API Pricing
Our latest models
Reasoning models for complex, multi-step problems
OpenAI o1
Frontier reasoning model that supports tools, Structured Outputs, and vision | 200k context length
Price
$15.00 / 100万トークン
$7.50 / 100万トークン
$60.00 / 100万トークン
OpenAI o3-mini
Small cost-efficient reasoning model that’s optimized for coding, math, and science, and supports tools and Structured Outputs | 200k context length
Price
$1.10 / 100万トークン
$0.55 / 100万トークン
$4.40 / 100万トークン
Save 50% on inputs and outputs with the Batch API(新しいウィンドウで開く) and run tasks asynchronously over 24 hours.
GPT models for everyday tasks
GPT-4o
High-intelligence model for complex tasks | 128k context length
Price
$2.50 / 100万トークン
$1.25 / 100万トークン
$10.00 / 100万トークン
GPT-4o mini
Affordable small model for fast, everyday tasks | 128k context length
Price
$0.150 / 100万トークン
$0.075 / 100万トークン
$0.600 / 100万トークン
Save 50% on inputs and outputs with the Batch API(新しいウィンドウで開く) and run tasks asynchronously over 24 hours.
Fine-tuning our models
Customize our models to get even higher performance for your specific use cases.
GPT-4o
Fine-tuning price
$3.750 / 100万トークン
$1.875 / 100万トークン
$15.000 / 100万トークン
$25.000 / 100万トークン
GPT-4o mini
Fine-tuning price
$0.30 / 100万トークン
$0.15 / 100万トークン
$1.20 / 100万トークン
$3.00 / 100万トークン
You can also fine-tune our legacy models(新しいウィンドウで開く).
Our APIs
Realtime API
Build low-latency, multimodal experiences including speech-to-speech.
Assistants API
Build assistant-like experiences with our tools.
Chat Completions API
Build text-based conversational experiences.
FAQ
We recommend that developers use GPT-4o or GPT-4o mini for everyday tasks. GPT-4o generally performs better on a wide range of tasks, while GPT-4o mini is fast and inexpensive for simpler tasks. Our o1 reasoning models are ideal for complex, multi-step tasks and STEM use cases that require deep thinking about tough problems. We recommend experimenting with all of these models in the Playground(新しいウィンドウで開く) to explore which models provide the best price performance trade-off for your usage.