token.app › Compare › GPT-4 Turbo Preview vs Claude Sonnet 5

GPT-4 Turbo Preview vs Claude Sonnet 5

Claude Sonnet 5 is 3.8× cheaper per token on a blended 3:1 basis. Claude Sonnet 5 accepts the larger context window (1M).

Head to head
Blended price uses a 3:1 input:output mix
GPT-4 Turbo PreviewClaude Sonnet 5
ProviderOpenAIAnthropic
Input $/1M$10.00$2.00
Output $/1M$30.00$10.00
Blended $/1M$15.00$4.00
Context window128K1M
Max output4K128K
ReleasedJan 2024Jun 2026
LicenceProprietaryProprietary
Choose GPT-4 Turbo Preview if…
  • No clear advantage on the data we hold.
Choose Claude Sonnet 5 if…
  • Costs less per token — $4.00 vs $15.00 blended
  • Larger context window (1M)
  • Newer model (released Jun 2026)
FAQ
Which is better, GPT-4 Turbo Preview or Claude Sonnet 5?
We do not hold independently-run benchmark scores covering both GPT-4 Turbo Preview and Claude Sonnet 5, so we make no quality claim. Their pricing and specifications are compared on this page.
Is GPT-4 Turbo Preview cheaper than Claude Sonnet 5?
Claude Sonnet 5 is cheaper: $4.00 versus $15.00 per million tokens blended at 3:1 input:output. Input alone: $10.00 vs $2.00. Output alone: $30.00 vs $10.00.
What context windows do GPT-4 Turbo Preview and Claude Sonnet 5 have?
GPT-4 Turbo Preview: 128,000 tokens. Claude Sonnet 5: 1,000,000 tokens.
Who makes GPT-4 Turbo Preview and Claude Sonnet 5?
GPT-4 Turbo Preview is made by OpenAI. Claude Sonnet 5 is made by Anthropic.
Related comparisons
GPT-4 Turbo Preview full details Claude Sonnet 5 full details GPT-4 Turbo Preview vs Ling 3.0 Tiny (free) GPT-4 Turbo Preview vs Muse Spark 1.2 GPT-4 Turbo Preview vs Qwen3.8 Max GPT-4 Turbo Preview vs DeepSeek V4 Flash Latest GPT-4 Turbo Preview vs DeepSeek V4 Flash 0731 GPT-4 Turbo Preview vs Inkling Small