Verified 2025-09-22 · sourced from OpenAI
GPT-4o Pricing Calculator: Official OpenAI API Cost for 1K, 100K & 1M Tokens
Use this GPT-4o pricing calculator to verify official current OpenAI API pricing per 1M tokens, check the latest $2.50 input / $10 output rates, estimate 1K, 100K, and 1M token spend, confirm the 128K context window, and compare GPT-4o with GPT-4.1, GPT-4o mini, GPT-5 mini, or Claude Sonnet 4 before you ship production chat, vision, and multimodal workflows.
Quick answer: GPT-4o pricing per 1M tokens is $2.50 input and $10.00 output. Context window: 128,000 tokens · Cached input: $1.250 / 1M.
Best for searches like GPT-4o pricing, official GPT-4o pricing, GPT-4o token calculator, GPT-4o pricing calculator, GPT-4o API pricing, current GPT-4o API price per million tokens, GPT-4o API cost, GPT-4o cost per 1000 tokens, GPT-4o price per 1K tokens, GPT-4o input token price, GPT-4o output token price, GPT-4o token cost, GPT-4o token price, GPT-4o cost per 100K tokens, GPT-4o 128K context window, GPT-4o 100K token cost, GPT-4o 1M token cost, GPT-4o vs GPT-4.1 pricing.
Pick the route that matches what you searched for
Some visitors want a fast GPT-4o API cost estimate, others want a direct 100K or 1M token budget, and some are already comparing alternatives. These shortcuts remove the extra click.
Estimate a single request or prompt budget right now.
Jump straight to the most common budgeting checkpoint.
Use this when you are sizing production traffic or a monthly plan.
Open the closest head-to-head comparison instead of researching from scratch.
Context window
128,000 tokens
Input price
$2.50 / 1M
Output price
$10.00 / 1M
Cached input
$1.250 / 1M
Usage scenarios
Compare standard and cached pricing (where available) across common workloads.
| Scenario | Tokens in | Tokens out | Total tokens | Standard cost | Cached cost |
|---|---|---|---|---|---|
Quick chat reply Single user question with a short assistant answer | 650 | 220 | 870 | $0.0038 | $0.0030 |
Coding assistant session Multi-turn pair programming exchange (≈6 turns) | 2,600 | 1,400 | 4,000 | $0.0205 | $0.0173 |
Knowledge base response Retrieval-augmented answer referencing multiple passages | 12,000 | 3,000 | 15,000 | $0.0600 | $0.0450 |
Near-max context run Large document processing approaching the 128K token limit | 112,000 | 16,000 | 128,000 | $0.440 | $0.300 |
Daily & monthly budgeting
Translate usage into predictable operating expenses across popular deployment sizes.
| Profile | Requests/day | Tokens/day | Daily cost | Monthly cost | Cached daily | Cached monthly |
|---|---|---|---|---|---|---|
| Team pilot | 25 | 75,000 | $0.375 | $11.25 | $0.313 | $9.38 |
| Product launch | 100 | 500,000 | $2.38 | $71.25 | $1.94 | $58.13 |
| Enterprise scale | 500 | 3,000,000 | $15.00 | $450.00 | $12.50 | $375.00 |
Pricing notes
- Primary multimodal flagship with audio, vision, and text support.
- Values reflect base pricing per 1M tokens: input $2.50, output $10.00, cache $1.25.
Frequently asked questions
How much does GPT-4o cost per 1,000 tokens?
At the published rates of $2.50 per million input tokens and $10.00 per million output tokens, a typical 1,000 token request (≈70% input, 30% output) costs about $0.0047.
Does GPT-4o offer cached input discounts?
GPT-4o drops input costs to $1.250 per million cached tokens. Using cached contexts, that same 1,000 token call totals $0.0039, a significant saving for chatbots and RAG systems.
What is the context window for GPT-4o?
GPT-4o supports up to 128,000 tokens (128K), allowing large prompts and retrieval-augmented payloads in a single call.
How fresh is the GPT-4o pricing data?
Pricing is sourced from https://platform.openai.com/docs/pricing and was last verified on 2025-09-22. The calculator updates automatically when models.json is refreshed.
What is GPT-4o pricing per 1M tokens?
GPT-4o is currently priced at $2.50 per million input tokens and $10.00 per million output tokens. If you use prompt caching, cached input is billed at $1.25 per million tokens.
How much does 100K GPT-4o tokens cost?
Using the official GPT-4o API rate, 100K input tokens cost about $0.250, 100K cached input tokens cost about $0.125, and 100K output tokens cost about $1.00. That quick budget check is useful when you are sizing multimodal chat, agent, or vision-heavy production flows before launch.
Does GPT-4o have a 128K context window?
Yes. GPT-4o supports a 128,000-token (128K) context window, so you can send long prompts, larger retrieved context, or multi-turn chat state without immediately moving to a separate long-context model.
Is GPT-4o cheaper than GPT-4.1 for multimodal apps?
GPT-4o is often chosen for production chat, vision, and multimodal workloads when teams want a strong balance of quality, latency, and cost. This page helps you compare GPT-4o directly with GPT-4.1, GPT-4o mini, and GPT-5 mini before you commit budget.