DeepSeek-R1-0528 is a lightly upgraded release of DeepSeek R1, utilizing more compute and advanced post-training techniques to push its reasoning and inference capabilities to the level of flagship models like O3 and Gemini 2.5 Pro. Excels in math, programming, and logic leaderboards, with a distilled 8B-parameter variant that rivals much larger models on key benchmarks.
Retired on Jan 27, 2026: requests to this model ID now return an error. These models are live and work with the same API key.
DeepSeek-R1-0528 is a lightly upgraded release of DeepSeek R1, utilizing more compute and advanced post-training techniques to push its reasoning and inference capabilities to the level of flagship models like O3 and Gemini 2.5 Pro.
No. DeepSeek Reasoner (Free) was retired on NagaAI on Jan 27, 2026, and requests to it now return an error. Live models you can use instead with the same API key: DeepSeek V4.1 Flash 1017, DeepSeek V4.1 Flash 0910 and LFM3-1.7B.
It takes text as input and returns text.
