Price Per TokenPrice Per Token
Anthropic
Anthropic
vs
OpenAI
OpenAI

Claude Sonnet 4 vs GPT-4

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:

  • Cheaper input tokens
  • Cheaper output tokens
  • Larger context window
  • Faster response time
  • Higher intelligence benchmark
  • Better at coding
  • Better at math
  • Supports vision
  • Has reasoning mode

GPT-4 wins:

  • No clear advantages in compared metrics
Price Advantage
Claude Sonnet 4
Benchmark Advantage
Claude Sonnet 4
Context Window
Claude Sonnet 4
Speed
Claude Sonnet 4

Pricing Comparison

Price Comparison

MetricClaude Sonnet 4GPT-4Winner
Input (per 1M tokens)$3.00$30.00 Claude Sonnet 4
Output (per 1M tokens)$15.00$60.00 Claude Sonnet 4
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, Claude Sonnet 4 is 84% cheaper overall.

Claude Sonnet 4 Providers

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

GPT-4 Providers

OpenAI $30.00 (Cheapest)
OpenRouter $30.00 (Cheapest)
Azure $30.00 (Cheapest)

Benchmark Comparison

8
Benchmarks Compared
2
Claude Sonnet 4 Wins
1
GPT-4 Wins

Benchmark Scores

BenchmarkClaude Sonnet 4GPT-4Winner
Intelligence Index
Overall intelligence score
32.712.8
Coding Index
Code generation & understanding
29.413.1
Math Index
Mathematical reasoning
38.0--
MMLU Pro
Academic knowledge
83.7--
GPQA
Graduate-level science
68.3--
LiveCodeBench
Competitive programming
44.9--
Aider
Real-world code editing
61.367.7
AIME
Competition math
40.7--
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
GPT-4
8,191
tokens
Max output: 4,096 tokens
Claude Sonnet 4 has a 99% larger context window.

Speed Performance

MetricClaude Sonnet 4GPT-4Winner
Tokens/second66.3 tok/s25.4 tok/s
Time to First Token1.90s0.81s
Claude Sonnet 4 responds 162% faster on average.

Capabilities

Feature Comparison

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

License & Release

PropertyClaude Sonnet 4GPT-4
LicenseProprietaryProprietary
AuthorAnthropicOpenAI
ReleasedMay 2025May 2023

Claude Sonnet 4 Modalities

Input
imagetextfile
Output
text

GPT-4 Modalities

Input
text
Output
text

Related Comparisons

Compare Claude Sonnet 4 with:

Compare GPT-4 with:

Frequently Asked Questions

Claude Sonnet 4 has cheaper input pricing at $3.00/M tokens. Claude Sonnet 4 has cheaper output pricing at $15.00/M tokens.
Claude Sonnet 4 scores higher on coding benchmarks with a score of 29.4, compared to GPT-4's score of 13.1.
Claude Sonnet 4 has a 1,000,000 token context window, while GPT-4 has a 8,191 token context window.
Claude Sonnet 4 supports vision. GPT-4 does not support vision.