Comparison · prices as of 2026-07-04 · re-verified 2026-08-18

Claude Sonnet 4.5 vs GPT-5 mini

On price alone, GPT-5 mini (OpenAI) runs about 89% cheaper than Claude Sonnet 4.5 for a typical chat workload (2K input + 500 output tokens, 1,000 requests/day). Whether that's the right trade depends on the capability gap — the breakdown below shows where each one wins.

Price per million tokens

Spec Claude Sonnet 4.5 GPT-5 mini
Input / MTok $3 $0.25
Output / MTok $15 $2
Context window 200K 400K
Max output 64K 128K
Class workhorse workhorse

Estimated monthly cost by workload

Same models, three realistic usage levels. The gap between them scales with volume, so the right pick can change as you grow.

Workload Claude Sonnet 4.5 GPT-5 mini Cheaper
Light — chatbot 0.5K in / 0.2K out · 200 req/day $27.00 $3.15 GPT-5 mini
Typical — assistant 2K in / 0.5K out · 1K req/day $405 $45.00 GPT-5 mini
Heavy — RAG / agent 8K in / 2K out · 5K req/day $8,100 $900 GPT-5 mini

Which should you pick?

Frequently asked questions

Is Claude Sonnet 4.5 or GPT-5 mini cheaper?

GPT-5 mini is cheaper — roughly 89% less per month on a typical assistant workload (2K input + 500 output tokens, 1,000 requests/day).

What do Claude Sonnet 4.5 and GPT-5 mini cost per million tokens?

Claude Sonnet 4.5 is $3 per million input tokens and $15 per million output. GPT-5 mini is $0.25 input and $2 output. Prices are first-party API list rates as of 2026-07-04.

Which has the larger context window, Claude Sonnet 4.5 or GPT-5 mini?

GPT-5 mini does, at 400K tokens versus 200K for Claude Sonnet 4.5.

When should I choose Claude Sonnet 4.5 over GPT-5 mini?

Both are workhorse-class models, so choose Claude Sonnet 4.5 when it measurably wins on your own evals or you prefer its provider (Anthropic); otherwise GPT-5 mini does the same job for less.

Related comparisons

Sources: Anthropic pricing · OpenAI pricing. Run your own numbers in the cost calculator.