DeepSeek-R1
deepseek/deepseek-r1
Classic open reasoning model for transparent math, coding, and deliberate problem solving
Capabilities
ReasoningYes
Tool callingYes
Structured outputNo
TemperatureSupported
AttachmentNo
Open weightsYes
Limits
Context128,000 tokens
Max inputN/A
Max output32,768 tokens
Details
Familydeepseek-thinking
Knowledge cutoff2024-07
Release date2025-01-20
Last updated2025-05-29
Modalities
Inputtext
Outputtext
Benchmarks
Aider Polyglot
56.9
percent correct
Artificial Analysis Coding Index
15.9
index
SciCode
35.7
percent correct
Terminal-Bench Hard
6.1
success rate
Community Rating
—
No ratings yet
Sign in to rate
Pricing
Cost per 1M tokens
InputN/A
OutputN/A