Is Gemini 2.5 Flash or Gemini 2.5 Pro cheaper?

For a typical request (10,000 input + 2,000 output tokens), Gemini 2.5 Flash is cheaper — about 75% less, or roughly $2450 saved per 100,000 requests. Gemini 2.5 Flash runs $0.3/$2.5 per 1M input/output tokens; Gemini 2.5 Pro runs $1.25/$10.

Which has the larger context window?

Both support a 1,000,000-token context window.

How accurate are these token counts?

Gemini 2.5 Flash: Approximated with o200k_base; drift typically ~3% on English and code. Gemini 2.5 Pro: Approximated with o200k_base; drift typically ~3% on English and code. The dollar math itself is exact once the token count is known.

Gemini 2.5 Flash vs Gemini 2.5 Pro: pricing & cost comparison

On input tokens, Gemini 2.5 Flash is the cheaper of the two — 76% less per million ($0.3 vs $1.25). On output, Gemini 2.5 Flash is 75% cheaper ($2.5 vs $10) — and since output is usually the dominant cost driver, that gap matters more than it looks.

Side by side

	Gemini 2.5 Flash	Gemini 2.5 Pro
Input / 1M tokens	$0.3	$1.25
Output / 1M tokens	$2.5	$10
Context window	1,000,000	1,000,000
Token-count accuracy	±3%	±3%
Cost — 10,000 input + 2,000 output tokens	$0.008	$0.0325

What a real request costs

Take a representative turn — 10,000 input + 2,000 output tokens. Gemini 2.5 Flash comes to $0.008, Gemini 2.5 Pro to $0.0325. Across 100,000 requests that's a $2450 swing in favour of Gemini 2.5 Flash. To run the numbers on your actual prompt, paste it into the calculator and toggle Compare across all models.

Which should you pick?

Both are Google models, so you can move between them without changing SDKs or re-tokenising — route the routine 80% of traffic to the cheaper one and reserve Gemini 2.5 Pro for the genuinely hard requests. See the full breakdown on the dedicated pages for Gemini 2.5 Flash and Gemini 2.5 Pro.

FAQ

Is Gemini 2.5 Flash or Gemini 2.5 Pro cheaper?: For a typical request (10,000 input + 2,000 output tokens), Gemini 2.5 Flash is cheaper — about 75% less, or roughly $2450 saved per 100,000 requests. Gemini 2.5 Flash runs $0.3/$2.5 per 1M input/output tokens; Gemini 2.5 Pro runs $1.25/$10.
Which has the larger context window?: Both support a 1,000,000-token context window.
How accurate are these token counts?: Gemini 2.5 Flash: Approximated with o200k_base; drift typically ~3% on English and code. Gemini 2.5 Pro: Approximated with o200k_base; drift typically ~3% on English and code. The dollar math itself is exact once the token count is known.