modelgrep
O

OpenAI: GPT-4

openai/gpt-4

ToolsJSON
Use via OpenRouter ↗
Intelligence
Design Elo
Speed
20
264th fastest
Latency
371ms
first token
Input price
$30.00
297th cheapest
Context
8K
4K max out

How it compares

Faster than11%
of all ranked models
Cheaper than0%
of all ranked models

Overview

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...

Benchmarks

independent · via OpenRouter
Artificial Analysis
Coding Index
13.1

Providers & pricing (2)

ProviderIn $/MOut $/MUptime
OpenAI$30.00$60.00
Azure$30.00$60.00

Specifications

Context window8K
Max output4K
Knowledge cutoffSep 2021
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price
ModeratedYes

GPT-4 FAQ

How much does GPT-4 cost?

GPT-4 costs $30.00 per million input tokens and $60.00 per million output tokens via OpenRouter, making it 297th cheapest of 298 paid models.

How fast is GPT-4?

GPT-4 generates around 20 tokens per second with 371ms time-to-first-token (p50), the 264th fastest tracked model.

What is GPT-4's context window?

GPT-4 supports a 8K-token context window and can output up to 4K tokens. It accepts text input.

Compare head-to-head