Price Per TokenPrice Per Token
Anthropic
Anthropic
vs
Deepseek
Deepseek

Claude Sonnet 4 vs R1

A detailed comparison of pricing, benchmarks, and capabilities

Sponsor Price Per Token Reach 5000+ developers comparing LLM APIs

116 out of our 296 tracked models have had a price change in January.

Make informed model choices with updates on pricing, new releases, and tools with our weekly newsletter.

Key Takeaways

Claude Sonnet 4 wins:

  • Larger context window
  • Faster response time
  • Higher intelligence benchmark
  • Better at coding
  • Supports vision

R1 wins:

  • Cheaper input tokens
  • Cheaper output tokens
  • Better at math
Price Advantage
R1
Benchmark Advantage
Claude Sonnet 4
Context Window
Claude Sonnet 4
Speed
Claude Sonnet 4

Pricing Comparison

Price Comparison

MetricClaude Sonnet 4R1Winner
Input (per 1M tokens)$3.00$0.70 R1
Output (per 1M tokens)$15.00$2.40 R1
Cache Read (per 1M)$300000.00N/A Claude Sonnet 4
Cache Write (per 1M)$3750000.00N/A Claude Sonnet 4
Using a 3:1 input/output ratio, R1 is 81% cheaper overall.

Claude Sonnet 4 Providers

Amazon Bedrock $3.00 (Cheapest)
OpenRouter $3.00 (Cheapest)
Google $3.00 (Cheapest)
Anthropic $3.00 (Cheapest)

R1 Providers

Chutes $0.30 (Cheapest)
Vercel $0.55
Novita $0.70
DeepInfra $1.00
Azure $1.49

Benchmark Comparison

8
Benchmarks Compared
2
Claude Sonnet 4 Wins
6
R1 Wins

Benchmark Scores

BenchmarkClaude Sonnet 4R1Winner
Intelligence Index
Overall intelligence score
32.718.7
Coding Index
Code generation & understanding
29.415.7
Math Index
Mathematical reasoning
38.068.0
MMLU Pro
Academic knowledge
83.784.4
GPQA
Graduate-level science
68.370.8
LiveCodeBench
Competitive programming
44.961.7
Aider
Real-world code editing
61.364.0
AIME
Competition math
40.768.3
Claude Sonnet 4 significantly outperforms in coding benchmarks.

Cost vs Quality

X-axis:
Y-axis:
Loading chart...
Claude Sonnet 4
Other models

Context & Performance

Context Window

Claude Sonnet 4
1,000,000
tokens
Max output: 64,000 tokens
R1
163,840
tokens
Max output: 163,840 tokens
Claude Sonnet 4 has a 84% larger context window.

Speed Performance

MetricClaude Sonnet 4R1Winner
Tokens/second66.3 tok/s0.0 tok/s
Time to First Token1.90s0.00s
Claude Sonnet 4 responds Infinity% faster on average.

Capabilities

Feature Comparison

FeatureClaude Sonnet 4R1
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyClaude Sonnet 4R1
LicenseProprietaryOpen Source
AuthorAnthropicDeepseek
ReleasedMay 2025Jan 2025

Claude Sonnet 4 Modalities

Input
imagetextfile
Output
text

R1 Modalities

Input
text
Output
text

Related Comparisons

Compare Claude Sonnet 4 with:

Compare R1 with:

Frequently Asked Questions

R1 has cheaper input pricing at $0.70/M tokens. R1 has cheaper output pricing at $2.40/M tokens.
Claude Sonnet 4 scores higher on coding benchmarks with a score of 29.4, compared to R1's score of 15.7.
Claude Sonnet 4 has a 1,000,000 token context window, while R1 has a 163,840 token context window.
Claude Sonnet 4 supports vision. R1 does not support vision.