PlanetGPU
OpenAI coding agent profile

OpenAI Codex / ChatGPT pricing and quotas

Best documented premium coding-agent quota across local, IDE, and cloud surfaces. This page separates published plan details from unofficial modeled value estimates.

Back to comparisonModeled estimates are unofficialSources shown per plan
AI coding agents and developer tooling plans represented as connected compute and workflow blocks.
Plans tracked
3
High transparency
3
BYOK / partial
3
Dollar estimate
unofficial
not a vendor entitlement
Back to all AI coding agents

Modeled value estimate caveat

Any dollar-equivalent figure on this page is PlanetGPU modeling, not an official vendor entitlement. Prefer the published quota, overage behavior, transparency, and source links when making a purchase decision.

Plus

high transparency
BYOK partialhybridverified 2026-06-14
$20/mo
fixed

Included usage / quota

Codex included with Plus. Published 5-hour examples: GPT-5.5 local messages 15-80, GPT-5.4 20-100, GPT-5.4 mini 60-350. Weekly limits may apply.

Overage

ChatGPT credits after included limits; Codex credit burn maps to token-based rate card.

Best for

Solo developers doing a few focused coding sessions each week.

Supported models

GPT-5.5GPT-5.4GPT-5.4 miniGPT-5.3-Codex

Surfaces

Web, CLI, VS Code IDE extension, iOS, Slack, GitHub review

Modeled estimate is unofficial

Modeled estimate ~$20 (medium confidence). Included usage may be more useful than equivalent direct API spend for active coding, but the official entitlement is quota/credits, not dollars.

Caveats

  • API-key auth enables local CLI/IDE usage but removes cloud features like GitHub review and Slack.
OfficialHelp

Pro 5x

high transparency
BYOK partialhybridverified 2026-06-14
$100/mo
fixed

Included usage / quota

5x Plus Codex usage. Published 5-hour examples: GPT-5.5 local messages 80-400, GPT-5.4 100-500, GPT-5.4 mini 300-1750.

Overage

ChatGPT credits after included limits; token-based Codex rate card applies.

Best for

Daily professional Codex users who need longer sessions.

Supported models

GPT-5.5GPT-5.4GPT-5.4 miniGPT-5.3-CodexGPT-5.3-Codex-Spark preview

Surfaces

Web, CLI, VS Code IDE extension, iOS, Slack, GitHub review

Modeled estimate is unofficial

Modeled estimate ~$100 (medium confidence). May exceed equivalent direct API spend under heavy use, but results vary by model, context, output, and fast mode.

Caveats

  • Pro-model allowance is still limited and may fall back to another model after limits.
OfficialHelp

Pro 20x

high transparency
BYOK partialhybridverified 2026-06-14
$200/mo
fixed

Included usage / quota

20x Plus Codex usage. Published 5-hour examples: GPT-5.5 local messages 300-1600, GPT-5.4 400-2000, GPT-5.4 mini 1200-7000.

Overage

ChatGPT credits after included limits; token-based Codex rate card applies.

Best for

Agent-heavy developers running Codex as a primary coding workflow.

Supported models

GPT-5.5GPT-5.4GPT-5.4 miniGPT-5.3-CodexGPT-5.3-Codex-Spark preview

Surfaces

Web, CLI, VS Code IDE extension, iOS, Slack, GitHub review

Modeled estimate is unofficial

Modeled estimate ~$14,000 (low confidence). High-utilization secondary estimate, not an official OpenAI entitlement. Official source publishes usage windows and credit rates, not a dollar value.

Caveats

  • Treat the modeled API-spend estimate as a ceiling-style estimate for heavy use, not guaranteed monthly value.
OfficialSecondary