Skip to content

Gemini 2.5 Pro Preview 06-05 vs Gemini 4 Hydrogen

Gemini 2.5 Pro Preview 06-05 (Google) and Gemini 4 Hydrogen (Google) are listed at different prices. Gemini 2.5 Pro Preview 06-05 costs less for input, $1.25 per 1M tokens against $1.50; Gemini 4 Hydrogen costs less for output, $7.50 per 1M tokens against $10.00. Both hold 1,048,576 tokens of context. Gemini 2.5 Pro Preview 06-05 charges $2.50 and $15.00 per 1M once a prompt passes 200,000 tokens; Gemini 4 Hydrogen keeps one price across its window. Gemini 2.5 Pro Preview 06-05 accepts text, images, files and audio and produces text; Gemini 4 Hydrogen accepts text, images, files, audio and video and produces text.

Google: Gemini 2.5 Pro Preview 06-05 and Google: Gemini 4 Hydrogen both accept text, images, audio, and files, produce text, support tools, structured outputs, response formats, and reasoning, and have a 1,048,576-token context. Gemini 4 Hydrogen also accepts video and has a higher maximum output-token limit.

Compared from catalog data checked

Side by side

0.00 the better figure in a row
Gemini 2.5 Pro Preview 06-05 and Gemini 4 Hydrogen specifications side by side
SpecificationGemini 2.5 Pro Preview 06-05Gemini 4 Hydrogen
Maker Google Google
Added to catalog 5 Jun 2025 12 Nov 2026
Input, per 1M tokens $1.25 $1.50
Output, per 1M tokens $10.00 $7.50
Input above 200K tokensPer 1M; long prompts $2.50 $1.50
Output above 200K tokens $15.00 $7.50
Cached input read, per 1M $0.125 $0.075
Context windowTokens 1,048,576 1,048,576
Max outputTokens 65,536 943,718
Accepts audio, file, image, text audio, file, image, text, video
Produces text text
Tool calling Yes Yes
Structured outputs Yes Yes
Reasoning effort control No Yes

List prices through OpenRouter, in US dollars. Each model's page has its variants, price history and sample outputs.

What the same task costs

List price for one request, from the token counts shown. The same four tasks are priced on every model page.

Check the provider's pageToken counts are estimates, and the two models count tokens differently.
Cost of the same task on Gemini 2.5 Pro Preview 06-05 and Gemini 4 Hydrogen
TaskGemini 2.5 Pro Preview 06-05Gemini 4 Hydrogen
Answer a short question500 in / 300 out $0.0036 $0.0030
Summarise a 50-page PDF25,000 in / 800 out $0.039 $0.044
Review a 2,000-line source file30,000 in / 2,000 out $0.058 $0.060
Read a 300-page contract set150,000 in / 1,500 out $0.203 $0.236

Which to choose

Choose Gemini 2.5 Pro Preview 06-05 if

  • Input tokens cost less: $1.25 against $1.50 per 1M
Gemini 2.5 Pro Preview 06-05 details

Choose Gemini 4 Hydrogen if

  • Output tokens cost less: $7.50 against $10.00 per 1M
  • Your prompts often run past 200K tokens: $1.50 against $2.50 per 1M input tokens there
  • Cached input costs less: $0.075 against $0.125 per 1M
  • You need longer answers in one response: 943,718 tokens against 65,536
  • It has to read video, which the other model does not
  • You want to set how much it reasons before it answers
Gemini 4 Hydrogen details

Neither maker's quality claims are repeated here. The reliable test is your own task: ask both the same question and read the two answers.

Comparison questions

Is Gemini 2.5 Pro Preview 06-05 cheaper than Gemini 4 Hydrogen?

It depends on the job: one costs less for input and the other for output. Gemini 2.5 Pro Preview 06-05 costs $1.25 per 1M input tokens and $10.00 per 1M output tokens; Gemini 4 Hydrogen costs $1.50 and $7.50 as checked on 22 Nov 2026.

Which has the larger context window, Gemini 2.5 Pro Preview 06-05 or Gemini 4 Hydrogen?

Neither: both hold 1,048,576 tokens.

Which is better for coding, Gemini 2.5 Pro Preview 06-05 or Gemini 4 Hydrogen?

This page does not rank models on quality, and it does not repeat either maker's claims. The table shows what each accepts, supports and costs; the reliable test is your own task: give both the same piece of code and compare the answers.

Can I use both Gemini 2.5 Pro Preview 06-05 and Gemini 4 Hydrogen?

Neither is offered in the Upend chat today. Both are listed in the catalog through OpenRouter, with the figures shown here.

Find the model for your task.

Every comparison is computed from the live catalog.

Sign in to Upend

Use an account you already have, or get a one-time code by email.

Use a password instead

For accounts that already have a password. Forgotten it? An emailed code signs you in just the same.