Gemini 2.5 Computer Use

Retired

Specialist UI-automation model that emitted browser/computer actions from a screenshot - not a general chat model; preview-only for its whole life. CONFIRMED RETIRED 2026-10-02 on the only signal this catalog accepts for a Google shutdown: Google's deprecations table now carries a row for gemini-2.5-computer-use-preview-10-2025 - release date October 7, 2025, shutdown date July 28, 2026, recommended replacement gemini-3.8-flash - and that row is grey (a literal class="row-gray" on the <tr>; the page's legend reads "Already-shutdown models are indicated with gray backgrounds"). check-lifecycle-drift.mjs read the marker and reported Google stating shut-down against our preview. The row did not exist on the 2026-09-29 read, and the model had appeared nowhere in the table on 2026-08-05 or since, so Google published the lifecycle data and the shutdown marker together between 2026-09-29 and 2026-10-02; in the same edit the pricing page dropped its Computer Use section and its Computer Use tool note now reads 'standard Gemini 3.8 Flash pricing' where it used to point at this model's table. released, retires_on and replacement were null until 2026-10-02 because Google published nothing; they now carry the table's values, and deprecated_on stays null because the table has no such column. Last published rates, kept for the record: input image+text, output text; 128,000 input / 64,000 output tokens; priced on the same two-tier scale as gemini-2.5-pro, $1.25/M in and $10.00/M out at <=200K prompt tokens, rising to $2.50/M and $15.00/M above it - the base tier is stored here, matching the gemini-2-5-pro row's convention. Cached-input rate was never published. Google's model page had noted that Gemini 3 Pro and Flash have built-in computer use without a separate model.

Gemini 2.5 Computer Use by Google costs $1.25 per 1M input tokens and $10 per 1M output tokens ($3.44/1M blended), with a 128K (128.000-token) context window. It has been retired (shut down 28 Jul 2026); the recommended migration is Gemini 3.8 Flash.

Last verified: 24 Oct 2026 · sourced from official provider documentation

Retired on 28 Jul 2026

Lifecycle warning

This model has been retired. Recommended migration: Gemini 3.8 Flash.

Read the Gemini 2.5 Computer Use migration guide → replacement & cheapest alternatives

Provider
Google
Status
Retired
Input price
$1.25 / 1M tokens
Output price
$10 / 1M tokens
Cached input
—
Blended price
$3.44 / 1M tokens
Context window
128.000 tokens (128K)
Max output
64.000 tokens
Modality
text, image
Open weights
No — API only
Knowledge cutoff
—
Released
7 Oct 2025
API string
gemini-2.5-computer-use-preview-10-2025

Source: Google official documentation ↗

FAQ

Gemini 2.5 Computer Use — questions & answers

How much does Gemini 2.5 Computer Use cost?

Gemini 2.5 Computer Use is priced at $1.25 per 1M input tokens and $10 per 1M output tokens ($3.44/1M blended at a 3:1 input-to-output ratio).

What is the context window of Gemini 2.5 Computer Use?

Gemini 2.5 Computer Use has a 128.000-token context window (128K), with up to 64.000 output tokens per request.

Is Gemini 2.5 Computer Use still available?

Gemini 2.5 Computer Use has been retired and is no longer available. Its scheduled shutdown date is 28 Jul 2026. The recommended migration is Gemini 3.8 Flash.

Does Gemini 2.5 Computer Use support image or vision input?

Yes — Gemini 2.5 Computer Use accepts image input. Listed modalities: text, image.

Can I self-host Gemini 2.5 Computer Use?

No — Gemini 2.5 Computer Use is proprietary. Its weights are not publicly released, so it is available only through Google's API (or hosted partners), not for self-hosting.

What is the API model string for Gemini 2.5 Computer Use?

The API model identifier for Gemini 2.5 Computer Use is "gemini-2.5-computer-use-preview-10-2025" when calling Google's API.