Price Per TokenPrice Per Token
Anthropic
Anthropic
vs
OpenAI
OpenAI

Claude Opus 4.1 vs GPT-4

A detailed comparison of pricing, benchmarks, and capabilities

OpenClaw

Best LLMs for OpenClaw Vote for which model works best with OpenClaw

112 out of our 301 tracked models have had a price change in February.

Get our weekly newsletter on pricing changes, new releases, and tools.

Key Takeaways

Claude Opus 4.1 wins:

  • Cheaper input tokens
  • Larger context window
  • Faster response time
  • Higher intelligence benchmark
  • Supports vision
  • Has reasoning mode

GPT-4 wins:

  • Cheaper output tokens
  • Better at coding
Price Advantage
Claude Opus 4.1
Benchmark Advantage
Claude Opus 4.1
Context Window
Claude Opus 4.1
Speed
Claude Opus 4.1

Pricing Comparison

Price Comparison

MetricClaude Opus 4.1GPT-4Winner
Input (per 1M tokens)$15.00$30.00 Claude Opus 4.1
Output (per 1M tokens)$75.00$60.00 GPT-4
Cache Read (per 1M)$1500000.00N/A Claude Opus 4.1
Cache Write (per 1M)$18750000.00N/A Claude Opus 4.1
Using a 3:1 input/output ratio, Claude Opus 4.1 is 20% cheaper overall.

Claude Opus 4.1 Providers

Amazon Bedrock $15.00 (Cheapest)
Google $15.00 (Cheapest)
Anthropic $15.00 (Cheapest)

GPT-4 Providers

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

Benchmark Comparison

3
Benchmarks Compared
1
Claude Opus 4.1 Wins
0
GPT-4 Wins

Benchmark Scores

BenchmarkClaude Opus 4.1GPT-4Winner
Intelligence Index
Overall intelligence score
23.612.8
Coding Index
Code generation & understanding
-13.1-
Aider
Real-world code editing
-67.7-
GPT-4 significantly outperforms in coding benchmarks.

Cost vs Quality

X-axis:
Y-axis:
Loading chart...
Other models

Context & Performance

Context Window

Claude Opus 4.1
200,000
tokens
Max output: 32,000 tokens
GPT-4
8,191
tokens
Max output: 4,096 tokens
Claude Opus 4.1 has a 96% larger context window.

Speed Performance

MetricClaude Opus 4.1GPT-4Winner
Tokens/second40.1 tok/s32.2 tok/s
Time to First Token1.45s0.72s
Claude Opus 4.1 responds 25% faster on average.

Capabilities

Feature Comparison

FeatureClaude Opus 4.1GPT-4
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyClaude Opus 4.1GPT-4
LicenseProprietaryProprietary
AuthorAnthropicOpenAI
ReleasedAug 2025May 2023

Claude Opus 4.1 Modalities

Input
imagetextfile
Output
text

GPT-4 Modalities

Input
text
Output
text

Related Comparisons

Compare Claude Opus 4.1 with:

Compare GPT-4 with:

Frequently Asked Questions

Claude Opus 4.1 has cheaper input pricing at $15.00/M tokens. GPT-4 has cheaper output pricing at $60.00/M tokens.
GPT-4 scores higher on coding benchmarks with a score of 13.1, compared to Claude Opus 4.1's score of N/A.
Claude Opus 4.1 has a 200,000 token context window, while GPT-4 has a 8,191 token context window.
Claude Opus 4.1 supports vision. GPT-4 does not support vision.