openai Vision

GPT-4o pricing & benchmarks

Released May 13, 2024 · served by 2 providers

Input / 1M tokens$2.50
Output / 1M tokens$10.00
Context window128K
Cached input$1.25
1M in + 300K out$5.50

What GPT-4o is

GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...

Providers and prices for GPT-4o

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
Azurecheapest $2.50 $10.00 128K 99.9%
OpenAI $2.50 $10.00 128K 100.0%

GPT-4o benchmark results

Design Arena head-to-head results, as reported through the OpenRouter model API.

CategoryArenaRankEloWin rate
3d models #100 926 39.2%
gamedev models #104 962 42.3%
uicomponent models #104 923 38.1%
dataviz models #109 887 36%
codecategories models #112 891 34.8%
website models #117 856 31.5%

FAQ

How much does the GPT-4o API cost?

$2.50 per 1M input tokens and $10.00 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $5.50.

Is GPT-4o free?

No. It is a paid model starting at $2.50 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for GPT-4o?

Azure at $2.50 input / $10.00 output per 1M tokens.

Can I self-host GPT-4o?

No. GPT-4o is closed-weight and only available through hosted APIs.