Price Per TokenPrice Per Token
Anthropic
Anthropic
vs
Anthropic
Anthropic

Claude Opus 4.6 vs Claude Sonnet 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 4.6 wins:

  • Higher intelligence benchmark
  • Better at coding

Claude Sonnet 4 wins:

  • Cheaper input tokens
  • Cheaper output tokens
  • Faster response time
  • Better at math
  • Has reasoning mode
  • Supports tool calls
Price Advantage
Claude Sonnet 4
Benchmark Advantage
Claude Opus 4.6
Context Window
Claude Sonnet 4
Speed
Claude Sonnet 4

Pricing Comparison

Price Comparison

MetricClaude Opus 4.6Claude Sonnet 4Winner
Input (per 1M tokens)$5.00$3.00 Claude Sonnet 4
Output (per 1M tokens)$25.00$15.00 Claude Sonnet 4
Cache Read (per 1M)$500000.00$300000.00 Claude Sonnet 4
Cache Write (per 1M)$6250000.00$3750000.00 Claude Sonnet 4
Using a 3:1 input/output ratio, Claude Sonnet 4 is 40% cheaper overall.

Claude Opus 4.6 Providers

Amazon Bedrock $5.00 (Cheapest)
Google $5.00 (Cheapest)
Anthropic $5.00 (Cheapest)

Claude Sonnet 4 Providers

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

Benchmark Comparison

8
Benchmarks Compared
3
Claude Opus 4.6 Wins
0
Claude Sonnet 4 Wins

Benchmark Scores

BenchmarkClaude Opus 4.6Claude Sonnet 4Winner
Intelligence Index
Overall intelligence score
46.433.0
Coding Index
Code generation & understanding
47.630.6
Math Index
Mathematical reasoning
-38.0-
MMLU Pro
Academic knowledge
-83.7-
GPQA
Graduate-level science
84.068.3
LiveCodeBench
Competitive programming
-44.9-
Aider
Real-world code editing
-61.3-
AIME
Competition math
-40.7-
Claude Opus 4.6 significantly outperforms in coding benchmarks.

Cost vs Quality

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

Context & Performance

Context Window

Claude Opus 4.6
1,000,000
tokens
Max output: 128,000 tokens
Claude Sonnet 4
1,000,000
tokens
Max output: 64,000 tokens

Speed Performance

MetricClaude Opus 4.6Claude Sonnet 4Winner
Tokens/second0.0 tok/s70.3 tok/s
Time to First Token0.00s1.14s
Claude Sonnet 4 responds Infinity% faster on average.

Capabilities

Feature Comparison

FeatureClaude Opus 4.6Claude Sonnet 4
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyClaude Opus 4.6Claude Sonnet 4
LicenseProprietaryProprietary
AuthorAnthropicAnthropic
ReleasedFeb 2026May 2025

Claude Opus 4.6 Modalities

Input
textimage
Output
text

Claude Sonnet 4 Modalities

Input
imagetextfile
Output
text

Related Comparisons

Compare Claude Opus 4.6 with:

Compare Claude Sonnet 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 Opus 4.6 scores higher on coding benchmarks with a score of 47.6, compared to Claude Sonnet 4's score of 30.6.
Claude Opus 4.6 has a 1,000,000 token context window, while Claude Sonnet 4 has a 1,000,000 token context window.
Claude Opus 4.6 supports vision. Claude Sonnet 4 supports vision.