Claude 3.7 Sonnet vs GPT-4o

API pricing, context window and capabilities for Claude 3.7 Sonnet and GPT-4o, side by side. Prices are the cheapest serving route per 1M tokens, verified against LiteLLM and OpenRouter.

Verdict

computed from the published numbers

Claude 3.7 Sonnet wins on intelligence and on context window. GPT-4o wins on price. Benchmark data is unavailable for one or both models.

Price
GPT-4o
Coding
Not called
Intelligence
Claude 3.7 Sonnet
Context window
Claude 3.7 Sonnet

Key takeaways

who wins on what, from the published numbers

Claude 3.7 Sonnet wins

  • Larger context window (200K vs 131K)
  • Higher max output (128K vs 16K)
  • Has reasoning mode

GPT-4o wins

  • Cheaper input ($3.00 vs $2.50 /1M)
  • Cheaper output ($15.00 vs $10.00 /1M)
  • More serving providers (5 vs 6)
  • Supports audio
Cheaper overall
GPT-4o
$2.50 + $10.00 /1M
Larger context
Claude 3.7 Sonnet
200K
More providers
GPT-4o
6 providers

Pricing & specs

cheapest serving route · per 1M tokens
Claude 3.7 SonnetGPT-4o
Input $/1M$3.00 $2.50 best
Output $/1M$15.00 $10.00 best
Context window200K best131K
Max output128K best16K
Serving providers5 6 best
Released2025-02-24 2024-05-13

Benchmarks

Artificial Analysis indices, side by side
Claude 3.7 SonnetGPT-4o
Intelligence23.5 best11.2
Coding36.4 Not available
GPQA Diamond66% best54%
Output speedNot available 99 t/s
Latency (TTFT)Not available 5.19s

Cost calculator

choose a serving route for each side
Input tokens / month
Output tokens / month
Claude 3.7 Sonnet
via Databricks
$30
GPT-4o
via Azure
$23

Capabilities

feature support, side by side
FeatureClaude 3.7 SonnetGPT-4o
Vision
Tool use
Reasoning
Audio
Prompt caching
Structured output
Web search

Related comparisons

Frequently asked questions

Which is cheaper, Claude 3.7 Sonnet or GPT-4o?
GPT-4o is cheaper for input ($3.00 vs $2.50 per 1M tokens). GPT-4o is cheaper for output ($15.00 vs $10.00 per 1M tokens).
What is the context window difference between Claude 3.7 Sonnet and GPT-4o?
Claude 3.7 Sonnet has a 200K-token context window and GPT-4o has 131K tokens, so Claude 3.7 Sonnet can take a larger prompt.
How do Claude 3.7 Sonnet and GPT-4o compare on benchmarks?
On the tracked Artificial Analysis indices, Claude 3.7 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