DeepSeek R1

DeepSeek

DeepSeek's advanced reasoning model from the R1 series, released May 2025. Built for deep chain-of-thought reasoning, it excels at complex mathematical, logical, and analytical problems. With 131K context and 32K output window, it handles substantial reasoning tasks. Superseded by the V3.2 Speciale model which achieves stronger reasoning at lower cost.

Try Now

Capabilities

Thinking

Technical Specifications

Context Window

131,072 tokens

Max Output

32,768 tokens

Pricing

Token Costs (per 1M tokens)

Cache Miss Input

$0.55

Non-Reasoning Output

$2.15

Cache Read Input

$0.35

Legacy

Made legacy on

Reason

Superseded by V3.2 Speciale with superior reasoning capabilities

Recommended Replacement

DeepSeek V3.2 Speciale