Which is cheaper, DeepSeek R1 (0528) or DeepSeek V3.2?

DeepSeek R1 (0528) costs $0.55/$2.19 per million input/output tokens, while DeepSeek V3.2 costs $0.28/$0.42. For a typical workload of 10M input and 1.5M output tokens per month, that's $8.79 versus $3.43.

Which model is better for coding, DeepSeek R1 (0528) or DeepSeek V3.2?

We don't yet track SWE-bench Verified results for both models; check their individual pages for coding-related scores.

DeepSeek R1 (0528) vs DeepSeek V3.2

Benchmarks, API pricing and specs, head to head. Data updated 2026-06-10.

DeepSeek R1 (0528)

DeepSeek · May 2025

67.8

The open reasoning model that started it all — RL-trained chain-of-thought, MIT licensed, and a research landmark.

DeepSeek V3.2

DeepSeek · Sep 2025

68.4

The sparse-attention release that halved DeepSeek's already-lowest-in-class prices while keeping GPT-class quality.

The verdict

DeepSeek V3.2 wins 3 of the 4 benchmarks these models share, against 1 for DeepSeek R1 (0528). On price the gap is dramatic: DeepSeek V3.2 works out roughly 3.0x cheaper per blended million tokens.

Benchmark head-to-head 1–3

GPQA Diamond

81%79.9%

DeepSeek R1 (0528)DeepSeek V3.2

AIME 2025

87.5%89.3%

DeepSeek R1 (0528)DeepSeek V3.2

HLE

17.7%~19.8%

DeepSeek R1 (0528)DeepSeek V3.2

MMLU-Pro

84.8%85%

DeepSeek R1 (0528)DeepSeek V3.2

Specs & pricing

	DeepSeek R1 (0528)	DeepSeek V3.2
modhub Index	67.8	68.4
Input price / 1M	$0.55	$0.28
Output price / 1M	$2.19	$0.42
Context window	128K	128K
Max output	64K	64K
Open weights	yes (MIT)	yes (MIT)
Reasoning model	yes	yes
Multimodal input	text	text
Knowledge cutoff	Mar 2025	Jul 2025
Released	May 2025	Sep 2025
Example monthly cost*	$8.79	$3.43

* 10M input + 1.5M output tokens per month at list prices, no caching. Green = better value on that row.

Frequently asked questions

Which is better, DeepSeek R1 (0528) or DeepSeek V3.2?: DeepSeek V3.2 wins 3 of the 4 benchmarks these models share, against 1 for DeepSeek R1 (0528). On price the gap is dramatic: DeepSeek V3.2 works out roughly 3.0x cheaper per blended million tokens.
Which is cheaper, DeepSeek R1 (0528) or DeepSeek V3.2?: DeepSeek R1 (0528) costs $0.55/$2.19 per million input/output tokens, while DeepSeek V3.2 costs $0.28/$0.42. For a typical workload of 10M input and 1.5M output tokens per month, that's $8.79 versus $3.43.
Which model is better for coding, DeepSeek R1 (0528) or DeepSeek V3.2?: We don't yet track SWE-bench Verified results for both models; check their individual pages for coding-related scores.

More comparisons

DeepSeek R1 (0528) vs GPT-5.5 DeepSeek V3.2 vs GPT-5.5 DeepSeek R1 (0528) vs GPT-5.2 DeepSeek V3.2 vs GPT-5.2 DeepSeek R1 (0528) vs GPT-5.1 DeepSeek V3.2 vs GPT-5.1 DeepSeek R1 (0528) vs GPT-5 DeepSeek V3.2 vs GPT-5 DeepSeek R1 (0528) vs GPT-5 mini DeepSeek V3.2 vs GPT-5 mini DeepSeek R1 (0528) vs OpenAI o3 DeepSeek V3.2 vs OpenAI o3