DeepSeek R1on Krater.ai
DeepSeek's advanced reasoning model, competitive with o1 on complex problem-solving. DeepSeek R1 uses chain-of-thought reasoning for challenging tasks.
Released January 20, 2025
Specifications
DeepSeek R1 at a glance
Context
163.8K tokens
Max output
16K tokens
Input
Text
Output
Text
Input price
$0.70 / 1M
Output price
$2.50 / 1M
Knowledge cutoff
2024-07-31
Capabilities
What it is good at
Catalog capabilities
- Generates text responses
- Supports tool calling
- Supports structured outputs
- Instruction format: deepseek-r1
- Advanced reasoning capabilities
- Excellent at math and science
Good for
Benchmarks
Catalog data, not Krater benchmarks.
Coding index score
24.6
Agentic index score
3.1
Intelligence index score
18.5
Compare
Compare DeepSeek R1
DeepSeek R1 vs Chat
DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions.
Open comparisonDeepSeek R1 vs R1 0528
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
Open comparisonDeepSeek R1 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 DeepSeek R1
Clear answers based on the model catalog and Krater access.
Use DeepSeek R1 in your API
Connect with Krater's unified API.