Skip to main content
OpenAI

API Pricing

Contact sales

Our latest models

Reasoning models for complex, multi-step problems

OpenAI o3

Our most powerful reasoning model with leading performance on coding, math, science, and vision

Price

Input:
$10.00 / 1M tokens
Cached input:
$2.50 / 1M tokens
Output:
$40.00 / 1M tokens

OpenAI o4-mini

Our faster, cost-efficient reasoning model delivering strong performance on math, coding and vision

Price

Input:
$1.100 / 1M tokens
Cached input:
$0.275 / 1M tokens
Output:
$4.400 / 1M tokens

Save 50% on inputs and outputs with the Batch API⁠(opens in a new window) and run tasks asynchronously over 24 hours.

GPT models for everyday tasks

GPT-4.1

Smartest model for complex tasks

Price

Input:
$2.00 / 1M tokens
Cached input:
$0.50 / 1M tokens
Output:
$8.00 / 1M tokens

GPT-4.1 mini

Affordable model balancing speed and intelligence

Price

Input:
$0.40 / 1M tokens
Cached input:
$0.10 / 1M tokens
Output:
$1.60 / 1M tokens

GPT-4.1 nano

Fastest, most cost-effective model for low-latency tasks

Pricing

Input:
$0.100 / 1M tokens
Cached input:
$0.025 / 1M tokens
Output:
$0.400 / 1M tokens

Save 50% on inputs and outputs with the Batch API⁠(opens in a new window) 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-4.1

Fine-tuning price

Input:
$3.00 / 1M tokens
Cached input:
$0.75 / 1M tokens
Output:
$12.00 / 1M tokens
Training:
$25.00 / 1M tokens

GPT-4.1 mini

Fine-tuning price

Input:
$0.80 / 1M tokens
Cached input:
$0.20 / 1M tokens
Output:
$3.20 / 1M tokens
Training:
$5.00 / 1M tokens

GPT-4o

Fine-tuning price

Input:
$3.750 / 1M tokens
Cached input:
$1.875 / 1M tokens
Output:
$15.000 / 1M tokens
Training:
$25.000 / 1M tokens

GPT-4o mini

Fine-tuning price

Input:
$0.30 / 1M tokens
Cached input:
$0.15 / 1M tokens
Output:
$1.20 / 1M tokens
Training:
$3.00 / 1M tokens

You can also fine-tune our legacy models⁠(opens in a new window).

Our APIs

Realtime API

Build low-latency, multimodal experiences including speech-to-speech.

GPT-4o
$5.00 / 1M input tokens
$2.50 / 1M cached input tokens
$20.00 / 1M output tokens
GPT-4o mini
$0.60 / 1M input tokens
$0.30 / 1M cached input tokens
$2.40 / 1M output tokens

Image Generation API

Precise, high-fidelity image generation and editing with our latest multimodal model.

GPT-image-1
$5.00 / 1M input tokens
-
GPT-image-1
$10.00 / 1M input tokens
$40.00 / 1M output tokens
Prompts are billed similarly to other GPT models. Image outputs cost approximately $0.01 (low), $0.04 (medium), and $0.17 (high) for square images. For detailed token usage by image quality and size, see the docs.

Responses API

Our newest API combining the simplicity of Chat Completions with the built-in tool use of Assistants.

Price
Responses API is not priced separately. Tokens are billed at the chosen language model’s input and output rates.

Chat Completions API

Build text-based conversational experiences.

Price
Chat Completions API is not priced separately. Tokens are billed at the chosen language model's input and output rates.

Assistants API

Build assistant-like experiences with our tools.

Price
Assistants API is not priced separately. Tokens are billed at the chosen language model's input and output rates.

Built-in tools

Extend model capabilities with built-in tools in the API Platform

Code Interpreter
$0.03
File Search Storage
$0.10 / GB of vector storage per day (first GB free)
File Search Tool Call (Responses API only)
$2.50 / 1k tool calls
Web Search Tool Call
Web search tool pricing is inclusive of tokens used to synthesize information from the web. Pricing depends on model and search context size. See below.
gpt-4o, gpt-4.1, and gpt-4o-search-preview
search_context_size low:
$30.00 / 1K calls
search_context_size medium (default):
$35.00 / 1K calls
search_context_size high:
$50.00 / 1K calls
gpt-4o-mini, gpt-4.1-mini, and gpt-4o-mini-search-preview
search_context_size low:
$25.00 / 1K calls
search_context_size medium (default):
$27.50 / 1K calls
search_context_size high:
$30.00 / 1K calls
The billing dashboard will report these line items as ‘web search tool calls | gpt-4o’ and ‘web search tool calls | gpt-4o-mini’
GB refers to binary gigabytes of storage (also known as gibibyte), where 1GB is 2^30 bytes.

Explore our offerings for Enterprise customers: Scale Tier⁠ and Reserved Capacity⁠.

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(opens in a new window) to explore which models provide the best price performance trade-off for your usage.

Start creating with OpenAI’s powerful models.

Get startedContact sales
close