gemini-2.5-pro-exp-03-25

by Google

Google’s latest experimental model, highly unstable, for experience only. It boasts strong reasoning and coding capabilities, able to "think" before responding, enhancing performance and accuracy in complex tasks. It supports multimodal inputs (text, audio, images, video) and a 1 million token context window, suitable for advanced programming, math, and science tasks. This means Gemini 2.5 can handle more complex problems in coding, science and math, and support more context-aware agents.

API Pricing

Input$1.25 / 1M tokens
Output$5 / 1M tokens
Cache read$0.13 / 1M tokens

Specifications

Modalitiestext, image, audio, video
Featuresstructured outputs, tool calling, long context

FAQ

What is gemini-2.5-pro-exp-03-25?

Google’s latest experimental model, highly unstable, for experience only. It boasts strong reasoning and coding capabilities, able to "think" before responding, enhancing performance and accuracy in complex tasks. It supports multimodal inputs (text, audio, images, video) and a 1 million token context window, suitable for advanced programming, math, and science tasks. This means Gemini 2.5 can handle more complex problems in coding, science and math, and support more context-aware agents.

How much does gemini-2.5-pro-exp-03-25 cost?

On AIHubMix, gemini-2.5-pro-exp-03-25 costs $1.25 per million input tokens and $5 per million output tokens. Cached input reads are billed at $0.13 per million tokens.

What modalities does gemini-2.5-pro-exp-03-25 support?

gemini-2.5-pro-exp-03-25 accepts text, image, audio and video input.

What features does gemini-2.5-pro-exp-03-25 support?

gemini-2.5-pro-exp-03-25 supports structured outputs, tool calling and long context. Per-protocol parameter support is listed in the capability table on this page.

How do I call gemini-2.5-pro-exp-03-25 via API?

gemini-2.5-pro-exp-03-25 is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to gemini-2.5-pro-exp-03-25 — no other code changes needed.

Who develops gemini-2.5-pro-exp-03-25?

gemini-2.5-pro-exp-03-25 is developed by Google. AIHubMix aggregates it alongside models from other providers behind one API and one bill.

More from Google

gemini-3.6-flash

by Google

Gemini 3.6 Flash provides sustained frontier-level intelligence optimized for real-world…

$1.5/1M in · $7.5/1M out
1,048,576 tokens context

gemini-3.1-flash-lite-image

by Google

Google's newest, most compact, and most cost-effective image generation and editing…

$0.25/1M in · $1.5/1M out

gemini-3.5-flash-lite

by Google

Gemini 3.5 Flash-Lite is a low-latency, cost-effective multimodal model optimized for…

$0.3/1M in · $2.5/1M out
1,048,576 tokens context

gemini-3.5-flash-lite-free

by Google

Gemini 3.5 Flash-Lite free version: Free model resources are limited and provided only…

1,048,576 tokens context

gemini-3.6-flash-free

by Google

Gemini 3.6 Flash free version: fFree model resources are limited and provided only for…

1,000,000 tokens context

gemini-3.5-flash

by Google

Gemini 3.5 Flash provides sustained frontier-level intelligence optimized for real-world…

$1.5/1M in · $9/1M out
1,000,000 tokens context

Use gemini-2.5-pro-exp-03-25 via the AIHubMix unified API — one interface for every major LLM.