BAD SKY.NET

OpenAI API Pricing

Compare input and output token prices across AI language models.

ProviderModel
Input
per 1M tokens
Output
per 1M tokens
OpenAIOpenAIGPT-OSS-20BOpen weights$0.03$0.14View
OpenAIOpenAIGPT-OSS-120BOpen weights$0.04$0.16View
OpenAIOpenAIGPT-5 Nano$0.05$0.40View
OpenAIOpenAIGPT-6 Luna$0.10$0.50View
OpenAIOpenAIGPT-4o Mini$0.15$0.60View
OpenAIOpenAIGPT-5.6 Luna$0.20$1.20View
OpenAIOpenAIGPT-5.4 Nano$0.20$1.25View
OpenAIOpenAIGPT-5 Mini$0.25$2.00View
OpenAIOpenAIGPT-4.1 Mini$0.40$1.60View
OpenAIOpenAIGPT-5.4 Mini$0.75$4.50View
OpenAIOpenAIGPT-6.1 Terra$1.00$5.00View
OpenAIOpenAIGPT-5$1.25$10.00View
OpenAIOpenAIGPT-5.1$1.25$10.00View
OpenAIOpenAIGPT-5.2$1.75$14.00View
OpenAIOpenAIGPT-5.3-Codex$1.75$14.00View
OpenAIOpenAIGPT-4.1$2.00$8.00View
OpenAIOpenAIo3$2.00$8.00View
OpenAIOpenAIGPT-6 Sol$2.00$10.00View
OpenAIOpenAIGPT-6.1 Sol$2.00$10.00View
OpenAIOpenAIGPT-5.6 Sol$2.00$10.00View
OpenAIOpenAIGPT-5.6 Terra$2.00$12.00View
OpenAIOpenAIGPT-4o$2.50$10.00View
OpenAIOpenAIGPT-5.4$2.50$15.00View
OpenAIOpenAIGPT-5.5$5.00$30.00View
OpenAIOpenAIGPT-6 Astra$10.00$50.00View
OpenAIOpenAIGPT-5 Pro$15.00$120.00View
OpenAIOpenAIo3-pro$20.00$80.00View
OpenAIOpenAIGPT-5.2 Pro$21.00$168.00View
OpenAIOpenAIGPT-5.5 Pro$30.00$180.00View
OpenAIOpenAIGPT-5.4 Pro$30.00$180.00View

OpenAI API cost calculator

Enter the tokens of a typical request to compare what it costs with every model in the table. Not sure how many tokens your prompt has? Paste it into the token calculator.

ModelPer requestPer month
GPT-OSS-20B (open weights, third-party host)$0.00013$1.30
GPT-OSS-120B (open weights, third-party host)$0.00016$1.57
GPT-5 Nano $0.0003$3.00
GPT-6 Luna $0.00045$4.50
GPT-4o Mini $0.0006$6.00
GPT-5.6 Luna $0.001$10.00
GPT-5.4 Nano $0.001$10.25
GPT-5 Mini $0.0015$15.00
GPT-4.1 Mini $0.0016$16.00
GPT-5.4 Mini $0.0037$37.50

How OpenAI API pricing works

The OpenAI API is billed per token, with separate prices for input tokens (your prompt, system message, and files) and output tokens (the generated answer, including reasoning tokens for reasoning models). Prices in the table are standard pay-as-you-go rates per 1 million tokens; a token is roughly three quarters of an English word.

Smaller models such as the mini and nano variants cost a fraction of the flagship models and are a good default for classification, extraction, and chat. Reasoning and pro models cost much more per token and also produce more output tokens, so test whether your task really needs them.

OpenAI also discounts batch requests and cached prompt tokens, which can lower the bill for repeated system prompts and offline jobs; the table shows standard on-demand prices.

FAQ

How much does the OpenAI API cost?

As of November 17, 2026, OpenAI charges from $0.05 to $30.00 per 1M input tokens and from $0.40 to $180.00 per 1M output tokens across the 28 models in the table above. OpenAI also publishes 2 open-weight models that you run on your own hardware or through third-party hosts, so their price depends on the host.

What is the cheapest OpenAI model?

GPT-5 Nano, at $0.05 per 1M input tokens and $0.40 per 1M output tokens. A request with 2,000 input and 500 output tokens costs about $0.0003 with it, so 1,000 such requests cost $0.30.

What is the most expensive OpenAI model?

GPT-5.5 Pro, at $30.00 per 1M input tokens and $180.00 per 1M output tokens. The same 2,000 input and 500 output token request costs about $0.15, so pick the smallest model that handles your task well.

Which OpenAI model has the largest context window?

GPT-6 Luna accepts up to 1.05M tokens of context. Long prompts are billed as input tokens, so filling the whole window costs about $0.11 per request.

Is OpenAI cheaper than other LLM APIs?

Not at the low end: Qwen3.7-Flash costs $0.03 per 1M input tokens and $0.13 per 1M output tokens, less than any OpenAI model. Price is only part of the choice, so compare quality and context window as well in the LLM price comparison.

How do I estimate the cost of my prompts?

Count the tokens of a typical prompt and answer with the token calculator, then enter them in the cost calculator above to see the price per request and per month for every OpenAI model.