TokenRate

GPT-4o Pricing

Balanced

OpenAI · 128K tokens context

GPT-4o from OpenAI costs $2.50 per 1 million input tokens and $10.00 per 1 million output tokens as of May 2026 (live OpenRouter data). The model supports a 128,000-token context window (approximately 96,000 words) with a 16K-token maximum output. A typical 1,000-token request costs $0.0025 in input charges; a 10,000-token request costs $0.0250.

GPT-4o pricing and capability summary
Input price$2.50 / 1M tokens
Output price$10.00 / 1M tokens
Output / input ratio4.0×
Context window128,000 tokens (~96,000 words)
Maximum output16,384 tokens
Cost per 1K tokens (input)$0.0025
TierBalanced
Last verified

GPT-4o is OpenAI's flagship multimodal model — capable of processing text, images, and audio. It's the default choice for most production OpenAI workloads, balancing cost, speed, and capability.

Live pricing from OpenRouter

Input Price

$2.50

per 1 million tokens

Output Price

$10.00

per 1 million tokens

Context Window

128K tokens

max 16K output

Cost Examples

Request TypeTokensInput CostOutput Cost
1,000 word article1,333$0.00333$0.004
10-page document (2,500 words)3,333$0.00833$0.01
1,000 lines of code5,000$0.0125$0.015
100K token document100,000$0.25$0.30

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

Strengths

  • Native multimodal: text, image, and audio
  • Strong coding and reasoning performance
  • Well-supported with extensive ecosystem
  • Competitive pricing vs GPT-4 Turbo

Limitations

  • 128K context limit (vs 200K for Claude)
  • Output quality can vary on highly complex tasks

Best Use Cases

Multimodal applications (image + text)
Coding assistants
Conversational AI products
Document analysis and summarization

Calculate GPT-4o Costs

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

Open Calculator →

GPT-4o — FAQ

Related Models

Related Guides