May 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass.
Fully open-source model.
Modalities
In / Out Price
$0.50 / $2.15per 1M
Context
164K
Released
May 28, 2025
Knowledge Cutoff
Mar 2025
May 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass. Fully open-source model.
R1 0528 costs $0.50/M input tokens and $2.15/M output tokens, with separate rates for Cache Read at $0.35/M tokens.
R1 0528 has a 163,840 token context window. It supports up to 32,768 completion tokens.
The R1 0528 endpoint shown on this page does not accept tools, so function calling is unavailable there. It also supports structured outputs via a JSON schema in response_format.
R1 0528 is served by 4 providers on OpenRouter: DeepInfra, SiliconFlow, StreamLake and NovitaAI. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.
R1 0528 was released on May 28, 2025. Its knowledge cutoff is March 31, 2025.