Is GPT-3.5 Turbo Instruct or DeepSeek-R1 cheaper?

GPT-3.5 Turbo Instruct is cheaper on output tokens ($2.00 vs $5.40 per 1M).

Which has the larger context window, GPT-3.5 Turbo Instruct or DeepSeek-R1?

DeepSeek-R1 has the larger context window (164K tokens).

GPT-3.5 Turbo Instruct vs DeepSeek-R1

GPT-3.5 Turbo Instruct is cheaper on output tokens, while DeepSeek-R1 offers a larger context window. Choose GPT-3.5 Turbo Instruct or DeepSeek-R1 based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	GPT-3.5 Turbo Instruct	DeepSeek-R1
Provider	Azure	Azure
Input / 1M tokens	$1.50	$1.35
Output / 1M tokens	$2.00	$5.40
Context window	4K	164K
Parameters	20B	671B
Open weights	No	Yes
Released	Sep 2023	Jan 2025

GPT-3.5 Turbo Instruct details →DeepSeek-R1 details →

FAQ

Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.