Price Per TokenPrice Per Token
Anthropic
Anthropic
vs
Anthropic
Anthropic

Claude Opus 4.5 vs Claude Opus 4.6

A detailed comparison of pricing, benchmarks, and capabilities

OpenClaw

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

101 out of our 303 tracked models have had a price change in February.

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

Key Takeaways

Claude Opus 4.5 wins:

  • Faster response time
  • Better at math
  • Has reasoning mode
  • Supports tool calls

Claude Opus 4.6 wins:

  • Larger context window
  • Higher intelligence benchmark
  • Better at coding
Price Advantage
Claude Opus 4.5
Benchmark Advantage
Claude Opus 4.6
Context Window
Claude Opus 4.6
Speed
Claude Opus 4.5

Pricing Comparison

Price Comparison

MetricClaude Opus 4.5Claude Opus 4.6Winner
Input (per 1M tokens)$5.00$5.00Tie
Output (per 1M tokens)$25.00$25.00Tie
Cache Read (per 1M)$500000.00$500000.00Tie
Cache Write (per 1M)$6250000.00$6250000.00Tie
Both models have similar overall pricing.

Claude Opus 4.5 Providers

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

Claude Opus 4.6 Providers

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

Benchmark Comparison

6
Benchmarks Compared
0
Claude Opus 4.5 Wins
3
Claude Opus 4.6 Wins

Benchmark Scores

BenchmarkClaude Opus 4.5Claude Opus 4.6Winner
Intelligence Index
Overall intelligence score
43.046.4
Coding Index
Code generation & understanding
42.947.6
Math Index
Mathematical reasoning
62.7--
MMLU Pro
Academic knowledge
88.9--
GPQA
Graduate-level science
81.084.0
LiveCodeBench
Competitive programming
73.8--
Claude Opus 4.5 shows stronger mathematical reasoning abilities.

Cost vs Quality

X-axis:
Y-axis:
Loading chart...
Claude Opus 4.5
Other models

Context & Performance

Context Window

Claude Opus 4.5
200,000
tokens
Max output: 64,000 tokens
Claude Opus 4.6
1,000,000
tokens
Max output: 128,000 tokens
Claude Opus 4.6 has a 80% larger context window.

Speed Performance

MetricClaude Opus 4.5Claude Opus 4.6Winner
Tokens/second80.4 tok/s0.0 tok/s
Time to First Token1.63s0.00s
Claude Opus 4.5 responds Infinity% faster on average.

Capabilities

Feature Comparison

FeatureClaude Opus 4.5Claude Opus 4.6
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyClaude Opus 4.5Claude Opus 4.6
LicenseProprietaryProprietary
AuthorAnthropicAnthropic
ReleasedNov 2025Feb 2026

Claude Opus 4.5 Modalities

Input
fileimagetext
Output
text

Claude Opus 4.6 Modalities

Input
textimage
Output
text

Related Comparisons

Compare Claude Opus 4.5 with:

Compare Claude Opus 4.6 with:

Frequently Asked Questions

Claude Opus 4.5 has cheaper input pricing at $5.00/M tokens. Claude Opus 4.5 has cheaper output pricing at $25.00/M tokens.
Claude Opus 4.6 scores higher on coding benchmarks with a score of 47.6, compared to Claude Opus 4.5's score of 42.9.
Claude Opus 4.5 has a 200,000 token context window, while Claude Opus 4.6 has a 1,000,000 token context window.
Claude Opus 4.5 supports vision. Claude Opus 4.6 supports vision.