DeepSeek R1 0528
Specifications
- Input
- Output
- Context window
- 164K tokens
- Veröffentlicht
- May 2025
Performance
- Speed
- 13 t/s
- TTFT
- 551 ms
- Latency
- 515 ms
- Intelligence
- —
Pricing
- Eingabe
- €0.60 per 1M tokens
- Ausgabe
- €2.40 per 1M tokens
Über dieses Modell
DeepSeek R1 0528 is an upgraded 685B parameter reasoning model with significantly enhanced depth of reasoning and inference capabilities. Achieves 87.5% on AIME 2025 (up from 70%), 91.4% on AIME 2024, 73.3% on LiveCodeBench, and 1930 Codeforces rating. Features system prompt support, averages 23K thinking tokens per question for deeper analysis, and reduced hallucination rate. Released under MIT license supporting commercial use and distillation. Performance approaching O3 and Gemini 2.5 Pro levels.
Technische Daten
- Fähigkeiten
- Eingabe-Modalitäten
- Ausgabe-Modalitäten
- Reasoning
- Standard on
Knowledge horizon
Veröffentlicht May 2025
Today
Since release 13 mo
See also
Modell zum Vergleich hinzufügen
Nach einem Modell suchen