How large is GPT-4o context window?

GPT-4o and GPT-4o mini both have a 128,000-token context window — roughly 96,000 words or about 200 pages of text. GPT-3.5 Turbo has a smaller 16,000-token window.

Does the system prompt count against the context window?

Yes. Every token in the system prompt, all previous user and assistant messages, and the new user message all count against the context window. Only generated output beyond the context limit gets cut off.

What happens if I exceed the GPT-4o context limit?

OpenAI will return a context_length_exceeded error. You must reduce your prompt length, shorten the conversation history, or switch to a model with a larger context window.

OpenAI Context Window Calculator

Check if your prompts fit within GPT-4o and GPT-3.5 context windows.

Model

System prompt

User prompt

Expected output tokensMax output for GPT-4o: 4,096 tokens

Total context usage

5000.4% of 128.0K

System tokens0

User tokens0

Output tokens500

Remaining127,500

Related Tools

GPTOpenAI Token CounterNEW

Count tokens for GPT-4o, GPT-4 Turbo, and GPT-3.5 models.

GPTOpenAI API Cost CalculatorNEW

Calculate GPT-4o, GPT-4 Turbo, and GPT-3.5 API costs.

CTXAI Context Window CalculatorNEW

Check if your prompts fit within any AI model context window.

CLDClaude Context Window CalculatorNEW

Calculate token usage against Claude 200K context windows.

FAQ

How large is GPT-4o context window?: GPT-4o and GPT-4o mini both have a 128,000-token context window — roughly 96,000 words or about 200 pages of text. GPT-3.5 Turbo has a smaller 16,000-token window.
Does the system prompt count against the context window?: Yes. Every token in the system prompt, all previous user and assistant messages, and the new user message all count against the context window. Only generated output beyond the context limit gets cut off.
What happens if I exceed the GPT-4o context limit?: OpenAI will return a context_length_exceeded error. You must reduce your prompt length, shorten the conversation history, or switch to a model with a larger context window.

Calculate context window usage for OpenAI GPT models. Enter system prompt, user message, and expected output tokens to see if your request fits within GPT-4o (128K), GPT-4 Turbo (128K), or GPT-3.5 Turbo (16K) limits.