Gemini 2.0 Flash (by Google)

Overview

Google’s latency-optimized Gemini model for everyday text and multimodal tasks (high-speed multimodal responses).

---

Quick facts

• Modes: Text → Text · Image → Text · Video → Text

---

What it’s great for

• Rapid drafting and Q&A with minimal latency

• Generating captions or descriptions for supplied visuals

• Converting short clips into concise summaries

---

Copy-and-paste prompts

Summarize the notes in `input_texts` into three stakeholder takeaways.

Provide descriptive alt text for the uploaded lifestyle photo.

Create a 5-sentence recap of the attached pitch video.

Draft a friendly follow-up email answering the questions in `input_texts`.

---

Parameters

Control	Type	Default	Notes
Prompt	Text	—	Natural-language instruction (required)
Input Texts	List	—	Optional supporting snippets to ground responses

---

Modes & endpoints (summary)

Mode	Estimated time	Required inputs	Typical use
Text → Text	4 s	Prompt, optional Input Texts	Fast drafting and Q&A
Image → Text	4 s	Prompt, Image(s)	Image captions or scene notes
Video → Text	4 s	Prompt, Video(s)	Short clip recaps

---

Prompt tips

• Attach transcripts or briefs in Input Texts to ground the response

• Request bullet counts or structured formats to manage token usage

---

Safety

Moderation is enforced under Google AI policies—avoid disallowed or sensitive content.

---