Identity
- Status
- preview
- Developer ID
gemini-2.5-computer-use-preview-10-2025- Released
- Not reported
- Version
- Gemini Computer Use
- License
- Unknown
Gemini Computer Use is a specialized model for viewing screens and producing browser UI actions.
| Provider | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M | Observed | Evidence |
|---|---|---|---|---|---|---|
Google AIAvailable | $1.25 | $10.00 | — | — | Aug 29, 2026 | Provider-reported |
At a Glance
gemini-2.5-computer-use-preview-10-2025This page represents one developer model product. Dated API snapshots, serving endpoints, pricing, regions, quantizations, and service tiers attach as versioned aliases or provider details and never create duplicate public model records.
Primary Evidence
Comparable Peers
| A | Pair | B | Context |
|---|---|---|---|
Gemini Computer UseGoogle DeepMind | vs | GPT-6 AstraOpenAI | cross-developer peerstext |
Gemini Computer UseGoogle DeepMind | vs | Claude Haiku 4.5Anthropic | cross-developer peerstext |
Gemini Computer UseGoogle DeepMind | vs | Gemini 2.5 FlashGoogle DeepMind | family variantstext |
Gemini Computer UseGoogle DeepMind | vs | Gemini 2.5 ProGoogle DeepMind | family variantstext |
Gemini Computer UseGoogle DeepMind | vs | Gemini 3.1 Flash LiteGoogle DeepMind | family variantstext |
Gemini Computer UseGoogle DeepMind | vs | Gemini 3.7 FlashGoogle DeepMind | family variantstext |
Gemini Computer UseGoogle DeepMind | vs | GPT-4.1 NanoOpenAI | cross-developer peerstext |
Gemini Computer UseGoogle DeepMind | vs | GPT-5 MiniOpenAI | cross-developer peerstext |
Gemini Computer UseGoogle DeepMind | vs | GPT-5 ProOpenAI | cross-developer peerstext |
Gemini Computer UseGoogle DeepMind | vs | GPT-5.3 CodexOpenAI | cross-developer peerstext |
Gemini Computer UseGoogle DeepMind | vs | o3-proOpenAI | cross-developer peerstext |
Gemini Computer UseGoogle DeepMind | vs | GLM 5V TurboZ.ai | cross-developer peerstext |
Questions
Gemini Computer Use is a specialized model for viewing screens and producing browser UI actions. It is developed by Google DeepMind and its current sourced lifecycle status is preview.
Gemini Computer Use's current record lists Text and Image as input and Text as output.
The current record lists a 128K-token context window and a maximum output of 64K tokens.
Gemini Computer Use is marked as API-available. The directly sourced provider records currently include Google AI and Google Gemini.
The lowest directly sourced prices currently attached to Gemini Computer Use are $1.25 per million input tokens through Google AI and $10.00 per million output tokens through Google AI. Prices are provider-specific and should be checked against each cited observation date.
Gemini Computer Use's recorded capabilities are generation, reasoning, and tools. Its supported tasks are computer-use, image, and text.
Gemini Computer Use is not marked as an open-weight model. Self-hosting is marked as unsupported, with no license recorded.
No predecessor is recorded. No successor is recorded. Recorded aliases are gemini-2.5-computer-use-preview-10-2025.
The current compatible peer set includes GPT-6 Astra, Claude Haiku 4.5, Gemini 2.5 Flash, Gemini 2.5 Pro, and Gemini 3.1 Flash Lite. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →
Gemini Computer Use was last verified Aug 29, 2026 from Google DeepMind's primary source, “Gemini 2.5 Computer Use Preview | Gemini API.” The evidence is classified as official fact.