Claude 3 Opus vs Claude 4 Sonnet

API pricing, context window and capabilities for Claude 3 Opus and Claude 4 Sonnet, side by side. Prices are the cheapest serving route per 1M tokens, verified against LiteLLM and OpenRouter.

Verdict

computed from the published numbers

Claude 4 Sonnet wins on price, on coding and on intelligence.

Price
Claude 4 Sonnet
Coding
Claude 4 Sonnet
Intelligence
Claude 4 Sonnet
Context window
Tied

Key takeaways

who wins on what, from the published numbers

Claude 3 Opus wins

No clear edge on the tracked metrics.

Claude 4 Sonnet wins

  • Cheaper input ($15.00 vs $3.00 /1M)
  • Cheaper output ($75.00 vs $15.00 /1M)
  • Higher max output (4K vs 200K)
  • More serving providers (2 vs 4)
  • Supports prompt caching
Cheaper overall
Claude 4 Sonnet
$3.00 + $15.00 /1M
Larger context
Tied
More providers
Claude 4 Sonnet
4 providers

Pricing & specs

cheapest serving route · per 1M tokens
Claude 3 OpusClaude 4 Sonnet
Input $/1M$15.00 $3.00 best
Output $/1M$75.00 $15.00 best
Context window200K 200K
Max output4K 200K best
Serving providers2 4 best
Released2024-03-04 n/a

Benchmarks

Artificial Analysis indices, side by side
Claude 3 OpusClaude 4 Sonnet
Intelligence11.8 25.5 best
Coding19.5 37.6 best
GPQA Diamond49% 68% best

Cost calculator

choose a serving route for each side
Input tokens / month
Output tokens / month
Claude 3 Opus
via Vercel AI Gateway
$150
Claude 4 Sonnet
via Replicate
$30

Capabilities

feature support, side by side
FeatureClaude 3 OpusClaude 4 Sonnet
Vision
Tool use
Reasoning
Audio
Prompt caching
Structured output
Web search

Related comparisons

Frequently asked questions

Which is cheaper, Claude 3 Opus or Claude 4 Sonnet?
Claude 4 Sonnet is cheaper for input ($15.00 vs $3.00 per 1M tokens). Claude 4 Sonnet is cheaper for output ($75.00 vs $15.00 per 1M tokens).
What is the context window difference between Claude 3 Opus and Claude 4 Sonnet?
Both Claude 3 Opus and Claude 4 Sonnet have about a 200K-token context window.
How do Claude 3 Opus and Claude 4 Sonnet compare on benchmarks?
On the tracked Artificial Analysis indices, Claude 4 Sonnet leads on coding, and Claude 4 Sonnet leads on intelligence.
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI