R1 0528on Krater.ai
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
Released May 28, 2025
Specifications
R1 0528 at a glance
Context
163.8K tokens
Max output
32.8K tokens
Input
Text
Output
Text
Input price
$0.50 / 1M
Output price
$2.15 / 1M
Knowledge cutoff
2025-03-31
Is DeepSeek down?
DeepSeek timing out? The live DeepSeek status page shows current incidents and faster models to switch to.
Live DeepSeek statusCapabilities
What it is good at
Catalog capabilities
- Generates text responses
- Supports tool calling
- Supports structured outputs
- Instruction format: deepseek-r1
Good for
Benchmarks
Catalog data, not Krater benchmarks.
Intelligence index score
13.1
Design Arena dataviz rank
#64
Design Arena svg rank
#75
Compare
Compare R1 0528
R1 0528 vs DeepSeek V3 0324
V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team.
Open comparisonR1 0528 vs DeepSeek V4 Flash 0423
V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window.
Open comparisonR1 0528 vs DeepSeek V4 Flash 0731
V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.
Open comparisonFAQ
Questions about R1 0528
Clear answers based on the model catalog and Krater access.