Coding tool plans - 7 entries
Codex and ChatGPT usage limits
OpenAI's official docs, read on October 17, 2026, set usage limits for Codex and ChatGPT plans across Standard Business, Free and Pro. For GPT-6 Astra (Codex, ChatGPT sign-in) on Standard Business, the docs list 5-45 Local messages per 5h (estimate).
Last verified from learn.chatgpt.com, chatgpt.com. What the docs leave out
- Tiers
- 3
- Tables
- 2
- Entries
- 7
- Verified
- Oct 17, 2026
Limits by model, endpoint and plan
Values are copied exactly as the docs show them, units included, in the docs' own order. A dash means the docs list no value for that row.
GPT-6 Astra (Codex, ChatGPT sign-in), GPT-6.1 Sol (Codex, ChatGPT sign-in) and 2 more
4 scopes - Standard Business
| Model or scope | Local messages per 5h (estimate) |
|---|---|
| GPT-6 Astra (Codex, ChatGPT sign-in) | 5-45 |
| |
| GPT-6.1 Sol (Codex, ChatGPT sign-in) | 15-160 |
| |
| GPT-6 Sol (Codex, ChatGPT sign-in) | 15-150 |
| |
| GPT-6 Luna (Codex, ChatGPT sign-in) | 350-3,000 |
| |
- GPT-6 Astra (Codex, ChatGPT sign-in): Business price: $20/ user / month (2+ users, billed annually); $25 per user per month when billed monthly. Estimate, not a fixed limit.
ChatGPT Chat context windows
3 tiers
| Tier | GPT Instant total context window |
|---|---|
| Free | 27K |
| |
| Go / Plus | 54K |
| |
| Pro | 128K |
| |
- Free: Everyday text chats: Unlimited* (subject to abuse guardrails).
- Go / Plus: Plus links to "Limits apply" (help.openai.com/articles/11909943).
- Pro: GPT-5.6 Sol, Terra, Luna and GPT-5 Thinking Mini: Unlimited* on Pro ("Usage must be reasonable and comply with our policies. Usage refers to Chat limits.").
How to raise your limits
GPT-6 Astra (Codex, ChatGPT sign-in), GPT-6.1 Sol (Codex, ChatGPT sign-in) and 2 more
Business, Edu, and Enterprise plans with flexible pricing can purchase additional workspace credits to continue working. API key usage at standard API rates for extra local chats.
ChatGPT Chat context windows
Upgrade plan.
What the docs leave out
- Exact numeric Codex allowances for Pro 100, Pro 200 and Pro 500: only relative statements are public (Pro 200 > Pro 100; Pro 500 highest; no five-hour limit); current values are shown only in the logged-in usage dashboard (chatgpt.com/codex/settings/usage) or via /status in the Codex CLI.
- Weekly Codex limit figures for any plan: docs say only 'Weekly limits may also apply'; reset times and remaining allowance appear only in the logged-in usage dashboard.
- Numeric Codex limits for Free and Go: published only as 'Limited'.
- Cloud task limits as numbers: docs state only that cloud tasks may use more of your allowance than local messages.
- Code Review (GitHub @Codex reviews) usage limit figures: not published.
- Per-seat Enterprise/Edu usage figures beyond 'same per-seat usage limits as Plus for most features'.
- Classic API-style metrics (RPM, TPM, RPD, concurrency) are not published for ChatGPT-plan Codex usage; API-key Codex usage follows OpenAI API organization rate limits (separate page).
FAQ
What are the Codex and ChatGPT usage limits?
OpenAI's official docs, read on October 17, 2026, set usage limits for Codex and ChatGPT plans across Standard Business, Free and Pro. For GPT-6 Astra (Codex, ChatGPT sign-in) on Standard Business, the docs list 5-45 Local messages per 5h (estimate).
How do I raise my Codex and ChatGPT plans usage limits?
Business, Edu, and Enterprise plans with flexible pricing can purchase additional workspace credits to continue working. API key usage at standard API rates for extra local chats. Upgrade plan.
Where do these ChatGPT plans and Codex numbers come from?
Every value is copied verbatim from OpenAI's official documentation at learn.chatgpt.com and chatgpt.com, read on October 17, 2026. This page lists all 7 entries in 2 tables, each linked to the page it came from.
Related reading
- Codex Usage Limits and Pricing in 2026: Pro 100, Pro 200, Pro 500, Resets, and 'Model at Capacity' ErrorsCodex usage limits and pricing per ChatGPT plan: what Plus, Pro $200 and Pro $500 buy, how resets work, and what to do about 'Selected model is at capacity'.
- OpenAI Cuts GPT-5.6 Luna 80% and Terra 20%: The Cost-Per-Task Math for Agent BuildersGPT-5.6 Luna drops 80% to $0.20/$1.20 per million tokens and Terra 20% to $2/$12. The cost-per-task math for agent builders, Codex quotas and rivals.
- Codex CLI 0.163: Instant Steering Is Now the DefaultCodex CLI 0.163.0 makes mid-response steering the default and adds searchable /config and a leader key. What changed and what to check before upgrading.
- Codex 'gpt-5.5 Model Is Not Supported' Error: The FixCodex says gpt-5.5 is not supported with a ChatGPT account because OpenAI retired it from ChatGPT sign-in on October 14. The fix and what still works.
- ChatGPT Free vs Go vs Plus After GPT-6: Which Model You GetFree and Go ($8) both get GPT-6 Luna in Chat. Plus ($20) is the cheapest plan with GPT-6 Sol and full Codex. What each ChatGPT plan buys now.
- ChatGPT Plus vs Claude Pro for Developers (October 2026)Both cost $20 a month. Plus meters Codex apart from chat and includes GPT-6 Astra; Claude Pro shares one pool with Claude Code. Which to pick.
Sources
Last verified . Every value is copied verbatim from the official pages below, read on that date.
Newsletter
Know when limits change
One email per week. New model releases, pricing and limit changes, and what they mean for what you build.