The modelled monthly GPU rent for Llama-3.1-8B-Instruct using 1 replica of 1 x AMD Instinct MI300X is $1,892.00 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 $1,892.00, cheapest comparable API $0.46. 1,500 requests per day, 22,828,125 output tokens per month: self-host $1,892.00, cheapest comparable API $1.37. 5,000 requests per day, 76,093,750 output tokens per month: self-host $1,892.00, cheapest comparable API $4.57. 15,000 requests per day, 228,281,250 output tokens per month: self-host $1,892.00, cheapest comparable API $13.70. 50,000 requests per day, 760,937,500 output tokens per month: self-host $1,892.00, cheapest comparable API $45.66. 56,226 requests per day, 855,691,288 output tokens per month: self-host $1,892.00, cheapest comparable API $51.34. 57,362 requests per day, 872,977,981 output tokens per month: self-host $3,783.99, cheapest comparable API $52.38. 150,000 requests per day, 2,282,812,500 output tokens per month: self-host $5,675.99, cheapest comparable API $136.97. 500,000 requests per day, 7,609,375,000 output tokens per month: self-host $17,027.95, cheapest comparable API $456.56. 1,500,000 requests per day, 22,828,125,000 output tokens per month: self-host $51,083.87, cheapest comparable API $1,369.69. 5,000,000 requests per day, 76,093,750,000 output tokens per month: self-host $168,387.56, cheapest comparable API $4,565.63.

Scroll horizontally to read every chart label and value.

Busy GPU-hours: 643.1, Engine-reported share doing token work. Idle GPU-hours billed: 87.4, 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 $1,892.00, cheapest comparable API $0.46. 1,500 requests per day, 22,828,125 output tokens per month: self-host $1,892.00, cheapest comparable API $1.37. 5,000 requests per day, 76,093,750 output tokens per month: self-host $1,892.00, cheapest comparable API $4.57. 15,000 requests per day, 228,281,250 output tokens per month: self-host $1,892.00, cheapest comparable API $13.70. 50,000 requests per day, 760,937,500 output tokens per month: self-host $1,892.00, cheapest comparable API $45.66. 56,226 requests per day, 855,691,288 output tokens per month: self-host $1,892.00, cheapest comparable API $51.34. 57,362 requests per day, 872,977,981 output tokens per month: self-host $3,783.99, cheapest comparable API $52.38. 150,000 requests per day, 2,282,812,500 output tokens per month: self-host $5,675.99, cheapest comparable API $136.97. 500,000 requests per day, 7,609,375,000 output tokens per month: self-host $17,027.95, cheapest comparable API $456.56. 1,500,000 requests per day, 22,828,125,000 output tokens per month: self-host $51,083.87, cheapest comparable API $1,369.69. 5,000,000 requests per day, 76,093,750,000 output tokens per month: self-host $168,387.56, cheapest comparable API $4,565.63.

Scroll horizontally to read every chart label and value.

Busy GPU-hours: 643.1, Engine-reported share doing token work. Idle GPU-hours billed: 87.4, 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 $1,892.00, cheapest comparable API $0.46. 1,500 requests per day, 22,828,125 output tokens per month: self-host $1,892.00, cheapest comparable API $1.37. 5,000 requests per day, 76,093,750 output tokens per month: self-host $1,892.00, cheapest comparable API $4.57. 15,000 requests per day, 228,281,250 output tokens per month: self-host $1,892.00, cheapest comparable API $13.70. 50,000 requests per day, 760,937,500 output tokens per month: self-host $1,892.00, cheapest comparable API $45.66. 56,226 requests per day, 855,691,288 output tokens per month: self-host $1,892.00, cheapest comparable API $51.34. 57,362 requests per day, 872,977,981 output tokens per month: self-host $3,783.99, cheapest comparable API $52.38. 150,000 requests per day, 2,282,812,500 output tokens per month: self-host $5,675.99, cheapest comparable API $136.97. 500,000 requests per day, 7,609,375,000 output tokens per month: self-host $17,027.95, cheapest comparable API $456.56. 1,500,000 requests per day, 22,828,125,000 output tokens per month: self-host $51,083.87, cheapest comparable API $1,369.69. 5,000,000 requests per day, 76,093,750,000 output tokens per month: self-host $168,387.56, cheapest comparable API $4,565.63.

Scroll horizontally to read every chart label and value.

Busy GPU-hours: 643.1, Engine-reported share doing token work. Idle GPU-hours billed: 87.4, 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 $1,892.00, cheapest comparable API $0.46. 1,500 requests per day, 22,828,125 output tokens per month: self-host $1,892.00, cheapest comparable API $1.37. 5,000 requests per day, 76,093,750 output tokens per month: self-host $1,892.00, cheapest comparable API $4.57. 15,000 requests per day, 228,281,250 output tokens per month: self-host $1,892.00, cheapest comparable API $13.70. 50,000 requests per day, 760,937,500 output tokens per month: self-host $1,892.00, cheapest comparable API $45.66. 56,226 requests per day, 855,691,288 output tokens per month: self-host $1,892.00, cheapest comparable API $51.34. 57,362 requests per day, 872,977,981 output tokens per month: self-host $3,783.99, cheapest comparable API $52.38. 150,000 requests per day, 2,282,812,500 output tokens per month: self-host $5,675.99, cheapest comparable API $136.97. 500,000 requests per day, 7,609,375,000 output tokens per month: self-host $17,027.95, cheapest comparable API $456.56. 1,500,000 requests per day, 22,828,125,000 output tokens per month: self-host $51,083.87, cheapest comparable API $1,369.69. 5,000,000 requests per day, 76,093,750,000 output tokens per month: self-host $168,387.56, cheapest comparable API $4,565.63.

Scroll horizontally to read every chart label and value.

Busy GPU-hours: 643.1, Engine-reported share doing token work. Idle GPU-hours billed: 87.4, Engine-reported share paid while idle.