TokenRate

GPT-4 Pricing

Flagship

OpenAI · 8K tokens context

GPT-4 from OpenAI costs $30.00 per 1 million input tokens and $60.00 per 1 million output tokens as of June 2026 (live OpenRouter data). The model supports a 8,191-token context window (approximately 6,143 words) with a 4K-token maximum output. A typical 1,000-token request costs $0.0300 in input charges; a 10,000-token request costs $0.3000.

GPT-4 pricing and capability summary
Input price$30.00 / 1M tokens
Output price$60.00 / 1M tokens
Output / input ratio2.0×
Context window8,191 tokens (~6,143 words)
Maximum output4,096 tokens
Cost per 1K tokens (input)$0.0300
TierFlagship
Last verified

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...

Live pricing from OpenRouter

Input Price

$30.00

per 1 million tokens

Output Price

$60.00

per 1 million tokens

Context Window

8K tokens

max 4K output

Cost Examples

Request TypeTokensInput CostOutput Cost
1,000 word article1,333$0.04$0.024
10-page document (2,500 words)3,333$0.10$0.06
1,000 lines of code5,000$0.15$0.09
100K token document100,000$3.00$1.80

Output cost estimated at 30% of input token count. Use the calculator for exact figures.

Strengths

  • Frontier-class quality on complex tasks
  • Strong general-purpose performance
  • Strong general-purpose performance

Limitations

  • Premium pricing — overkill for simple tasks
  • Smaller 8K-token context limits long-document use

Best Use Cases

Complex research and analysis
Advanced coding and architecture
Long-form content generation
High-stakes production workloads

Calculate GPT-4 Costs

Use the TokenRate calculator to convert any budget, token count, or text into exact GPT-4 costs — and compare across all models.

Open Calculator →

GPT-4 — FAQ

Related Models

Related Guides