How much does GPT-4o cost?

GPT-4o costs $2.5 per million input tokens and $10 per million output tokens. The blended average is $6.25 per million tokens.

What is the context window of GPT-4o?

GPT-4o supports a context window of 128K tokens (128,000 tokens) and can generate up to 16K output tokens per request.

What is GPT-4o best for?

GPT-4o is best for: General purpose. It supports chat, vision, function_calling, code capabilities.

GPT-4o — Pricing, Benchmarks & Specs

GPT-4o

OpenAIflagship

OpenAI's flagship multimodal model with vision, code generation, and function calling. Excellent all-round performance.

Context Window

128K

tokens

Max Output

16K

tokens

Input Price

$2.5

per 1M tokens

Output Price

$10

per 1M tokens

Speed

109

tokens/sec

Released

May 2024

2024-05-13

Blended Cost

$6.25

per 1M tokens

Value Score

13.6

quality per $

Capabilities

ChatVisionFunction CallingCode Generation

Benchmarks

Quality Index

MMLU Pro

88.7

HumanEval (Coding)

90.2

MATH

76.6

Arena ELO

1285

Pricing History

May 13, 2024$5 / $15(launch)

Oct 1, 2024$2.5 / $10current

Try in Playground Use via Swfte Connect OpenAI Docs

Compare With

Quality: 96·$25.00/1M

GPT-4.1

Quality: 89·$5.00/1M

Claude Opus 4

Quality: 95·$45.00/1M

Gemini 2.5 Pro

Quality: 92·$5.63/1M

About GPT-4o

GPT-4o is a flagship AI model by OpenAI, released on May 13, 2024. It supports a context window of 128K tokens and can generate up to 16K output tokens.

At $2.5 per million input tokens and $10 per million output tokens, its blended cost of $6.25/1M tokens places it in the premium pricing tier. Its value score of 13.6 reflects the balance of quality and cost.

Using GPT-4o with Swfte

Access GPT-4o through Swfte Connect, our unified LLM gateway. Connect gives you a single API for 50+ models, with automatic routing, cost optimization, and fallback handling. You can also try GPT-4o in our AI Playground before integrating.