Last verified
RETIRED JUL 28 2026COMPUTER USEdocumented elsewhereTEXT + VISIONNO CACHE SKU

Gemini 2.5 Computer Use Preview API Pricing

Retired July 28, 2026: Google shut gemini-2.5-computer-use-preview-10-2025 down on that date and names Gemini 3.8 Flash as the replacement; computer use is now billed as ordinary tokens at the chosen model's rates. Gemini 2.5 Computer Use Preview was Google's browser-agent preview with Gemini Pro-style tiering. $1.25/M input, $10/M output. The base tier is shown here; Google also lists a higher tier above 200K input tokens.

Input - per 1M tokens
$1.25/M
Source Google preview
Output - per 1M tokens
$10.00/M
Use for cost checks preview
Cached input
$1.25/M
Cache no separate SKU not listed
Effective - agentic blend
$1.95/M
92/8 split - no cache
§ 01 / TERMINAL

Gemini 2.5 Computer Use Preview API cost calculator.

Calculator pre-loaded with Gemini 2.5 Computer Use Preview rates. Tweak spend, output mix, or cache hit rate to compare this model with current alternatives.

$ /mo
Workload split
Tokens you can process
—
Words equivalent (English)
—
Effective rate
—
Open full calculator (all models · share URL · CSV) →
§ 02 / SCENARIOS

Gemini 2.5 Computer Use Preview cost on real workloads.

§ 03 / TOKENIZER

Gemini 2.5 Computer Use Preview token counter and cost.

What's a token →
Estimate · gemini-tokenizer-estimate · ≈4.2 chars/token Auto-counts as you type

This is a chars-per-token approximation, not a real tokenizer. Actual tokens vary by language, code density, and tool-call overhead — counts are typically ±10–20% off for English prose, more for code or non-Latin scripts. For exact billing, use the vendor's official tokenizer.

Characters 279
Words 42
Tokens (estimated) 66 tokens
Cost as input · uncached $0.00008 USD
Cost as output · uncached $0.00066 USD
§ 04 / SHELF

Gemini 2.5 Computer Use Preview vs similar models.

All models →
Model Input /M Output /M Effective blended Context Best for
Gemini 2.5 Computer Use Preview Current $1.25 $10.00 $1.95 agentic 92/8 documented elsewhere Browser-agent preview loops
Gemini 3.8 Flash $0.75 cache $0.075 $3.75 $0.481 −4.1× · promo 1M Gemini multimodal workloads
Gemini 3.5 Flash-Lite $0.30 cache $0.03 $2.50 $0.272 −7.2× 1M Gemini multimodal workloads
GPT-6.1 Sol $2.00 cache $0.10 $10.00 $1.29 −34% 1.05M OpenAI's balanced model for coding and agents
Claude Sonnet 5.5 $2.00 cache $0.10 $10.00 $1.29 −34% 1M Anthropic's current Sonnet
DeepSeek V4 Pro $1.32 cache $0.044 $3.96 $0.569 −3.4× 1M Low-cost reasoning and coding
§ 05 / DEEP LINKS

Gemini 2.5 Computer Use Preview cost by scenario.

All calculators →

Gemini 2.5 Computer Use Preview API pricing FAQ.

Short answers for teams checking Gemini 2.5 Computer Use Preview pricing, status, and migration choices.

Q · 01 Is Gemini 2.5 Computer Use Preview still available? +
No. Google's deprecations page lists gemini-2.5-computer-use-preview-10-2025 with a shutdown date of July 28, 2026 and names Gemini 3.8 Flash as the replacement. Google's pricing page no longer has a Computer Use row: the tool is charged as regular tokens at the rates of whichever model runs it. This page keeps the last published price for reference.
Q · 02 How much does Gemini 2.5 Computer Use Preview cost? +
Gemini 2.5 Computer Use Preview is listed at $1.25/M input and $10/M output.
Q · 03 Is cached-input pricing included? +
No separate cached-input SKU is listed for this archive entry, so the calculator treats cached input as undiscounted.
Q · 04 What should teams compare it against? +
Use the shelf to compare current replacements and nearby models. Snapshot replacement: current same-provider models.
Q · 05 Why keep this page? +
These pages preserve price history, preview economics, and migration context without pretending every older or preview model is the best current default.