How to get an OpenAI API key

An OpenAI API key lets apps use OpenAI's GPT models, image generation and speech models under your own OpenAI organization. You pay OpenAI per token, with no app markup. This is separate from a ChatGPT Plus or Pro subscription: the key comes from the OpenAI Platform at platform.openai.com.

Step by step

1. Sign in at platform.openai.com with your OpenAI account, or create one.
2. Add billing. In Settings → Billing, add a payment method and some credit. OpenAI uses pay-as-you-go pricing, and after you add billing it sets an approved usage limit for your organization.
3. Open the API keys page at platform.openai.com/settings/organization/api-keys and create a new secret key.
4. Choose a project and an expiration. OpenAI recommends an expiration date for project keys. Name the key after the app you'll use it in.
5. Copy the key (it starts with sk-) and paste it into the app's settings, usually under Providers → OpenAI.

What it costs

Prices per million tokens on OpenAI's pricing page, 2026-10-23 (standard tier, prompts up to 272K tokens):

Model	Input	Output
gpt-6-astra (flagship)	$10.00	$50.00
gpt-6.1-sol	$2.00	$10.00
gpt-5.6-terra	$2.00	$12.00
gpt-5.4-mini	$0.75	$4.50
gpt-5.6-luna	$0.20	$1.20
gpt-5.4-nano	$0.20	$1.25

For a chat turn of about 2,000 tokens in and 500 out, gpt-5.6-luna costs around $0.001 (about 5,000 turns for $5), gpt-6.1-sol about $0.009, and the flagship gpt-6-astra about $0.045. Most BYOK apps let you pick the model per chat, so you can use a cheap model by default and a bigger one when it matters.

Usage tiers and limits

OpenAI places each organization in a usage tier based on how much credit it has bought in total:

Tier	You qualify after buying	Monthly usage limit
Free	(available in supported countries)	$100
Build	$5	$500
Launch	$100	$5,000
Grow	$500	$200,000

Higher tiers also get higher rate limits. You'll find your tier and limits under Settings → Organization → Limits.

Keep the key and the bill under control

• Spend alerts: set them on the Limits page to get an email when usage passes an amount.
• Hard spend limits stop API traffic once tracked spend reaches the limit. Set one before giving a key to a new app.
• Separate projects (for example "personal apps" and "experiments") can each have their own rate and spend limits.
• Rotate and revoke: create a replacement key, update the app, then revoke the old key. Never paste keys into public code or shared documents.
• Prefer apps that keep the key on your device and call OpenAI directly.