400K tokens
Context window
OpenAI ChatGPT
GPT-5
Tool calling, structured output, agentic loops
128K tokens
Max output
Paid
Cost
late 2024
Knowledge cutoff
text, image, audio
Modalities
Last verified 20 May 2026 Pricing is deliberately not listed here - check the vendor's own page. Report a correction
What it tends to refuse
Weapons, malware, explicit sexual content, medical and legal advice presented as professional guidance
Of everything listed here it sticks to a JSON schema best. It also weights the end of a long prompt over the start, so the rules that must hold go last.
Standing rules for this model go in AGENTS.md, not in every message.
See the config files.
Written for ChatGPT
All 24- CheatsheetChatGPT
ChatGPT image prompts that actually work
Phrases that reliably control background, aspect ratio, style and edits in ChatGPT image generation, and the one habit that fixes most unwanted…
Tested on GPT-5 · Sep 2026
- CheatsheetChatGPT
ChatGPT commands for the desktop app
The composer slash commands in the ChatGPT desktop app: switching models, running a review, and working in the cloud or in a git worktree.
Tested on GPT-5 · Sep 2026
- ErrorChatGPTGemini
This model's maximum context length is N tokens
The request is longer than the model can hold. Your prompt, the whole conversation history and the space reserved for the answer all count. The…
Tested on GPT-5 · May 2026
- CheatsheetChatGPT
ChatGPT commands and keyboard shortcuts
The commands and shortcuts the interface never shows you, in one table. Mostly keyboard, mostly undocumented.
Tested on GPT-5 · May 2026
Editor who does not flatten your voice
Separates fixing what is wrong from rewriting what is fine, and does only the first unless you ask. It stops the slide into the neutral register…
Tested on GPT-5 · May 2026
ChatGPT desktop app
The native macOS and Windows app: a global hotkey, screen access on request, and a persistent window in place of a browser tab you keep losing.
Tested on GPT-5 · Jun 2026