Compare deepinfra/DeepSeek-R1 vs anthropic/claude-opus-4.5

Model Comparison

Metric	DeepSeek-R1 deepinfra	claude-opus-4.5 anthropic
Pricing
Input Price	$0.75 / 1M tokens	$5 / 1M tokens
Output Price	$2.4 / 1M tokens	$25 / 1M tokens
Capabilities
Context Window	16K tokens	200K tokens
Capabilities	tools
Input type	text	text, image
Category Scores
Overall Average	63.3	76.6
Maths	76.0	91.3
Finance	64.0	80.5
Science	75.3	81.3
Writing	58.5	71.2
Academia	66.7	78.2
Marketing	58.8	73.3
Programming	44.1	60.2
Benchmark Tests
HLE	14.9	28.4
AIME	89.3	_
GPQA	81.3	86.6
SciCode	40.3	49.5
MATH-500	98.3	_
MMLU-Pro	84.9	89.5
LiveCodeBench	77.0	87.1
AA Math Index	76.0	91.3
AA Coding Index	44.1	60.2
AAII	52.0	69.8

DeepSeek-R1 Advantages

• Lower input token cost ($0.75 / 1M tokens vs $5 / 1M tokens)

claude-opus-4.5 Advantages

• Higher benchmark scores (76.6 vs 63.3)
• Larger context window (200K tokens vs 16K tokens)

Compare deepinfra/DeepSeek-R1 vs anthropic/claude-opus-4.5