Gemini 2.5 Pro

Overview

Freshness note: Model capabilities, limits, and pricing can change quickly. This profile is a point-in-time snapshot last verified on June 8, 2026.

Gemini 2.5 Pro is Google’s older high-capability 2.5 tier for difficult multimodal and long-context tasks. Google’s current deprecation table lists gemini-2.5-pro with an October 16, 2026 shutdown date and names gemini-3.1-pro-preview as the recommended replacement.

This entry remains useful for compatibility planning, regression tests, and reading older Gemini Pro references. It should not be the default starting point for new premium Gemini API work.

Capabilities

The model remains effective for large-context reasoning, technical analysis, multimodal interpretation, and harder coding or STEM-style reasoning tasks. The practical issue is not immediate capability collapse; it is lifecycle. Any active deployment pinned to gemini-2.5-pro now needs a migration plan before the published shutdown date.

Technical Details

Google’s model docs still list Gemini 2.5 Pro with a 1,048,576 token input window and a 65,536 token output limit. It supports text, image, video, audio, and PDF inputs plus tooling features such as code execution, file search, function calling, search grounding, Google Maps grounding, URL context, and structured outputs.

Migration target:

• gemini-3.1-pro-preview

Pricing & Access

Google’s current Gemini API pricing lists Gemini 2.5 Pro at $1.25 per 1M input tokens and$10 per 1M output tokens for prompts up to 200K tokens, with $2.50 /$15 above that threshold. Batch pricing is half that level, and context caching/storage pricing is published separately for the paid tier. Access remains available through Google AI Studio and Vertex AI until the endpoint is shut down.

Best Use Cases

Best for existing systems that need a controlled migration window, regression comparisons, and compatibility testing against Gemini 3.1 Pro Preview. New systems should choose Gemini 3.1 Pro Preview for the premium lane or Gemini 3.5 Flash when fast stable behavior is more important than Pro-tier depth.

Comparisons

Compared with GPT-5.5, Gemini 2.5 Pro is now mainly relevant for Google ecosystem compatibility and migration planning. Compared with Gemini 3.1 Pro Preview, 2.5 Pro is the older endpoint with a dated shutdown path. Compared with Claude Opus 4.8, tradeoffs usually center on reasoning style, lifecycle risk, and platform integration.