0 | Claude Code not included | verified |
| Pro | $20/mo | $17/mo billed annually ($200/yr); includes Claude Code | verified |
| Max 5x | $100/mo | 5x Pro usage; includes $100/mo API credits | verified |
| Max 20x | $200/mo | 20x Pro usage; $200/mo API credits listed. Plan price not shown explicitly on page text ('From $100') | unverified |
| Enterprise | $20/mo | $20/seat/mo + usage at API rates, billed annually | verified |
Source: https://claude.com/pricing · Last verified 2026-10-13
Usage resets on a rolling 5-hour session window; paid plans add weekly limits. Claude Code shares one usage pool with Claude chat. Pro = at least 5x Free per session; Max = 5x or 20x Pro. No fixed message count is published. Past the limit you can enable usage credits billed at standard API rates.
API cost on the same workload
| Model | In / Cached / Out | Est./month |
|---|---|---|
| GPT-6.1 Sol | $2 / $0.1 / $10 | $90 |
| GPT-5.3 Codex | $1.75 / $0.175 / $14 | $99 |
| Claude Sonnet 5.5 | $2 / — / $10 | $165 |
| Claude Opus 5.5 | $4 / $0.2 / $20 | $180 |
3M in + 150K out/day, 60% cache, 22 days. Full side-by-side: Claude Code vs OpenAI Codex.
FAQ
Is Codex cheaper than Claude Code?
At the $20 tier both cost the same (ChatGPT Plus vs Claude Pro). On the API, GPT-6.1 Sol ($2 in / $0.10 cached / $10 out) and Claude Sonnet 5.5 ($2 / $10, no cache price listed) have the same list price, but Sol's cached-input rate makes it cheaper for cache-heavy agent loops.
Which has better usage limits?
Both use a rolling 5-hour window on the $20 plan. OpenAI's Pro plans currently have no 5-hour limit (weekly limits may apply); Claude Max raises the allowance 5x or 20x.
What do the top plans cost?
Codex: Pro 100 ($100), Pro 200 ($200), Pro 500 ($500). Claude: Max 5x ($100) and Max 20x.