The modelled monthly GPU rent for Llama-3.1-8B-Instruct using 7 replicas of 1 x NVIDIA A40 48 GB is $1,789.73 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 $255.67, cheapest comparable API $0.46. 1,500 requests per day, 22,828,125 output tokens per month: self-host $255.67, cheapest comparable API $1.37. 5,000 requests per day, 76,093,750 output tokens per month: self-host $255.67, cheapest comparable API $4.57. 7,379 requests per day, 112,303,425 output tokens per month: self-host $255.67, cheapest comparable API $6.74. 7,528 requests per day, 114,572,181 output tokens per month: self-host $511.35, cheapest comparable API $6.87. 15,000 requests per day, 228,281,250 output tokens per month: self-host $767.03, cheapest comparable API $13.70. 50,000 requests per day, 760,937,500 output tokens per month: self-host $1,789.73, cheapest comparable API $45.66. 150,000 requests per day, 2,282,812,500 output tokens per month: self-host $5,369.17, cheapest comparable API $136.97. 500,000 requests per day, 7,609,375,000 output tokens per month: self-host $17,385.90, cheapest comparable API $456.56. 1,500,000 requests per day, 22,828,125,000 output tokens per month: self-host $51,646.35, cheapest comparable API $1,369.69. 5,000,000 requests per day, 76,093,750,000 output tokens per month: self-host $171,557.93, cheapest comparable API $4,565.63.

Scroll horizontally to read every chart label and value.

Busy GPU-hours: 4,900.2, Engine-reported share doing token work. Idle GPU-hours billed: 213.3, 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 $255.67, cheapest comparable API $0.46. 1,500 requests per day, 22,828,125 output tokens per month: self-host $255.67, cheapest comparable API $1.37. 5,000 requests per day, 76,093,750 output tokens per month: self-host $255.67, cheapest comparable API $4.57. 7,379 requests per day, 112,303,425 output tokens per month: self-host $255.67, cheapest comparable API $6.74. 7,528 requests per day, 114,572,181 output tokens per month: self-host $511.35, cheapest comparable API $6.87. 15,000 requests per day, 228,281,250 output tokens per month: self-host $767.03, cheapest comparable API $13.70. 50,000 requests per day, 760,937,500 output tokens per month: self-host $1,789.73, cheapest comparable API $45.66. 150,000 requests per day, 2,282,812,500 output tokens per month: self-host $5,369.17, cheapest comparable API $136.97. 500,000 requests per day, 7,609,375,000 output tokens per month: self-host $17,385.90, cheapest comparable API $456.56. 1,500,000 requests per day, 22,828,125,000 output tokens per month: self-host $51,646.35, cheapest comparable API $1,369.69. 5,000,000 requests per day, 76,093,750,000 output tokens per month: self-host $171,557.93, cheapest comparable API $4,565.63.

Scroll horizontally to read every chart label and value.

Busy GPU-hours: 4,900.2, Engine-reported share doing token work. Idle GPU-hours billed: 213.3, 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 $255.67, cheapest comparable API $0.46. 1,500 requests per day, 22,828,125 output tokens per month: self-host $255.67, cheapest comparable API $1.37. 5,000 requests per day, 76,093,750 output tokens per month: self-host $255.67, cheapest comparable API $4.57. 7,379 requests per day, 112,303,425 output tokens per month: self-host $255.67, cheapest comparable API $6.74. 7,528 requests per day, 114,572,181 output tokens per month: self-host $511.35, cheapest comparable API $6.87. 15,000 requests per day, 228,281,250 output tokens per month: self-host $767.03, cheapest comparable API $13.70. 50,000 requests per day, 760,937,500 output tokens per month: self-host $1,789.73, cheapest comparable API $45.66. 150,000 requests per day, 2,282,812,500 output tokens per month: self-host $5,369.17, cheapest comparable API $136.97. 500,000 requests per day, 7,609,375,000 output tokens per month: self-host $17,385.90, cheapest comparable API $456.56. 1,500,000 requests per day, 22,828,125,000 output tokens per month: self-host $51,646.35, cheapest comparable API $1,369.69. 5,000,000 requests per day, 76,093,750,000 output tokens per month: self-host $171,557.93, cheapest comparable API $4,565.63.

Scroll horizontally to read every chart label and value.

Busy GPU-hours: 4,900.2, Engine-reported share doing token work. Idle GPU-hours billed: 213.3, 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 $255.67, cheapest comparable API $0.46. 1,500 requests per day, 22,828,125 output tokens per month: self-host $255.67, cheapest comparable API $1.37. 5,000 requests per day, 76,093,750 output tokens per month: self-host $255.67, cheapest comparable API $4.57. 7,379 requests per day, 112,303,425 output tokens per month: self-host $255.67, cheapest comparable API $6.74. 7,528 requests per day, 114,572,181 output tokens per month: self-host $511.35, cheapest comparable API $6.87. 15,000 requests per day, 228,281,250 output tokens per month: self-host $767.03, cheapest comparable API $13.70. 50,000 requests per day, 760,937,500 output tokens per month: self-host $1,789.73, cheapest comparable API $45.66. 150,000 requests per day, 2,282,812,500 output tokens per month: self-host $5,369.17, cheapest comparable API $136.97. 500,000 requests per day, 7,609,375,000 output tokens per month: self-host $17,385.90, cheapest comparable API $456.56. 1,500,000 requests per day, 22,828,125,000 output tokens per month: self-host $51,646.35, cheapest comparable API $1,369.69. 5,000,000 requests per day, 76,093,750,000 output tokens per month: self-host $171,557.93, cheapest comparable API $4,565.63.

Scroll horizontally to read every chart label and value.

Busy GPU-hours: 4,900.2, Engine-reported share doing token work. Idle GPU-hours billed: 213.3, Engine-reported share paid while idle.