The modelled monthly GPU rent for Llama-3.1-8B-Instruct using 3 replicas of 1 x NVIDIA H100 PCIe 80 GB is $4,361.09 at 50,000 requests/day.

Scroll horizontally to read every volume point.

500 requests per day, 7,609,375 output tokens per month: self-host $1,453.70, cheapest comparable API $0.46. 1,500 requests per day, 22,828,125 output tokens per month: self-host $1,453.70, cheapest comparable API $1.37. 5,000 requests per day, 76,093,750 output tokens per month: self-host $1,453.70, cheapest comparable API $4.57. 15,000 requests per day, 228,281,250 output tokens per month: self-host $1,453.70, cheapest comparable API $13.70. 21,247 requests per day, 323,355,931 output tokens per month: self-host $1,453.70, cheapest comparable API $19.40. 21,676 requests per day, 329,888,374 output tokens per month: self-host $2,907.39, cheapest comparable API $19.79. 50,000 requests per day, 760,937,500 output tokens per month: self-host $4,361.09, cheapest comparable API $45.66. 150,000 requests per day, 2,282,812,500 output tokens per month: self-host $10,175.87, cheapest comparable API $136.97. 500,000 requests per day, 7,609,375,000 output tokens per month: self-host $34,888.68, cheapest comparable API $456.56. 1,500,000 requests per day, 22,828,125,000 output tokens per month: self-host $101,758.65, cheapest comparable API $1,369.69. 5,000,000 requests per day, 76,093,750,000 output tokens per month: self-host $338,710.94, cheapest comparable API $4,565.63.

Scroll horizontally to read every chart label and value.

Busy GPU-hours: 1,701.9, Engine-reported share doing token work. Idle GPU-hours billed: 489.6, Engine-reported share paid while idle.

Scroll horizontally to read every volume point.

500 requests per day, 7,609,375 output tokens per month: self-host $1,453.70, cheapest comparable API $0.46. 1,500 requests per day, 22,828,125 output tokens per month: self-host $1,453.70, cheapest comparable API $1.37. 5,000 requests per day, 76,093,750 output tokens per month: self-host $1,453.70, cheapest comparable API $4.57. 15,000 requests per day, 228,281,250 output tokens per month: self-host $1,453.70, cheapest comparable API $13.70. 21,247 requests per day, 323,355,931 output tokens per month: self-host $1,453.70, cheapest comparable API $19.40. 21,676 requests per day, 329,888,374 output tokens per month: self-host $2,907.39, cheapest comparable API $19.79. 50,000 requests per day, 760,937,500 output tokens per month: self-host $4,361.09, cheapest comparable API $45.66. 150,000 requests per day, 2,282,812,500 output tokens per month: self-host $10,175.87, cheapest comparable API $136.97. 500,000 requests per day, 7,609,375,000 output tokens per month: self-host $34,888.68, cheapest comparable API $456.56. 1,500,000 requests per day, 22,828,125,000 output tokens per month: self-host $101,758.65, cheapest comparable API $1,369.69. 5,000,000 requests per day, 76,093,750,000 output tokens per month: self-host $338,710.94, cheapest comparable API $4,565.63.

Scroll horizontally to read every chart label and value.

Busy GPU-hours: 1,701.9, Engine-reported share doing token work. Idle GPU-hours billed: 489.6, Engine-reported share paid while idle.

Scroll horizontally to read every volume point.

500 requests per day, 7,609,375 output tokens per month: self-host $1,453.70, cheapest comparable API $0.46. 1,500 requests per day, 22,828,125 output tokens per month: self-host $1,453.70, cheapest comparable API $1.37. 5,000 requests per day, 76,093,750 output tokens per month: self-host $1,453.70, cheapest comparable API $4.57. 15,000 requests per day, 228,281,250 output tokens per month: self-host $1,453.70, cheapest comparable API $13.70. 21,247 requests per day, 323,355,931 output tokens per month: self-host $1,453.70, cheapest comparable API $19.40. 21,676 requests per day, 329,888,374 output tokens per month: self-host $2,907.39, cheapest comparable API $19.79. 50,000 requests per day, 760,937,500 output tokens per month: self-host $4,361.09, cheapest comparable API $45.66. 150,000 requests per day, 2,282,812,500 output tokens per month: self-host $10,175.87, cheapest comparable API $136.97. 500,000 requests per day, 7,609,375,000 output tokens per month: self-host $34,888.68, cheapest comparable API $456.56. 1,500,000 requests per day, 22,828,125,000 output tokens per month: self-host $101,758.65, cheapest comparable API $1,369.69. 5,000,000 requests per day, 76,093,750,000 output tokens per month: self-host $338,710.94, cheapest comparable API $4,565.63.

Scroll horizontally to read every chart label and value.

Busy GPU-hours: 1,701.9, Engine-reported share doing token work. Idle GPU-hours billed: 489.6, Engine-reported share paid while idle.

Scroll horizontally to read every volume point.

500 requests per day, 7,609,375 output tokens per month: self-host $1,453.70, cheapest comparable API $0.46. 1,500 requests per day, 22,828,125 output tokens per month: self-host $1,453.70, cheapest comparable API $1.37. 5,000 requests per day, 76,093,750 output tokens per month: self-host $1,453.70, cheapest comparable API $4.57. 15,000 requests per day, 228,281,250 output tokens per month: self-host $1,453.70, cheapest comparable API $13.70. 21,247 requests per day, 323,355,931 output tokens per month: self-host $1,453.70, cheapest comparable API $19.40. 21,676 requests per day, 329,888,374 output tokens per month: self-host $2,907.39, cheapest comparable API $19.79. 50,000 requests per day, 760,937,500 output tokens per month: self-host $4,361.09, cheapest comparable API $45.66. 150,000 requests per day, 2,282,812,500 output tokens per month: self-host $10,175.87, cheapest comparable API $136.97. 500,000 requests per day, 7,609,375,000 output tokens per month: self-host $34,888.68, cheapest comparable API $456.56. 1,500,000 requests per day, 22,828,125,000 output tokens per month: self-host $101,758.65, cheapest comparable API $1,369.69. 5,000,000 requests per day, 76,093,750,000 output tokens per month: self-host $338,710.94, cheapest comparable API $4,565.63.

Scroll horizontally to read every chart label and value.

Busy GPU-hours: 1,701.9, Engine-reported share doing token work. Idle GPU-hours billed: 489.6, Engine-reported share paid while idle.