Is DeepSeek-R1 or DeepSeek-V3 cheaper?

DeepSeek-V3 is cheaper at $1.10 / 1M tokens per million output tokens, vs $2.19 / 1M tokens for DeepSeek-R1.

Which has the larger context window?

Both DeepSeek-R1 and DeepSeek-V3 ship a 128K-token context window.

Is DeepSeek-R1 or DeepSeek-V3 better for coding?

Both DeepSeek-R1 and DeepSeek-V3 are competitive on coding benchmarks. See each model's individual spec page for HumanEval and SWE-bench scores where published. For an opinionated pick, consult our Best LLM for Coding ranking.

Are either of these models open source?

Both ship with open weights. DeepSeek-R1 is licensed under MIT; DeepSeek-V3 under MIT.

When were DeepSeek-R1 and DeepSeek-V3 released?

DeepSeek-R1 was released by DeepSeek on 2025-01-20. DeepSeek-V3 was released by DeepSeek on 2024-12-26.

Is DeepSeek-R1 or DeepSeek-V3 cheaper?

DeepSeek-V3 is cheaper at $1.10 / 1M tokens per million output tokens, vs $2.19 / 1M tokens for DeepSeek-R1.

Which has the larger context window?

Both DeepSeek-R1 and DeepSeek-V3 ship a 128K-token context window.

Is DeepSeek-R1 or DeepSeek-V3 better for coding?

Both DeepSeek-R1 and DeepSeek-V3 are competitive on coding benchmarks. See each model's individual spec page for HumanEval and SWE-bench scores where published. For an opinionated pick, consult our Best LLM for Coding ranking.

Are either of these models open source?

Both ship with open weights. DeepSeek-R1 is licensed under MIT; DeepSeek-V3 under MIT.

When were DeepSeek-R1 and DeepSeek-V3 released?

DeepSeek-R1 was released by DeepSeek on 2025-01-20. DeepSeek-V3 was released by DeepSeek on 2024-12-26.

DeepSeek-R1 vs DeepSeek-V3

A complete head-to-head: pricing, context window, benchmarks, modality coverage, and openness, with a programmatic verdict synthesized from the underlying data.

UpdatedApr 30, 2026

DeepSeek-R1 specs · DeepSeek-V3 specs

Verdict by category

PriceDeepSeek-V3
DeepSeek-V3 is roughly 2.0× cheaper on output tokens ($1.10 vs $2.19 per 1M).
Context windowTie
Both ship a 128K-token context window.
BenchmarksTie
No directly comparable public benchmarks are available for both models, check the spec sheets for individual scores.
ModalitiesTie
Both handle text.
OpennessTie
Both ship open weights, self-host either one.

On balance DeepSeek-V3 edges ahead, winning 1 of 5 categories against DeepSeek-R1's 0. DeepSeek-V3 is roughly 2.0× cheaper on output tokens ($1.10 vs $2.19 per 1M). Both ship a 128K-token context window.

No directly comparable public benchmarks are available for both models, check the spec sheets for individual scores. Both target the same set of modalities (text), so the deciding factors are price, context, and raw quality. Both ship open weights, self-host either one.

Both shipped within roughly a month of each other in 2025, so they share the same generation of training data and tooling. DeepSeek-R1 is usually picked for reasoning and math workloads, while DeepSeek-V3 sees more deployments in open source llm and commercial use llm. If pricing matters more than every last benchmark point, run the numbers in the calculator below before committing.

Side-by-side specs

Spec	DeepSeek-R1	DeepSeek-V3
Provider	DeepSeek	DeepSeek
Released	Jan 2025	Dec 2024
Modalities	text	text
Context window	128K tokens	128K tokens
Max output	,	,
Input · 1M	$0.55 / 1M tokens	$0.27 / 1M tokens
Output · 1M	$2.19 / 1M tokens	$1.10 / 1M tokens
Knowledge cutoff	2024-07	2024-07
Open weights	Yes (MIT)	Yes (MIT)
API available	Yes	Yes

Pricing at scale

What you'd actually pay at typical workloads. Numbers come from each model's published per-million-token rates.

Light usage, 100k in / 50k out per day$4.94 vs $2.46
Heavy usage, 1M in / 500k out per day$49.35 vs $24.60
RAG workload, 5M in / 200k out per day$95.64 vs $47.10

Light usage, 100k in / 50k out per day: $4.94 vs $2.46 per month, model B comes out ahead. Heavy usage, 1M in / 500k out per day: $49.35 vs $24.60 per month, model B comes out ahead. RAG workload, 5M in / 200k out per day: $95.64 vs $47.10 per month, model B comes out ahead.

Price calculator

Estimated spend for the listed models at your usage. Numbers are derived from each model's published per-million-token rates.

Input tokens / dayOutput tokens / dayHorizon

DeepSeek-R1$0.165
DeepSeek-V3$0.082

Benchmarks compared

Only sourced numbers. Where a benchmark is missing for one model we show the available value rather than fabricating the other.

DeepSeek-R1DeepSeek-V3

MMLU,88.5
HumanEval,90.0
GPQA71.5

Pick DeepSeek-R1 if

DeepSeek-R1 fits when…

Open-weight reasoning model on par with o1
MIT license
Cheap reasoning per token

Pick DeepSeek-V3 if

DeepSeek-V3 fits when…

Frontier-level quality at open-weight prices
MIT license, clean commercial use
Cheap to serve via MoE architecture
Cost-sensitive workloads, 2.0× cheaper than DeepSeek-R1 on output tokens.

Don't want either?

Consider DeepSeek-Coder-V2

DeepSeek's code-specialized model, strong on a broad set of programming languages and FIM tasks.

See DeepSeek-Coder-V2 specs DeepSeek-R1 vs DeepSeek-Coder-V2 DeepSeek-V3 vs DeepSeek-Coder-V2

Frequently asked

Is DeepSeek-R1 or DeepSeek-V3 cheaper?
DeepSeek-V3 is cheaper at $1.10 / 1M tokens per million output tokens, vs $2.19 / 1M tokens for DeepSeek-R1.
Which has the larger context window?
Both DeepSeek-R1 and DeepSeek-V3 ship a 128K-token context window.
Is DeepSeek-R1 or DeepSeek-V3 better for coding?
Both DeepSeek-R1 and DeepSeek-V3 are competitive on coding benchmarks. See each model's individual spec page for HumanEval and SWE-bench scores where published. For an opinionated pick, consult our Best LLM for Coding ranking.
Are either of these models open source?
Both ship with open weights. DeepSeek-R1 is licensed under MIT; DeepSeek-V3 under MIT.
When were DeepSeek-R1 and DeepSeek-V3 released?
DeepSeek-R1 was released by DeepSeek on 2025-01-20. DeepSeek-V3 was released by DeepSeek on 2024-12-26.

Friday digest

One short email every Friday, new models, leaks, and quietly-shipped APIs you missed.