Claude 3 Opus vs GPT-4 Turbo

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

Verdict

computed from the published numbers

Claude 3 Opus wins on intelligence and on context window. GPT-4 Turbo wins on price and on coding.

Price
GPT-4 Turbo
Coding
GPT-4 Turbo
Intelligence
Claude 3 Opus
Context window
Claude 3 Opus

Key takeaways

who wins on what, from the published numbers

Claude 3 Opus wins

  • Larger context window (200K vs 128K)
  • Supports structured output

GPT-4 Turbo wins

  • Cheaper input ($15.00 vs $10.00 /1M)
  • Cheaper output ($75.00 vs $30.00 /1M)
  • More serving providers (2 vs 3)
  • Supports prompt caching
Cheaper overall
GPT-4 Turbo
$10.00 + $30.00 /1M
Larger context
Claude 3 Opus
200K
More providers
GPT-4 Turbo
3 providers

Pricing & specs

cheapest serving route · per 1M tokens
Claude 3 OpusGPT-4 Turbo
Input $/1M$15.00 $10.00 best
Output $/1M$75.00 $30.00 best
Context window200K best128K
Max output4K 4K
Serving providers2 3 best
Released2024-03-04 2023-11-06

Benchmarks

Artificial Analysis indices, side by side
Claude 3 OpusGPT-4 Turbo
Intelligence11.8 best7.9
Coding19.5 21.5 best
GPQA Diamond49% Not available
Output speedNot available 12 t/s
Latency (TTFT)Not available 19.20s

Cost calculator

choose a serving route for each side
Input tokens / month
Output tokens / month
Claude 3 Opus
via Vercel AI Gateway
$150
GPT-4 Turbo
via Azure
$80

Capabilities

feature support, side by side
FeatureClaude 3 OpusGPT-4 Turbo
Vision
Tool use
Reasoning
Audio
Prompt caching
Structured output
Web search

Related comparisons

Frequently asked questions

Which is cheaper, Claude 3 Opus or GPT-4 Turbo?
GPT-4 Turbo is cheaper for input ($15.00 vs $10.00 per 1M tokens). GPT-4 Turbo is cheaper for output ($75.00 vs $30.00 per 1M tokens).
What is the context window difference between Claude 3 Opus and GPT-4 Turbo?
Claude 3 Opus has a 200K-token context window and GPT-4 Turbo has 128K tokens, so Claude 3 Opus can take a larger prompt.
How do Claude 3 Opus and GPT-4 Turbo compare on benchmarks?
On the tracked Artificial Analysis indices, GPT-4 Turbo leads on coding, and Claude 3 Opus 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