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
At a glance
- Input / 1M
- $30
- Output / 1M
- $60
- Context
- 8K
- Max output
- 4K
- Intelligence
- 6.7
- Released
- May 2023
Pricing
GPT-4 API pricing
Per-token rates, plus what common tasks actually cost.
| Input tokensPer 1M tokens | $30 |
|---|---|
| Output tokensPer 1M tokens | $60 |
| Cached input (read)Per 1M tokens | Not available |
| Cache writePer 1M tokens | Not available |
Chat message
2K in, 500 out
$90
per 1,000 requests
Coding task
30K in, 4K out
$1140
per 1,000 requests
Long document summary
150K in, 2K out
$4620
per 1,000 requests
Benchmarks
GPT-4 benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
6.7
Coding index
13.1
Agentic index
Not available
Specs
Context window and capabilities
What it can read, what it can write, and which API features it supports.
- Context window
- 8K tokens
- Max output
- 4K tokens
- Input types
- Text
- Output types
- Text
- Reasoning effort
- Not available
- Release date
- May 28, 2023
- Knowledge cutoff
- September 30, 2021
- Tool calling
- Structured outputs
- JSON mode
- Reasoning
- Temperature
- Stop sequences
- Deterministic seed
- Verbosity control
Compare
GPT-4 vs other models
See how GPT-4 stacks up head to head on price, benchmarks, and features.
VSGPT-4 vs o1
OpenAI vs OpenAI
See comparisonVSGPT-4 vs GPT-4.1
OpenAI vs OpenAI
See comparisonVSGPT-4 vs o1-pro
OpenAI vs OpenAI
See comparisonVS
GPT-4 vs Nova Premier 1.0
OpenAI vs Amazon
See comparisonVSGPT-4 vs GPT-4o (2024-11-20)
OpenAI vs OpenAI
See comparisonVSGPT-4 vs GPT-4o (2024-08-06)
OpenAI vs OpenAI
See comparisonAlternatives
GPT-4 alternatives
Similar models worth considering, and where each one has the edge.
OpenAI
o1
OpenAI
GPT-4.1
Amazon
Nova Premier 1.0
Want to learn about other models? Browse all models
FAQ
Frequently asked questions
How much does GPT-4 cost?
GPT-4 costs $30 per 1M input tokens and $60 per 1M output tokens through the API. A typical chat message costs about $90 per 1,000 messages.
What is the context window of GPT-4?
GPT-4 accepts up to 8K tokens of input and can write up to 4K tokens in a single response.
What is the best alternative to GPT-4?
o1 from OpenAI is a strong alternative. It offers: higher intelligence score, larger 200k context, accepts image and file.
Can I use GPT-4 alongside other models?
Yes. Shortcut Chat sends one prompt to GPT-4 and any other models you pick at the same time, so you can compare answers side by side.
Try GPT-4 next to every other model.
Use GPT-4 alongside all the other models. Use one at a time, or multiple together. Get the best answer from every AI.