Skip to content

GPT-4o (2024-05-13) vs GPT-5.5

GPT-4o (2024-05-13) (OpenAI) and GPT-5.5 (OpenAI) are listed at different prices. GPT-4o (2024-05-13) costs less: $5.00 per 1M input tokens and $15.00 per 1M output tokens, against $5.00 and $30.00 for GPT-5.5. GPT-5.5 has the larger context window, 1,050,000 tokens against 128,000 for GPT-4o (2024-05-13). GPT-5.5 charges $10.00 and $45.00 per 1M once a prompt passes 272,000 tokens; GPT-4o (2024-05-13) keeps one price across its window. Both accept text, images and files and produce text.

OpenAI: GPT-4o (2024-05-13) and OpenAI: GPT-5.5 both accept text, images, and files and produce text. GPT-4o has a 128,000-token context and 4,096-token output limit, while GPT-5.5 has a 1,050,000-token context and 128,000-token output limit; their listed additional support includes web search options for GPT-4o and reasoning for GPT-5.5.

Compared from catalog data checked

GPT-4o (2024-05-13)

$5.00 in
$15.00 out
128K context

GPT-5.5

$5.00 in
$30.00 out
1.05M context

Side by side

0.00 the better figure in a row
GPT-4o (2024-05-13) and GPT-5.5 specifications side by side
SpecificationGPT-4o (2024-05-13)GPT-5.5
Maker OpenAI OpenAI
Added to catalog 13 May 2024 24 Apr 2026
Input, per 1M tokens $5.00 $5.00
Output, per 1M tokens $15.00 $30.00
Input above 272K tokensPer 1M; long prompts n/a $10.00
Output above 272K tokens n/a $45.00
Cached input read, per 1M n/a $0.50
Context windowTokens 128,000 1,050,000
Max outputTokens 4,096 128,000
Accepts file, image, text file, image, text
Produces text text
Tool calling Yes Yes
Structured outputs Yes Yes
Reasoning effort control No Yes

List prices through OpenRouter, in US dollars. Each model's page has its variants, price history and sample outputs.

What the same task costs

List price for one request, from the token counts shown. The same four tasks are priced on every model page.

Check the provider's pageToken counts are estimates, and the two models count tokens differently.
Cost of the same task on GPT-4o (2024-05-13) and GPT-5.5
TaskGPT-4o (2024-05-13)GPT-5.5
Answer a short question500 in / 300 out $0.0070 $0.012
Summarise a 50-page PDF25,000 in / 800 out $0.137 $0.149
Review a 2,000-line source file30,000 in / 2,000 out $0.180 $0.210
Read a 300-page contract set150,000 in / 1,500 out $0.773 $0.795

Which to choose

Choose GPT-4o (2024-05-13) if

  • Output tokens cost less: $15.00 against $30.00 per 1M
GPT-4o (2024-05-13) details

Choose GPT-5.5 if

  • Cached input costs less: $0.50 against n/a per 1M
  • You need the larger context window: 1,050,000 tokens against 128,000
  • You need longer answers in one response: 128,000 tokens against 4,096
  • You want to set how much it reasons before it answers
GPT-5.5 details

Neither maker's quality claims are repeated here. The reliable test is your own task: ask both the same question and read the two answers.

Comparison questions

Is GPT-4o (2024-05-13) cheaper than GPT-5.5?

Yes, GPT-4o (2024-05-13) is the cheaper of the two. GPT-4o (2024-05-13) costs $5.00 per 1M input tokens and $15.00 per 1M output tokens; GPT-5.5 costs $5.00 and $30.00 as checked on 22 Nov 2026.

Which has the larger context window, GPT-4o (2024-05-13) or GPT-5.5?

GPT-5.5, at 1,050,000 tokens against 128,000 for GPT-4o (2024-05-13).

Which is better for coding, GPT-4o (2024-05-13) or GPT-5.5?

This page does not rank models on quality, and it does not repeat either maker's claims. The table shows what each accepts, supports and costs; the reliable test is your own task: give both the same piece of code and compare the answers.

Can I use both GPT-4o (2024-05-13) and GPT-5.5?

Neither is offered in the Upend chat today. Both are listed in the catalog through OpenRouter, with the figures shown here.

Find the model for your task.

Every comparison is computed from the live catalog.

Sign in to Upend

Use an account you already have, or get a one-time code by email.

Use a password instead

For accounts that already have a password. Forgotten it? An emailed code signs you in just the same.