AI model comparison
GPT-4o (2024-08-06) vs GPT-4
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
OpenAI
GPT-4o (2024-08-06)
The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/).
- Input / 1M
- $2.50
- Output / 1M
- $10
- Context
- 128K
OpenAI
GPT-4
OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning
- Input / 1M
- $30
- Output / 1M
- $60
- Context
- 8K
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
GPT-4o (2024-08-06)
9x cheaper for a typical chat
Higher intelligence score
GPT-4o (2024-08-06)
7.7 vs 6.7 on Artificial Analysis
Larger context window
GPT-4o (2024-08-06)
128K vs 8K tokens
Newer release
GPT-4o (2024-08-06)
Released August 6, 2024
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
GPT-4o (2024-08-06)7.7GPT-46.7Coding index
GPT-4o (2024-08-06)Not availableGPT-413.1Agentic index
GPT-4o (2024-08-06)Not availableGPT-4Not availablePricing
GPT-4o (2024-08-06) vs GPT-4 API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | GPT-4o (2024-08-06) | GPT-4 |
|---|---|---|
| Input tokensPer 1M tokens | $2.50 | $30 |
| Output tokensPer 1M tokens | $10 | $60 |
| Cached input (read)Per 1M tokens | $1.25 | Not available |
| Cache writePer 1M tokens | Not available | Not available |
What it costs in practice
Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.
Chat message
2K in, 500 out
GPT-4o (2024-08-06)$10GPT-4$90Coding task
30K in, 4K out
GPT-4o (2024-08-06)$115$77.50 cachedGPT-4$1140Long document summary
150K in, 2K out
GPT-4o (2024-08-06)$395$207.50 cachedGPT-4$4620Specs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | GPT-4o (2024-08-06) | GPT-4 |
|---|---|---|
| Context window | 128K tokens | 8K tokens |
| Max output | 16K tokens | 4K tokens |
| Input types | File, Image, Text | Text |
| Output types | Text | Text |
| Reasoning effort levels | Not available | Not available |
| Default reasoning effort | Not available | Not available |
| Release date | August 6, 2024 | May 28, 2023 |
Features
Supported features
API features available for each model.
| Metric | GPT-4o (2024-08-06) | GPT-4 |
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Not supported | Not supported |
| Temperature | Supported | Supported |
| Stop sequences | Supported | Supported |
| Deterministic seed | Supported | Supported |
| Verbosity control | Not supported | Not supported |
Keep exploring
More on these models
Other head-to-heads, the full model page, and the alternatives list for each model.
GPT-4o (2024-08-06)View full model details- GPT-4o (2024-08-06) vs GPT-4.1
- GPT-4o (2024-08-06) vs GPT-4.1 Mini
- GPT-4o (2024-08-06) vs o1-pro
- GPT-4o (2024-08-06) vs o3 Mini High
- GPT-4o (2024-08-06) vs Nova Premier 1.0
- GPT-4o (2024-08-06) vs GPT-4o (2024-11-20)
- GPT-4o (2024-08-06) vs Sonar Pro
- GPT-4o (2024-08-06) vs Mistral Large 2407
- GPT-4o (2024-08-06) vs GPT-4o (2024-05-13)
- GPT-4o (2024-08-06) vs GPT-4 Turbo
- GPT-4o (2024-08-06) vs Mistral Large
- GPT-4o (2024-08-06) vs Mixtral 8x22B Instruct
Our take
GPT-4o (2024-08-06) is 9x cheaper for a typical chat. GPT-4o (2024-08-06) scores higher on the Artificial Analysis Intelligence Index (7.7 vs 6.7). GPT-4o (2024-08-06) has the larger context window (128K vs 8K tokens). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.
FAQ
Frequently asked questions
Is GPT-4o (2024-08-06) or GPT-4 cheaper?
GPT-4o (2024-08-06) is cheaper for a typical chat (2K input tokens and 500 output tokens). GPT-4o (2024-08-06) costs $2.50 per 1M input tokens and $10 per 1M output tokens, while GPT-4 costs $30 per 1M input tokens and $60 per 1M output tokens.
Which has a bigger context window, GPT-4o (2024-08-06) or GPT-4?
GPT-4o (2024-08-06) supports up to 128K tokens of context, compared with 8K for GPT-4.
Is GPT-4o (2024-08-06) smarter than GPT-4?
On the Artificial Analysis Intelligence Index, GPT-4o (2024-08-06) scores 7.7 and GPT-4 scores 6.7, putting GPT-4o (2024-08-06) ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use GPT-4o (2024-08-06) and GPT-4 at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see GPT-4o (2024-08-06) and GPT-4 answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to GPT-4o (2024-08-06) and GPT-4 at the same time. Compare the answers side by side and keep the best one.