The modelled monthly GPU rent for Llama-3.1-8B-Instruct using 3 replicas of 1 x NVIDIA A100 PCIe 80 GB is $2,607.88 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 $869.30, cheapest comparable API $0.46. 1,500 requests per day, 22,828,125 output tokens per month: self-host $869.30, cheapest comparable API $1.37. 5,000 requests per day, 76,093,750 output tokens per month: self-host $869.30, cheapest comparable API $4.57. 15,000 requests per day, 228,281,250 output tokens per month: self-host $869.30, cheapest comparable API $13.70. 20,484 requests per day, 311,741,106 output tokens per month: self-host $869.30, cheapest comparable API $18.70. 20,898 requests per day, 318,038,906 output tokens per month: self-host $1,738.59, cheapest comparable API $19.08. 50,000 requests per day, 760,937,500 output tokens per month: self-host $2,607.88, cheapest comparable API $45.66. 150,000 requests per day, 2,282,812,500 output tokens per month: self-host $6,954.36, cheapest comparable API $136.97. 500,000 requests per day, 7,609,375,000 output tokens per month: self-host $21,732.38, cheapest comparable API $456.56. 1,500,000 requests per day, 22,828,125,000 output tokens per month: self-host $63,458.53, cheapest comparable API $1,369.69. 5,000,000 requests per day, 76,093,750,000 output tokens per month: self-host $210,369.39, cheapest comparable API $4,565.63.

Scroll horizontally to read every chart label and value.

Busy GPU-hours: 1,765.3, Engine-reported share doing token work. Idle GPU-hours billed: 426.2, 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 $869.30, cheapest comparable API $0.46. 1,500 requests per day, 22,828,125 output tokens per month: self-host $869.30, cheapest comparable API $1.37. 5,000 requests per day, 76,093,750 output tokens per month: self-host $869.30, cheapest comparable API $4.57. 15,000 requests per day, 228,281,250 output tokens per month: self-host $869.30, cheapest comparable API $13.70. 20,484 requests per day, 311,741,106 output tokens per month: self-host $869.30, cheapest comparable API $18.70. 20,898 requests per day, 318,038,906 output tokens per month: self-host $1,738.59, cheapest comparable API $19.08. 50,000 requests per day, 760,937,500 output tokens per month: self-host $2,607.88, cheapest comparable API $45.66. 150,000 requests per day, 2,282,812,500 output tokens per month: self-host $6,954.36, cheapest comparable API $136.97. 500,000 requests per day, 7,609,375,000 output tokens per month: self-host $21,732.38, cheapest comparable API $456.56. 1,500,000 requests per day, 22,828,125,000 output tokens per month: self-host $63,458.53, cheapest comparable API $1,369.69. 5,000,000 requests per day, 76,093,750,000 output tokens per month: self-host $210,369.39, cheapest comparable API $4,565.63.

Scroll horizontally to read every chart label and value.

Busy GPU-hours: 1,765.3, Engine-reported share doing token work. Idle GPU-hours billed: 426.2, 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 $869.30, cheapest comparable API $0.46. 1,500 requests per day, 22,828,125 output tokens per month: self-host $869.30, cheapest comparable API $1.37. 5,000 requests per day, 76,093,750 output tokens per month: self-host $869.30, cheapest comparable API $4.57. 15,000 requests per day, 228,281,250 output tokens per month: self-host $869.30, cheapest comparable API $13.70. 20,484 requests per day, 311,741,106 output tokens per month: self-host $869.30, cheapest comparable API $18.70. 20,898 requests per day, 318,038,906 output tokens per month: self-host $1,738.59, cheapest comparable API $19.08. 50,000 requests per day, 760,937,500 output tokens per month: self-host $2,607.88, cheapest comparable API $45.66. 150,000 requests per day, 2,282,812,500 output tokens per month: self-host $6,954.36, cheapest comparable API $136.97. 500,000 requests per day, 7,609,375,000 output tokens per month: self-host $21,732.38, cheapest comparable API $456.56. 1,500,000 requests per day, 22,828,125,000 output tokens per month: self-host $63,458.53, cheapest comparable API $1,369.69. 5,000,000 requests per day, 76,093,750,000 output tokens per month: self-host $210,369.39, cheapest comparable API $4,565.63.

Scroll horizontally to read every chart label and value.

Busy GPU-hours: 1,765.3, Engine-reported share doing token work. Idle GPU-hours billed: 426.2, 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 $869.30, cheapest comparable API $0.46. 1,500 requests per day, 22,828,125 output tokens per month: self-host $869.30, cheapest comparable API $1.37. 5,000 requests per day, 76,093,750 output tokens per month: self-host $869.30, cheapest comparable API $4.57. 15,000 requests per day, 228,281,250 output tokens per month: self-host $869.30, cheapest comparable API $13.70. 20,484 requests per day, 311,741,106 output tokens per month: self-host $869.30, cheapest comparable API $18.70. 20,898 requests per day, 318,038,906 output tokens per month: self-host $1,738.59, cheapest comparable API $19.08. 50,000 requests per day, 760,937,500 output tokens per month: self-host $2,607.88, cheapest comparable API $45.66. 150,000 requests per day, 2,282,812,500 output tokens per month: self-host $6,954.36, cheapest comparable API $136.97. 500,000 requests per day, 7,609,375,000 output tokens per month: self-host $21,732.38, cheapest comparable API $456.56. 1,500,000 requests per day, 22,828,125,000 output tokens per month: self-host $63,458.53, cheapest comparable API $1,369.69. 5,000,000 requests per day, 76,093,750,000 output tokens per month: self-host $210,369.39, cheapest comparable API $4,565.63.

Scroll horizontally to read every chart label and value.

Busy GPU-hours: 1,765.3, Engine-reported share doing token work. Idle GPU-hours billed: 426.2, Engine-reported share paid while idle.