Google (Gemini) Gemini 2.5 Pro — what it is, when to use it and what to use instead

Summary

Gemini 2.5 Pro is Google's stable Pro-series model, at $1.25 per million input tokens and $10 per million output tokens. It has a 1,048,576-token context window, a 65,536-token output limit and a January 2025 knowledge cutoff.

Google positions Gemini 2.5 Pro as a thinking model for complex problems in code, mathematics and STEM, and for analysing large datasets, codebases and documents in long context. It is listed with a June 2025 update, which makes it one of the oldest models in Google's active line-up here, alongside Gemini 2.5 Flash.

It takes text, image, video, audio and PDF input and returns text, with caching, code execution, file search, function calling, Maps and search grounding, structured outputs, thinking, URL context, the Batch API and flex and priority inference. The Live API is not supported.

No deprecation has been announced for the stable model ID; the 2.5 Pro preview snapshots from 2025 have already been shut down.

Modality

• Text
• Vision

Use case

• Chat
• Coding
• Reasoning
• Agents & tool use
• Long context

Tier

• Frontier

Access

• Hosted API

Specifications

Input price

$1.25 / M tokens

Output price

$10.00 / M tokens

Price band

Premium

Context window

1M tokens

Max output

65.5K tokens

Input

Text, image

Output

Text

Knowledge cutoff

January 2025

Tool use

Yes

Structured output

Yes

Weights licence

not published

Model maker

Google (Gemini)

“unknown” means the figure has not been published, or we have not verified it yet — never that the answer is no. “not published” under the weights licence means this model is not offered with downloadable weights. The price band is ours: it bands the blended price (three parts input to one part output) as budget (≤ $0.50), standard (≤ $3), premium (≤ $12) or flagship.

Lifecycle

Google (Gemini) has not announced a deprecation or shutdown date for this model. That is a statement about what has been published, not a guarantee — providers typically announce a shutdown months ahead, and this page updates when they do.

1. Released 17 June 2025
2. Deprecated not announced
3. Retired not announced

Use it for

• Analyse large codebases, datasets or document sets in a single long-context request.
• Work through maths and STEM problems that need explicit thinking rather than a fast answer.
• Keep a stable Pro-series model in production while the Gemini 3 Pro series is still in preview.

Avoid it when

• Your prompts depend on facts after January 2025, this model's knowledge cutoff.
• Cost per call is a constraint; Gemini 3.8 Flash costs $0.75 / $3.75 against $1.25 / $10 here.
• You need more than 65,536 output tokens in a single response.

Alternatives to consider

• Gemini 3.1 Pro Preview Curated

  Google (Gemini) ● Active

  The newer Pro-series release at $2 / $12 with a February 2026 update, at the cost of being a preview model.

  $2.00 in · $12.00 out / M tokens · 1M context

• Gemini 3.8 Flash Curated

  Google (Gemini) ● Active

  Newer and cheaper at $0.75 / $3.75 with the same limits and modalities.

  $0.75 in · $3.75 out / M tokens · 1M context

• Claude Sonnet 5 Curated

  Anthropic ● Active

  Anthropic's mid tier at $2 / $10 with a 1M-token window and a January 2026 knowledge cutoff.

  $2.00 in · $10.00 out / M tokens · 1M context

• GPT-5.6 Terra Curated

  OpenAI ● Active

  OpenAI's balanced tier at $2 / $12 with a 1.05M-token window and a February 2026 knowledge cutoff.

  $2.00 in · $12.00 out / M tokens · 1.1M context

• Claude Opus 4.5 Derived

  Amazon Bedrock ● Active

  Alternative from Amazon Bedrock, same tier (frontier), similar price; shares chat, coding, reasoning, agents and long-context.

  $5.00 in · $25.00 out / M tokens · 200K context

Curated suggestions were picked by a reviewer, with the reason written by hand. Derived suggestions are ranked from the data — shared tags, the same tier and a comparable price band — not from benchmark scores. Check the capability fit yourself: we track lifecycle, price and specifications.

Sources

• ai.google.dev ↗ https://ai.google.dev/gemini-api/docs/models
• ai.google.dev ↗ https://ai.google.dev/gemini-api/docs/pricing
• ai.google.dev ↗ https://ai.google.dev/gemini-api/docs/deprecations
• ai.google.dev ↗ https://ai.google.dev/gemini-api/docs/models/gemini-2.5-pro

Verified against the source on 10 September 2026. Dataset snapshot 10 September 2026. Providers can change a date without notice — the link above is always the final word.

About this profile

The specifications and dates above are facts from Google (Gemini), with the sources listed. The summary, the use-for and avoid-when lists and the curated alternatives are our assessment: editorial profile reviewed on 21 September 2026 by llm-researcher.