> Codex Cloud
OpenAI Codex is the coding agent that runs across ChatGPT, an IDE extension, the CLI and cloud environments on a single ChatGPT account, with cloud worktrees, scheduled background tasks, Skills and code review. The Codex pricing documentation lists Free at $0/month for "quick coding tasks", Go at $8/month, Plus at $20/month, Pro from $100/month, Business at $20/user/month billed annually ($25 monthly, minimum 2 users) and Enterprise/Edu by contact, plus an API-key route billed at API rates. Usage is measured as messages per five-hour period that vary by model: on Plus, the documented ranges run from 250-2,000 messages for GPT-5.6 Luna down to 5-45 for GPT-6 Astra, and OpenAI states these are estimates rather than fixed limits.
OpenAI API key with Codex Cloud task access.
// pros
- Free at $0/month lets you run Codex on quick coding tasks with no payment, and Go at $8/month is the cheapest paid step up.
- Plus at $20/month includes Codex on web, CLI, IDE extension and iOS, cloud-based code review and Slack integration, and the GPT-5.6 model family.
- Published per-five-hour usage ranges make planning concrete: for example GPT-5.6 Luna is listed at 250-2,000 local messages on Plus and 5,000-40,000 on Pro 20x.
- API-key usage gives CLI, SDK and IDE access billed at API pricing, which suits CI and shared environments without a ChatGPT seat.
- Business adds no training on business data by default, SAML SSO and MFA, and lets teams extend usage with ChatGPT credits.
// cons
- Free access is described only as "explore Codex capabilities on quick coding tasks", and no free message count is published - the usage table covers Plus, Pro, Business and API-key only.
- Message allowances are ranges affected by model, task complexity, context, tool use, retrieval and caching, and OpenAI states they are not fixed message limits.
- Cloud features including Codex cloud, GitHub code review, Slack and Linear integration require a ChatGPT plan; API-key access excludes all of them.
- Image generation is not available on the Free plan, Codex usage is shared with agentic features such as ChatGPT Work, and model churn is documented on the same page - GPT-5.5 retires from ChatGPT, ChatGPT Work and Codex on all plans on October 14, 2026.
Treat the Free tier as an evaluation rather than a working setup, choose Plus at $20/month if your coding is a few focused sessions a week, and move to Pro from $100/month when agents run continuously. Teams already paying for GitHub Copilot should compare Copilot cloud agent against Codex cloud before funding both.
written by Mike Fleming, Uprouter editorial · verified against official sources September 16, 2026
Value taken from the provider’s own published free-tier terms, expressed in USD.
note: Codex Free is $0/month, described as "Explore Codex capabilities on quick coding tasks"; no fixed free message count is published (Codex pricing docs, checked 2026-09-16).
| Plan | Type | Monthly | Input /1M | Output /1M | Note |
|---|---|---|---|---|---|
| Pay-as-you-go | payg | — | $0.0000 | $0.0000 | Cheapest tracked model rate (OpenRouter-normalized). |
| Free | free | — | — | — | Basic access to explore Codex capabilities for quick coding tasks. |
| Go | subscription | $8.00/mo | — | — | Lightweight plan for coding tasks with increased limits. |
| ChatGPT Free / Go (Codex included) | subscription | $0/mo | — | — | Codex is included across ChatGPT plans, including Free and Go; usage limits vary by plan (help.openai.com, 2026). |
| ChatGPT Plus | subscription | $20.00/mo | — | — | Codex usage included within the Plus allowance; expanded Codex usage and cloud environments (chatgpt.com/codex/pricing). |
| ChatGPT Pro ($100 tier) | subscription | $100.00/mo | — | — | Higher Codex usage allowance; newer codex models (e.g., GPT-6 Astra) included within the existing Codex usage allowance on the $100 Pro plan. |
| ChatGPT Pro ($200 tier) | subscription | $200.00/mo | — | — | Top individual Codex usage allowance; $200 Pro tier for heavy agent use (chatgpt.com/codex/pricing; community announcement of the $100/$200 Pro tiers). |
| OpenAI API (pay-as-you-go) | payg | — | — | — | Codex models are also available on the OpenAI platform with token-based pricing; exact per-model rates not captured in this batch (see catalog entries for gpt-5.x pricing). |
Pricing normalized from public sources — always verify with the provider.
// model prices
$ Does Codex Cloud have a free tier?
Yes — Codex Cloud offers a free tier that we value at roughly $0 in free credits. Always confirm current limits on Codex Cloud's official pricing page — free tiers change without notice.
$ How much does Codex Cloud cost per 1M tokens?
The cheapest model we track at Codex Cloud is $0.0000 per 1M input tokens and $0.0000 per 1M output tokens. This is normalized from Codex Cloud's published pricing — verify with the provider before purchasing, since prices change frequently.
$ Is Codex Cloud safe to use?
Uprouter rates Codex Cloud as low risk. Medium risk. A $0 plan exists but is scoped to quick tasks with no published message allowance, so free capacity is unquantified and shared with ChatGPT Work. Allowances are model-dependent ranges rather than guarantees, Business pricing assumes annual billing and 2+ users, and OpenAI documents fixed model retirement dates that can change which models a plan can reach. Risk ratings are editorial, evidence-based, and never influenced by affiliate relationships.
Raw community sentiment, shown unblended. Votes never feed into objective data fields like price, risk, or status — and never into sort order.
No published reviews yet — be the first.
// more_informationprice history · live status · risk & confidence · code snippets
price_history
No recorded changes yet.
live_status
current: unknownNo probes recorded yet.
Uprouter runs its own probes; best-effort, not a guarantee. Probe results depend on our network location and cadence — for production, always use the provider’s own status page.
risk_&_confidence
Medium risk. A $0 plan exists but is scoped to quick tasks with no published message allowance, so free capacity is unquantified and shared with ChatGPT Work. Allowances are model-dependent ranges rather than guarantees, Business pricing assumes annual billing and 2+ users, and OpenAI documents fixed model retirement dates that can change which models a plan can reach.
Confidence reflects how much verifiable evidence (official docs, probe history, community reports) backs this entry. Risk is our editorial assessment of operator reliability and terms — not financial advice.
code_snippets
# Codex Cloud's own API — get a key from their dashboard
curl https://openai.com/codex/chat/completions \
-H "Authorization: Bearer THEIR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-5-6-sol",
"messages": [{ "role": "user", "content": "Hello" }]
}'Direct to the provider — Uprouter receives nothing; verify their current pricing before purchasing.
Ranked by neutral similarity signals only — live status, free-tier shape and free-credit proximity. Commercial relationships never influence this list.