Claude Sonnet 5 vs GPT-5.5

API pricing, context window and capabilities for Claude Sonnet 5 and GPT-5.5, side by side. Prices are the cheapest serving route per 1M tokens, verified against LiteLLM and OpenRouter.

Verdict

computed from the published numbers

Claude Sonnet 5 wins on price. GPT-5.5 wins on coding, on intelligence and on context window.

Price
Claude Sonnet 5
Coding
GPT-5.5
Intelligence
GPT-5.5
Context window
GPT-5.5

Key takeaways

who wins on what, from the published numbers

Claude Sonnet 5 wins

  • Cheaper input ($2.00 vs $5.00 /1M)
  • Cheaper output ($10.00 vs $30.00 /1M)
  • More serving providers (4 vs 2)

GPT-5.5 wins

  • Larger context window (1M vs 1.1M)
  • Has web search
Cheaper overall
Claude Sonnet 5
$2.00 + $10.00 /1M
Larger context
GPT-5.5
1.1M
More providers
Claude Sonnet 5
4 providers

Pricing & specs

cheapest serving route · per 1M tokens
Claude Sonnet 5GPT-5.5
Input $/1M$2.00 best$5.00
Output $/1M$10.00 best$30.00
Context window1M 1.1M best
Max output128K 128K
Serving providers4 best2
Released2026-06-30 2026-04-23

Benchmarks

Artificial Analysis indices, side by side
Claude Sonnet 5GPT-5.5
Intelligence53.4 54.8 best
Coding71.5 74.9 best
GPQA Diamond91% 94% best
Output speed67 t/s 87 t/s best
Latency (TTFT)42.19s 23.21s best

Cost calculator

choose a serving route for each side
Input tokens / month
Output tokens / month
Claude Sonnet 5
via Amazon Bedrock
$20
GPT-5.5
via Azure
$55

Capabilities

feature support, side by side
FeatureClaude Sonnet 5GPT-5.5
Vision
Tool use
Reasoning
Audio
Prompt caching
Structured output
Web search

Related comparisons

Frequently asked questions

Which is cheaper, Claude Sonnet 5 or GPT-5.5?
Claude Sonnet 5 is cheaper for input ($2.00 vs $5.00 per 1M tokens). Claude Sonnet 5 is cheaper for output ($10.00 vs $30.00 per 1M tokens).
What is the context window difference between Claude Sonnet 5 and GPT-5.5?
Claude Sonnet 5 has a 1M-token context window and GPT-5.5 has 1.1M tokens, so GPT-5.5 can take a larger prompt.
How do Claude Sonnet 5 and GPT-5.5 compare on benchmarks?
On the tracked Artificial Analysis indices, GPT-5.5 leads on coding, and GPT-5.5 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