The modelled monthly GPU rent for Llama-3.3-70B-Instruct using 6 replicas of 1 x NVIDIA B300 is $30,418.02 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 $5,069.67, cheapest comparable API $3.20. 1,500 requests per day, 22,828,125 output tokens per month: self-host $5,069.67, cheapest comparable API $9.59. 5,000 requests per day, 76,093,750 output tokens per month: self-host $5,069.67, cheapest comparable API $31.96. 9,303 requests per day, 141,584,299 output tokens per month: self-host $5,069.67, cheapest comparable API $59.47. 9,491 requests per day, 144,444,588 output tokens per month: self-host $10,139.34, cheapest comparable API $60.67. 15,000 requests per day, 228,281,250 output tokens per month: self-host $10,139.34, cheapest comparable API $95.88. 50,000 requests per day, 760,937,500 output tokens per month: self-host $30,418.02, cheapest comparable API $319.59. 150,000 requests per day, 2,282,812,500 output tokens per month: self-host $81,114.72, cheapest comparable API $958.78. 500,000 requests per day, 7,609,375,000 output tokens per month: self-host $273,762.18, cheapest comparable API $3,195.94. 1,500,000 requests per day, 22,828,125,000 output tokens per month: self-host $811,147.20, cheapest comparable API $9,587.81. 5,000,000 requests per day, 76,093,750,000 output tokens per month: self-host $2,702,134.11, cheapest comparable API $31,959.38.

Scroll horizontally to read every chart label and value.

Busy GPU-hours: 3,886.8, Engine-reported share doing token work. Idle GPU-hours billed: 496.2, 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 $5,069.67, cheapest comparable API $3.20. 1,500 requests per day, 22,828,125 output tokens per month: self-host $5,069.67, cheapest comparable API $9.59. 5,000 requests per day, 76,093,750 output tokens per month: self-host $5,069.67, cheapest comparable API $31.96. 9,303 requests per day, 141,584,299 output tokens per month: self-host $5,069.67, cheapest comparable API $59.47. 9,491 requests per day, 144,444,588 output tokens per month: self-host $10,139.34, cheapest comparable API $60.67. 15,000 requests per day, 228,281,250 output tokens per month: self-host $10,139.34, cheapest comparable API $95.88. 50,000 requests per day, 760,937,500 output tokens per month: self-host $30,418.02, cheapest comparable API $319.59. 150,000 requests per day, 2,282,812,500 output tokens per month: self-host $81,114.72, cheapest comparable API $958.78. 500,000 requests per day, 7,609,375,000 output tokens per month: self-host $273,762.18, cheapest comparable API $3,195.94. 1,500,000 requests per day, 22,828,125,000 output tokens per month: self-host $811,147.20, cheapest comparable API $9,587.81. 5,000,000 requests per day, 76,093,750,000 output tokens per month: self-host $2,702,134.11, cheapest comparable API $31,959.38.

Scroll horizontally to read every chart label and value.

Busy GPU-hours: 3,886.8, Engine-reported share doing token work. Idle GPU-hours billed: 496.2, 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 $5,069.67, cheapest comparable API $3.20. 1,500 requests per day, 22,828,125 output tokens per month: self-host $5,069.67, cheapest comparable API $9.59. 5,000 requests per day, 76,093,750 output tokens per month: self-host $5,069.67, cheapest comparable API $31.96. 9,303 requests per day, 141,584,299 output tokens per month: self-host $5,069.67, cheapest comparable API $59.47. 9,491 requests per day, 144,444,588 output tokens per month: self-host $10,139.34, cheapest comparable API $60.67. 15,000 requests per day, 228,281,250 output tokens per month: self-host $10,139.34, cheapest comparable API $95.88. 50,000 requests per day, 760,937,500 output tokens per month: self-host $30,418.02, cheapest comparable API $319.59. 150,000 requests per day, 2,282,812,500 output tokens per month: self-host $81,114.72, cheapest comparable API $958.78. 500,000 requests per day, 7,609,375,000 output tokens per month: self-host $273,762.18, cheapest comparable API $3,195.94. 1,500,000 requests per day, 22,828,125,000 output tokens per month: self-host $811,147.20, cheapest comparable API $9,587.81. 5,000,000 requests per day, 76,093,750,000 output tokens per month: self-host $2,702,134.11, cheapest comparable API $31,959.38.

Scroll horizontally to read every chart label and value.

Busy GPU-hours: 3,886.8, Engine-reported share doing token work. Idle GPU-hours billed: 496.2, 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 $5,069.67, cheapest comparable API $3.20. 1,500 requests per day, 22,828,125 output tokens per month: self-host $5,069.67, cheapest comparable API $9.59. 5,000 requests per day, 76,093,750 output tokens per month: self-host $5,069.67, cheapest comparable API $31.96. 9,303 requests per day, 141,584,299 output tokens per month: self-host $5,069.67, cheapest comparable API $59.47. 9,491 requests per day, 144,444,588 output tokens per month: self-host $10,139.34, cheapest comparable API $60.67. 15,000 requests per day, 228,281,250 output tokens per month: self-host $10,139.34, cheapest comparable API $95.88. 50,000 requests per day, 760,937,500 output tokens per month: self-host $30,418.02, cheapest comparable API $319.59. 150,000 requests per day, 2,282,812,500 output tokens per month: self-host $81,114.72, cheapest comparable API $958.78. 500,000 requests per day, 7,609,375,000 output tokens per month: self-host $273,762.18, cheapest comparable API $3,195.94. 1,500,000 requests per day, 22,828,125,000 output tokens per month: self-host $811,147.20, cheapest comparable API $9,587.81. 5,000,000 requests per day, 76,093,750,000 output tokens per month: self-host $2,702,134.11, cheapest comparable API $31,959.38.

Scroll horizontally to read every chart label and value.

Busy GPU-hours: 3,886.8, Engine-reported share doing token work. Idle GPU-hours billed: 496.2, Engine-reported share paid while idle.