
ChatGPT Plus Codex Usage Limits and Credits: Is Codex Included?
Yes, Codex is included in ChatGPT Plus. OpenAI estimates 15–150 GPT-6 Sol messages per five hours, weekly limits may apply, and credits extend usage.

Yes, Codex is included in ChatGPT Plus. OpenAI estimates 15–150 GPT-6 Sol messages per five hours, weekly limits may apply, and credits extend usage.

A saved ChatGPT reset works only once a Work or Codex limit is under 80%. A paid one applies at once and moves your weekly reset; Chat isn't covered.

As of October 8, 2026, everyday ChatGPT text chat is unlimited on every plan. Thinking, tools, Work and Codex have separate caps; few have published numbers.

Claude Fable 5.2 costs 4x GPT-6.2 Sol per token and 6.5–12x per task in same-prompt tests, where both passed every answer. Fable leads only from high effort up.

As of November 14, 2026, Google Flow allows 400 free images a day and AI Mode 25; the Gemini app publishes no number. Uploads stop at 10 files a prompt.

Gemini says "I can't depict some public figures" when it reads a request as a real, identifiable person. Invented people and your own photos still work.

Writing HD or 4K in a Gemini prompt does not set the output pixels. Use a specific creative brief for visual quality, set image_size and aspect_ratio on a supported API model for delivery size, then inspect the saved file before changing prompts, plans, or providers.

Same 9 prompts, one draw each at 1K: Pro, GPT Image 2.5 and 2.6 matched the requested wording; Nano Banana 2.1 slipped on text but costs a quarter of Pro.

As of November 2, 2026, Flow caps Nano Banana 2.1 and 2 Lite at 400 images a day, 1,000 on a plan; the Gemini app has 5-hour and weekly limits, no image count.

Label Image 1 as the identity and Image 2 as the scene, swap only the face or the whole person, and keep the rest. Only for photos you have consent to edit.

No single Nano Banana Pro daily limit: Flow caps Pro at 20–500 images a day by plan, the Gemini app refreshes every 5 hours, AI Mode and Workspace reset daily.

As of November 20, 2026, GPT Image 2.5 low (~$0.006), Recraft ($0.007) and FLUX 3 Klein ($0.009) cost least at 1K; FLUX 3 Image beats 2.6 at high and up.

GPT-6.2 Astra costs 4x GPT-6.2 Sol per token. Sol max ties Astra medium but costs more on short tasks, less on long input. GPT-6.1 Sol vs GPT-6 Astra inside.

Veo 3.1 left the Gemini API on October 22, 2026, so Kling vs Veo now means Gemini Omni 1.2 Flash vs Kling 4.0: Kling costs 2.26× per 720p clip but runs to 30 s.

Google AI Pro and Ultra both include Gemini 4 Argon in AI Studio, with higher daily quota on Ultra. Gemini app limits use five-hour and weekly windows; API billing is separate.

Same tasks, one gateway: Opus 5.5 at high effort cost $0.31, Argon at high $0.40 through Nov 30 and $0.81 from Dec 1, when its token price equals Opus.

Gemini 4 Argon lists at 2.67x 3.8 Flash per token, but on five same-prompt calls it cost 1.57x as much through Nov 30, 2026, and 3.15x in December.

Since November 10, 2026, both cost the same per token, but on identical prompts Carbon wrote 3.8x Argon's output. It pays on hard, long jobs, not quick ones.

On 11 identical API calls, Gemini 4 Hydrogen and 3.1 Pro both passed every task, but 3.1 Pro cost 3.2x as much. The Gemini app's personal plans no longer offer 3.1 Pro.

At default settings, Gemini 4 Neon costs 14% more per task than Carbon through November 30 and 43% less from December 1. Hydrogen costs half as much as Neon.

Gemini 4 Neon at high scores 60 for 0.37x the cost per task of Claude Opus 5.5 at max (59). GPT-6.2 Sol is cheaper than both but tops out at 57.

Gemini high demand error? In the app, “another model was used” means a lighter model answered, not a usage limit. In the API, split 503 from 429 and 504 first.

Gemini 4 Argon has no free plan, and the Gemini app no longer lists it. Arena or a family plan gets you in; US student and Pixel 11 Pro offers are less sure.

Claude cloud session credit claims closed October 7, 2026; all balances expired November 4. Cloud sessions now use plan limits; usage credits bill at API rates.