OpenAI: GPT-4

OpenAI: GPT-4

openai · Released May 28, 2023 Professional
Intelligence #10 / 565
82.0 Our Score
Speed #245 / 266
37.5 tokens / sec
Input #565 / 571
$30.00 per 1M tokens
Output #557 / 571
$60.00 per 1M tokens
Context #439 / 571
8,191 tokens

Analysis Summary

Built by OpenAI, OpenAI: GPT-4 belongs to the GPT-4 family. It was released in May 2023. We place it in the Professional tier, where it sits at #10 of 565 models overall. For raw reasoning ability it ranks #266 of 374, putting it in the broader field for overall intelligence.

On coding it ranks #206 of 311, a reasonable fit for everyday development support. Its 8K-token context window is larger than 23% of the models we list, suiting long documents, large codebases, and retrieval-heavy workloads. It supports tool use and function calling.

At $30.00 input and $60.00 output per 1M tokens, OpenAI: GPT-4 is among the most expensive options we list, so it is best reserved for high-value work where answer quality matters more than per-token cost. OpenAI: GPT-4 is a dependable pick for businesses that need strong, well-rounded performance without paying frontier prices.

Editorial notes

Original GPT-4 benchmarks show limited capability by current standards, with an 8K context window and $30/1M input pricing that makes it a poor choice versus modern models.

Assessed May 31, 2026

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence1.8Technical2.3Value4.3Content0
Intelligence 1.8/10
Technical 2.3/10
Content 0/10
Value 4.3/10

How OpenAI: GPT-4 compares

OpenAI: GPT-4 ranks #266 of 374 AI models we track for overall intelligence, #206 of 311 for coding. Its 8K-token context window is larger than 23% of the models we list. At $30.00 per million input tokens it is cheaper than 1% of comparable models.

About 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..

Capabilities

Tool Use Function Calling

Performance Indices

Source: Artificial Analysis

12.8 Intelligence Index
13.1 Coding Index

How does OpenAI: GPT-4 stack up?

Compare side-by-side with other professional models.

Compare Models

Model Information

OpenRouter ID openai/gpt-4
Provideropenai
Model FamilyGPT-4
Release Date May 28, 2023
Context Length8,191 tokens
Max Completion4,096 tokens
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $30.00 $0.030000
Output $60.00 $0.060000

Live Performance

Live endpoint metrics, refreshed every 30 minutes.

304ms
Best Latency (TTFT)
12 tok/s
Best Throughput
0/2
Active Endpoints
Available via: OpenAI, Azure

Frequently asked questions about OpenAI: GPT-4

How much does OpenAI: GPT-4 cost?

OpenAI: GPT-4 costs $30.00 per million input tokens and $60.00 per million output tokens.

What is the context window of OpenAI: GPT-4?

OpenAI: GPT-4 has a context window of 8,191 tokens (8K).

Is OpenAI: GPT-4 good for coding?

On our coding benchmark index, OpenAI: GPT-4 ranks #206 of 311 models, placing it in the broader range of the field for code generation and debugging.

What can OpenAI: GPT-4 do?

OpenAI: GPT-4 supports tool use and function calling.

Who created OpenAI: GPT-4?

OpenAI: GPT-4 is developed by OpenAI and was released on May 28, 2023.