DeepSeek-R1-Distill-8B
Smallest R1 distill, Llama 3.1 8B base. Tradeoff: limited reasoning depth vs the larger distills.
DeepSeek-R1-Distill-8B is a reasoning AI model from DeepSeek. It costs $0.0700 per million input tokens and $0.2000 per million output tokens (blended $0.1090/M), with a 128,000-token context window.
RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.
Hand-maintained from DeepSeek's published pricing; no check date on record.
- Smallest R1 distill
- Edge-friendly
- Open weights
- Edge reasoning experiments
- Distillation research
Benchmarks
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)89.1%self-reported by DeepSeek · no date on the source · R1 distilled-model table, Distill-Llama-8B, 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-8B cost?
DeepSeek-R1-Distill-8B costs $0.0700 per million input tokens and $0.2000 per million output tokens, for a blended reference rate of $0.1090 per million tokens.
What is DeepSeek-R1-Distill-8B's context window?
DeepSeek-R1-Distill-8B supports up to 128,000 tokens of context in a single request.
What is DeepSeek-R1-Distill-8B best for?
DeepSeek-R1-Distill-8B is well suited to Smallest R1 distill, Edge-friendly and Open weights.
Who makes DeepSeek-R1-Distill-8B?
DeepSeek-R1-Distill-8B is developed and served by DeepSeek. It was released in Jan 2025.
