Cache read $0.04 · Input $0.40 · Output $1.20 per 1M tokens, at 87% cache read, 12% input, 1% output
1D
1W
1M
3M
6M
YTD
1Y
0.0%
—
—
—
—
—
—
Compute Futures Prices
Compute Rental Prices
#ModelAs ofShareUSD / 1M tokens
Other Posted Prices
Providers outside the index, such as the hyperscalers: each one's lowest on-demand price per GPU-hour as it posts it, not standardized to the benchmark contract; a price posted in euros is converted at the European Central Bank's rate of the day, with the euro price under it (methodology).
Beam 1.0 501B A23B is a model from Reflection AI. Its posted API price is $0.40 per 1M input tokens, $0.04 per 1M cached input tokens and $1.20 per 1M output tokens, or $0.0948 per 1M tokens at the mix of tokens agents send (87% cache read, 12% input, 1% output). Its price has not changed since Oct 28, 2026. It is not among Reflection AI's models in OpenRouter's daily top 50 today, so it is not in the Reflection AI token price index. At today's H100 rental price of $3.71 per GPU-hour, its break-even throughput is 1,719 tokens per second per GPU at its list price (3 input : 1 output). Prices are collected once a day, for each UTC day.
Cite as: Compute Screener, “Beam 1.0 501B A23B API price”, computescreener.com/models/beam-1-0-501b-a23b. The figures are free to reuse under CC BY 4.0 with credit to Compute Screener.