OpenAI API pricing
65 OpenAI models, ranked by what your workload would cost per month. Prices as listed on OpenRouter at 22 Nov 2026, 06:52 UTC.
15 of 15 models, sorted by your monthly cost — loading the complete list…
Each row: input / output price, the index where listed, then your monthly cost. Token prices per 1M tokens. Tick up to 4 models to compare.
“Your cost” applies the cache-read price only where the source lists one; a model with no price data shows a dash and is never ranked as cheapest. The quality index is the Intelligence Index, a third-party score by Artificial Analysis relayed by OpenRouter; a dash means none is relayed for that model.
Collected from the OpenRouter models API (476 entries). 104 models are cross-checked against provider list prices in the LiteLLM price table.
OpenAI prices at a glance
- 65 models listed, 65 of them with a paid price. Batch variants are folded into their base model.
- Lowest input price: gpt-oss-20b, at $0.017 per million input tokens and $0.085 per million output tokens.
- Highest input price: GPT-5.4 Pro, at $30.00 input and $180 output per million tokens.
- 52 models publish a cache-read price; the median discount on input is 90% (from 50% to 95%).
- 40 models have a batch variant on OpenRouter, with a median discount of 50% on input.
These are OpenRouter prices. Open a model in the table to see the provider list price recorded by LiteLLM, where there is one, and whether the two differ. To understand the discounts, read the guide to prompt caching and batch pricing.
OpenAI models with their own page
Questions and answers
How many OpenAI models are listed?
65 at the collection of 22 Nov 2026, 06:52 UTC, of which 65 have a paid price on OpenRouter. Batch variants are folded into their base model.
What is the cheapest OpenAI model?
By input price, gpt-oss-20b: $0.017 per million input tokens and $0.085 per million output tokens. Whether it is the cheapest for you depends on your mix of input and output, which is what the table on this page calculates.
What is the most expensive OpenAI model?
By input price, GPT-5.4 Pro: $30.00 per million input tokens and $180 per million output tokens.
Do OpenAI models have cached-input prices?
52 of the 65 listed models publish a cache-read price. The table shows it in the “Cached in” column.
Are these the prices OpenAI charges directly?
They are the prices on OpenRouter. Where LiteLLM records the provider list price for a model, opening the model shows both, and the row is flagged when they differ by more than 1%.
Keep going
- Price tableEvery model and its price, sorted by your monthly bill.
- Cost calculatorYour bill on up to four models, what switching saves and how long a budget lasts.
- Cheapest modelsThe five lowest-cost models in each category.
- Free modelsModels listed at zero price, kept apart from the paid ones.
- Price changesA dated log of every price that went up or down.
- Caching and batch discountsHow the two discounts work and what you save.
- Long-context pricingModels that read very long prompts, and what they charge.
- JSON and RSS dataThe full price file, the change log and the RSS feed, with their units and update times.