Codex vs Claude Code limits (ChatGPT vs Claude plans)
Generated from our dataset. Checked 2026-10-19.
| ChatGPT Plus $20/mo | Claude Pro $20/mo ($17/mo billed annually) | ChatGPT Pro $100/mo ($100, $200 or $500/mo tiers) | Claude Max 5x $100/mo | Claude Max 20x $200/mo | |
|---|---|---|---|---|---|
| Price | $20/mo [source, checked 2026-10-19] | $20/mo monthly; $17/mo annual ($200 up front) [source, checked 2026-10-19] | $100, $200 or $500/mo (3 usage tiers) [source, checked 2026-10-19] | $100/mo [source, checked 2026-10-19] | $200/mo (not printed on card; card says 'From $100'; $200 tier implied by '$100 to $200/month in API credits' — verify) [source, checked 2026-10-19] |
| Context window (Instant / Reasoning) | 54K / 256K [source, checked 2026-10-19] | not published / n/a | 128K / 400K [source, checked 2026-10-19] | not published / n/a | not published / n/a |
| Codex local messages per 5h (estimate) | 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 [source, checked 2026-10-19] | not published / n/a | not published / n/a | not published / n/a | not published / n/a |
| Codex surfaces | Web, CLI, IDE extension, iOS; cloud code review [source, checked 2026-10-19] | not published / n/a | not published / n/a | not published / n/a | not published / n/a |
| Chat message caps | not published [source, checked 2026-10-19] | not published / n/a | not published / n/a | not published / n/a | not published / n/a |
| Usage | not published / n/a | At least 5x Free per 5-hour session, plus weekly limits; no fixed message count [source, checked 2026-10-19] | not published / n/a | 5x Pro per 5-hour session, plus weekly limits [source, checked 2026-10-19] | 20x Pro per 5-hour session, plus weekly limits [source, checked 2026-10-19] |
| Claude Code | not published / n/a | Included; shares the same usage pool as chat [source, checked 2026-10-19] | not published / n/a | Included, shared pool [source, checked 2026-10-19] | Included, shared pool [source, checked 2026-10-19] |
| Fable model | not published / n/a | Usage credits only [source, checked 2026-10-19] | not published / n/a | 50% of weekly limits [source, checked 2026-10-19] | not published / n/a |
| Context window | not published / n/a | Up to 1M, varies by model [source, checked 2026-10-19] | not published / n/a | not published / n/a | not published / n/a |
| Codex 5-hour limit | not published / n/a | not published / n/a | None currently ("Pro plans currently have no five-hour limit"); weekly allowance not published [source, checked 2026-10-19] | not published / n/a | not published / n/a |
| Ultrafast mode | not published / n/a | not published / n/a | Pro $500 only; uses 8x included usage [source, checked 2026-10-19] | not published / n/a | not published / n/a |
| Voice / images | not published / n/a | not published / n/a | Unlimited* (reasonable use) [source, checked 2026-10-19] | not published / n/a | not published / n/a |
| API credits | not published / n/a | not published / n/a | not published / n/a | $100/month [source, checked 2026-10-19] | $200/month [source, checked 2026-10-19] |
| Key models | GPT-6, GPT-6.1 Sol, GPT-6 Astra, GPT-6 Sol, GPT-5.6 Sol/Terra | Opus, Sonnet, Haiku (Fable via usage credits) | GPT-6 Astra (Pro reasoning), GPT-6.1 Sol (expanded) | Fable, Opus, Sonnet, Haiku | Fable, Opus, Sonnet, Haiku |