DeepSeek
Reasoning

DeepSeek-R1-Distill-14B

Distilled

R1 distilled into a 14B Qwen base. Cheap reasoning that fits on consumer GPUs.

DeepSeek-R1-Distill-14B is a reasoning AI model from DeepSeek. It costs $0.1000 per million input tokens and $0.3500 per million output tokens (blended $0.1750/M), with a 128,000-token context window.

RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.

INPUT
$0.1000/M
per million input tokens
OUTPUT
$0.3500/M
per million output tokens
BLENDED 70/30
$0.1750/M
unchanged since 3 May
CONTEXT
128,000
tokens

Hand-maintained from DeepSeek's published pricing; no check date on record.

What it is good at
  • Consumer-GPU reasoning
  • Open weights
Typical use cases
  • On-device reasoning research
  • Cheap STEM tutoring

Benchmarks

vs. best public score
Graduate-level science questions, "Google-proof". Source: DeepSeek (self-reported), GPQA Diamond (pass@1), read 2026-11-10.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.

Also reported by the provider

Results on benchmarks outside the set we compare across models. They are listed for completeness and are deliberately excluded from the bars above and from every ranking on this site, because a score is only comparable against the same benchmark variant. Why benchmark scores do not compare →

  • MATH-500 (pass@1)93.9%self-reported by DeepSeek · no date on the source · R1 distilled-model table, Distill-Qwen-14B, pass@1 from 64 responses per query, temperature 0.6, top-p 0.95, up to 32,768 tokens. Not comparable with the MATH column, so shown here and never ranked.

More from DeepSeek

See all 11 →

Frequently asked questions

How much does DeepSeek-R1-Distill-14B cost?

DeepSeek-R1-Distill-14B costs $0.1000 per million input tokens and $0.3500 per million output tokens, for a blended reference rate of $0.1750 per million tokens.

What is DeepSeek-R1-Distill-14B's context window?

DeepSeek-R1-Distill-14B supports up to 128,000 tokens of context in a single request.

What is DeepSeek-R1-Distill-14B best for?

DeepSeek-R1-Distill-14B is well suited to Consumer-GPU reasoning, Open weights and On-device reasoning research.

Who makes DeepSeek-R1-Distill-14B?

DeepSeek-R1-Distill-14B is developed and served by DeepSeek. It was released in Jan 2025.

Terms used on this page