The modelled monthly GPU rent for Llama-3.1-8B-Instruct using 6 replicas of 1 x NVIDIA L40S 48 GB is $3,462.57 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 $577.10, cheapest comparable API $0.46. 1,500 requests per day, 22,828,125 output tokens per month: self-host $577.10, cheapest comparable API $1.37. 5,000 requests per day, 76,093,750 output tokens per month: self-host $577.10, cheapest comparable API $4.57. 9,181 requests per day, 139,725,823 output tokens per month: self-host $577.10, cheapest comparable API $8.38. 9,367 requests per day, 142,548,566 output tokens per month: self-host $1,154.19, cheapest comparable API $8.55. 15,000 requests per day, 228,281,250 output tokens per month: self-host $1,154.19, cheapest comparable API $13.70. 50,000 requests per day, 760,937,500 output tokens per month: self-host $3,462.57, cheapest comparable API $45.66. 150,000 requests per day, 2,282,812,500 output tokens per month: self-host $9,810.62, cheapest comparable API $136.97. 500,000 requests per day, 7,609,375,000 output tokens per month: self-host $31,163.13, cheapest comparable API $456.56. 1,500,000 requests per day, 22,828,125,000 output tokens per month: self-host $93,489.39, cheapest comparable API $1,369.69. 5,000,000 requests per day, 76,093,750,000 output tokens per month: self-host $311,631.30, cheapest comparable API $4,565.63.

Scroll horizontally to read every chart label and value.

Busy GPU-hours: 3,938.5, Engine-reported share doing token work. Idle GPU-hours billed: 444.5, 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 $577.10, cheapest comparable API $0.46. 1,500 requests per day, 22,828,125 output tokens per month: self-host $577.10, cheapest comparable API $1.37. 5,000 requests per day, 76,093,750 output tokens per month: self-host $577.10, cheapest comparable API $4.57. 9,181 requests per day, 139,725,823 output tokens per month: self-host $577.10, cheapest comparable API $8.38. 9,367 requests per day, 142,548,566 output tokens per month: self-host $1,154.19, cheapest comparable API $8.55. 15,000 requests per day, 228,281,250 output tokens per month: self-host $1,154.19, cheapest comparable API $13.70. 50,000 requests per day, 760,937,500 output tokens per month: self-host $3,462.57, cheapest comparable API $45.66. 150,000 requests per day, 2,282,812,500 output tokens per month: self-host $9,810.62, cheapest comparable API $136.97. 500,000 requests per day, 7,609,375,000 output tokens per month: self-host $31,163.13, cheapest comparable API $456.56. 1,500,000 requests per day, 22,828,125,000 output tokens per month: self-host $93,489.39, cheapest comparable API $1,369.69. 5,000,000 requests per day, 76,093,750,000 output tokens per month: self-host $311,631.30, cheapest comparable API $4,565.63.

Scroll horizontally to read every chart label and value.

Busy GPU-hours: 3,938.5, Engine-reported share doing token work. Idle GPU-hours billed: 444.5, 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 $577.10, cheapest comparable API $0.46. 1,500 requests per day, 22,828,125 output tokens per month: self-host $577.10, cheapest comparable API $1.37. 5,000 requests per day, 76,093,750 output tokens per month: self-host $577.10, cheapest comparable API $4.57. 9,181 requests per day, 139,725,823 output tokens per month: self-host $577.10, cheapest comparable API $8.38. 9,367 requests per day, 142,548,566 output tokens per month: self-host $1,154.19, cheapest comparable API $8.55. 15,000 requests per day, 228,281,250 output tokens per month: self-host $1,154.19, cheapest comparable API $13.70. 50,000 requests per day, 760,937,500 output tokens per month: self-host $3,462.57, cheapest comparable API $45.66. 150,000 requests per day, 2,282,812,500 output tokens per month: self-host $9,810.62, cheapest comparable API $136.97. 500,000 requests per day, 7,609,375,000 output tokens per month: self-host $31,163.13, cheapest comparable API $456.56. 1,500,000 requests per day, 22,828,125,000 output tokens per month: self-host $93,489.39, cheapest comparable API $1,369.69. 5,000,000 requests per day, 76,093,750,000 output tokens per month: self-host $311,631.30, cheapest comparable API $4,565.63.

Scroll horizontally to read every chart label and value.

Busy GPU-hours: 3,938.5, Engine-reported share doing token work. Idle GPU-hours billed: 444.5, 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 $577.10, cheapest comparable API $0.46. 1,500 requests per day, 22,828,125 output tokens per month: self-host $577.10, cheapest comparable API $1.37. 5,000 requests per day, 76,093,750 output tokens per month: self-host $577.10, cheapest comparable API $4.57. 9,181 requests per day, 139,725,823 output tokens per month: self-host $577.10, cheapest comparable API $8.38. 9,367 requests per day, 142,548,566 output tokens per month: self-host $1,154.19, cheapest comparable API $8.55. 15,000 requests per day, 228,281,250 output tokens per month: self-host $1,154.19, cheapest comparable API $13.70. 50,000 requests per day, 760,937,500 output tokens per month: self-host $3,462.57, cheapest comparable API $45.66. 150,000 requests per day, 2,282,812,500 output tokens per month: self-host $9,810.62, cheapest comparable API $136.97. 500,000 requests per day, 7,609,375,000 output tokens per month: self-host $31,163.13, cheapest comparable API $456.56. 1,500,000 requests per day, 22,828,125,000 output tokens per month: self-host $93,489.39, cheapest comparable API $1,369.69. 5,000,000 requests per day, 76,093,750,000 output tokens per month: self-host $311,631.30, cheapest comparable API $4,565.63.

Scroll horizontally to read every chart label and value.

Busy GPU-hours: 3,938.5, Engine-reported share doing token work. Idle GPU-hours billed: 444.5, Engine-reported share paid while idle.