Hooshware
DeepSeek-R1 is an open-weights Mixture-of-Experts reasoning model with 671B total and 37B active parameters. It combines reinforcement learning without initial supervised fine-tuning with targeted distillation under the MIT license.
Hooshware signals & evidence
Recorded signals are separated from independent benchmarks and source claims.
Momentum reflects recent attention and activity. Hype and Reality appear only when recorded; missing values are never silently estimated.
Model intelligence
About DeepSeek-R1
DeepSeek-R1 is an open-weights Mixture-of-Experts reasoning model with 671B total and 37B active parameters. It combines reinforcement learning without initial supervised fine-tuning with targeted distillation under the MIT license.
Discovery
Related models
No verified model relationships recorded yet.
Recorded facts
Technical profile
- Parameters
- 671000000000
- Context window
- 128,000 tokens
- Maximum output
- 8,192 tokens
- License
- Unknown
- Open weights
- Yes
- Input price / 1M
- 0.55
- Output price / 1M
- 2.19