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

Claude Sonnet 4.5 vs Gemini 2.5 Flash

On price alone, Gemini 2.5 Flash (Google) runs about 86% 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 Gemini 2.5 Flash
Input / MTok $3 $0.30
Output / MTok $15 $2.50
Context window 200K 1M
Max output 64K 66K
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 Gemini 2.5 Flash Cheaper
Light — chatbot 0.5K in / 0.2K out · 200 req/day $27.00 $3.90 Gemini 2.5 Flash
Typical — assistant 2K in / 0.5K out · 1K req/day $405 $55.50 Gemini 2.5 Flash
Heavy — RAG / agent 8K in / 2K out · 5K req/day $8,100 $1,110 Gemini 2.5 Flash

Which should you pick?

Frequently asked questions

Is Claude Sonnet 4.5 or Gemini 2.5 Flash cheaper?

Gemini 2.5 Flash is cheaper — roughly 86% less per month on a typical assistant workload (2K input + 500 output tokens, 1,000 requests/day).

What do Claude Sonnet 4.5 and Gemini 2.5 Flash cost per million tokens?

Claude Sonnet 4.5 is $3 per million input tokens and $15 per million output. Gemini 2.5 Flash is $0.30 input and $2.50 output. Prices are first-party API list rates as of 2026-07-04.

Which has the larger context window, Claude Sonnet 4.5 or Gemini 2.5 Flash?

Gemini 2.5 Flash does, at 1M tokens versus 200K for Claude Sonnet 4.5.

When should I choose Claude Sonnet 4.5 over Gemini 2.5 Flash?

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 Gemini 2.5 Flash does the same job for less.

Related comparisons

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