Skip to content
Prices
esc

  • Pages

↑↓to move↵to open

Every host for GPT-3.5 Turbo Instruct

Per 1M tokens
HostBlendedInputOutputCachedPrecisionUptime
OpenAI
$1.63
$1.50$2.00——0.0%
Blended price: three input tokens for every output token, per 1M tokens.
CSV

Cheapest price over time

Per 1M tokens
Cheapest input and output price for GPT-3.5 Turbo Instruct over timeFree$0.50$1.00$1.50$2.00Sept 2023Sept 2024Oct 2025Oct 2026$2.00$1.50
  • Input
  • Output
The cheapest list price at any host on each day it changed.
CSV

What your workload costs

A month, at every host
Cheapest a month
$650.00
OpenAI
  • OpenAI
    $650.00

Rent GPUs or pay per token?

Break-even
Renting the GPUs
$16,878/mo
Break-even volume
10.4B tokens/mo
Needed around the clock
4K tok/s

8 × H100 cost $16,878 a month. The cheapest API (OpenAI) charges $1.63 per 1M blended tokens, so the GPUs only pay off above 10.4B tokens a month: the box must serve 4K tokens a second, every second.

GPU price: cheapest on-demand offer per GPU-hour × 730 hours. No throughput is assumed: it depends on the model size, precision, batch size and serving software, so measure yours. Power, storage, egress and engineering time are not included.

LMArena rating over time

Text leaderboard
LMArena text rating of GPT-3.5 Turbo Instruct over time1,0001,0501,1001,150Dec 2023Nov 2024Nov 2025Oct 20261,094

Rated about the same, by price

Blended, per 1M tokens

Quality data: LMArena (CC BY 4.0), Epoch AI (CC BY 4.0). Prices: OpenRouter, LiteLLM (MIT), provider pages. List prices in US dollars before discounts and taxes; other currencies converted at the European Central Bank reference rate. The figures on these pages are free to reuse under CC BY 4.0 with a link to this page.