GPT-6.1 Sol

New

OpenAIgpt-6.1-sol

Compare input, output and cache prices for GPT-6.1 Sol, calculate request costs, and connect it to your team's tools.

Input$2USD / 1M tokens≤ 272,000 input tokens

Output$10USD / 1M tokens≤ 272,000 input tokens

Cache read$0.1USD / 1M tokens≤ 272,000 input tokens

Cache write$2.5USD / 1M tokens≤ 272,000 input tokens

Cache read savings95%Compared with the input token rate in the same tier.

Compare token prices

Price for 1 million tokens at the selected input length.

Input$2

Output$10

Cache read$0.1

Cache write$2.5

Input tokensOutput tokensCached input tokens

Estimated request cost$0.04

Standard input

Input means uncached tokens. Cached input is added to determine the pricing tier. Cache writes are not included.

USD / 1M tokens

input tokens	Input	Output	Cache read	Cache write
≤ 272,000	$2	$10	$0.1	$2.5
> 272,000	$4	$15	$0.2	$5

The total input length, including cached tokens, selects the prices for the entire request. Output uses the same tier.

Codex

OpenCode

Model access and available credits follow your selected plan. Compare plans