Provider pricing guide

OpenAI API Pricing Calculator & Model Cost Guide

OpenAI billing depends on the model and modality. Text models normally separate input, cached input, and output tokens, while image and transcription products use different units. The table below keeps those units explicit.

Open OpenAI cost calculator

ProviderModality

Example comparison basis: 1M input tokens + 1M output tokens. This is a rate comparison, not a quality or capability ranking.

AI model pricing comparison filtered by provider and modality
Provider / model	Input	Output	Cached / batch	Unit price	Example cost	Verified / source	Use
OpenAI GPT-4.1 mini Cheapest	$0.40 / 1M	$1.60 / 1M	$0.10 cache	—	$2.00	Verified Jun 21, 2026 OpenAI model pricing	Calculate
OpenAI GPT-4.1 Highest	$2.00 / 1M	$8.00 / 1M	$0.50 cache	—	$10.00	Verified Jun 21, 2026 OpenAI model pricing	Calculate

Pricing FAQ

How is OpenAI API text pricing calculated?

Multiply input tokens by the model input rate and output tokens by the output rate, each divided by one million. Add both values and multiply by request volume.

Does cached input use the standard input rate?

Eligible cache hits can use a lower published rate. Cache writes, retention, and eligibility rules vary, so confirm the linked OpenAI documentation.

Are image and transcription rates token based?

Not always. TokenMath displays the provider's published planning unit, such as per image or estimated per audio minute, alongside the source date.

Related comparisons

OpenAI vs Anthropic API Cost Comparison

Compare representative OpenAI and Anthropic API model costs for the same text workload and monthly request volume.

Open

OpenAI vs Gemini API Cost Comparison

Compare representative OpenAI and Gemini API costs for 1,000 input tokens, 300 output tokens, and 10,000 monthly requests.

Open

Related glossary terms

Input tokens

Input tokens are the tokenized units sent to a model, including instructions, user content, conversation history, retrieved context, and tool definitions.

Open

Output tokens

Output tokens are the tokenized units generated by a language model, including visible responses and any billable reasoning or thinking tokens defined by the provider.

Open

Cached tokens

Cached tokens are repeated prompt tokens that qualify for a provider's prompt-caching mechanism and may use a separate cache-hit rate.

Open