DeepSeek model product
DeepSeek-R1-Distill-Llama
DeepSeek-R1 is the first-generation reasoning model built atop DeepSeek-V3 (671B total parameters, 37B activated per token).
Updated Aug 12, 2026. Default version: DeepSeek R1 Distill Llama 8B
LLMBoard score12.4DeepSeek R1 Distill Llama 8B
Coverage80%4 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable
DeepSeek-R1-Distill-Llama Specifications
Technical details for the model's default version.
- Version
- DeepSeek R1 Distill Llama 8B
- Released
- Jan 20, 2025
- Knowledge cutoff
- Unknown
- Parameters
- 8B
- Context window
- N/A
- Max output
- N/A
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- MIT
DeepSeek-R1-Distill-Llama Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
DeepSeek-R1-Distill-Llama Benchmark Results
Benchmark scores for DeepSeek R1 Distill Llama 8B.
| AIME 2024 | 0.8 | 29 | 53 | 46.1% | C | |
| MATH-500 | 0.9 | 29 | 32 | 9.7% | C | |
| LiveCodeBench | 0.4 | 50 | 73 | 31.9% | C | |
| GPQA | 0.5 | 181 | 234 | 22.8% | C |
DeepSeek-R1-Distill-Llama Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
DeepSeek-R1-Distill-Llama Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- N/A
- Tracked offerings
- 1
| Alibaba (China) | deepseek-r1-distill-llama-8b | global | N/A | N/A | 32.8K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
DeepSeek-R1-Distill-Llama Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| DeepSeek R1 Distill Llama 70B | N/A | 70.6B | 128K | 128K | No | MIT | |
| DeepSeek R1 Distill Llama 8B | 12.4 | 8B | N/A | N/A | No | MIT |
What is DeepSeek-R1-Distill-Llama?
Key information about DeepSeek-R1-Distill-Llama and its available data.
DeepSeek-R1 is the first-generation reasoning model built atop DeepSeek-V3 (671B total parameters, 37B activated per token). It incorporates large-scale reinforcement learning (RL) to enhance its chain-of-thought and reasoning capabilities, delivering strong performance in math, code, and multi-step reasoning tasks.
Data as of 2026-08-11.
DeepSeek-R1-Distill-Llama vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to DeepSeek-R1-Distill-Llama
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
DE
DeepSeek-V2.5
DeepSeek
DE
DeepSeek-R1-Distill-Qwen
DeepSeek
DE
DeepSeek-VL2
DeepSeek
DE
DeepSeek-V3
DeepSeek
DE
DeepSeek-V3.1
DeepSeek
DE
DeepSeek-R1
DeepSeek
FAQ
Common questions about DeepSeek-R1-Distill-Llama.
When was DeepSeek-R1-Distill-Llama released?
DeepSeek-R1-Distill-Llama's default version was released on Jan 20, 2025.
How much does DeepSeek-R1-Distill-Llama cost?
No official standard PAYG price is currently available for DeepSeek-R1-Distill-Llama.
Who created DeepSeek-R1-Distill-Llama?
DeepSeek-R1-Distill-Llama was created by DeepSeek.
What is the context window for DeepSeek-R1-Distill-Llama?
A context window is not available for the default version.
Is DeepSeek-R1-Distill-Llama open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer DeepSeek-R1-Distill-Llama?
1 provider offerings are linked to the default version.
What models should I compare DeepSeek-R1-Distill-Llama with?
Nearby ranked alternatives include Nova Lite, Llama 3.1 70B, Qwen2.5 VL 7B.