Skip to main content

Gemini 2.5 Flash

Google's fast, cheap multimodal model with a 1M-token context window.

Gemini 2.5 Flash specifications

ProviderGoogle
Context window1,000,000 tokens (1.0M)
Input price$0.10 / 1M tokens
Output price$0.40 / 1M tokens
InputsText, Images, Audio, Video
Reasoning modeYes
Vision (image input)Yes
Tool / function callingYes
Native real-time webNo
Open-weightNo

Pricing & context web-verified June 2026 confirm on Google's pricing page.

What Gemini 2.5 Flash is best for

  • Cheap long-context processing
  • High-volume multimodal tasks
  • Latency-sensitive apps

How to prompt Gemini 2.5 Flash

  • Hard to beat for cheap long-context — a 1M window at a low price.
  • Use it for bulk multimodal extraction and triage.
  • Escalate to Gemini Pro for the hardest reasoning.

Work with Gemini 2.5 Flash

Frequently asked questions

What is Gemini 2.5 Flash's context window?

Gemini 2.5 Flash has a 1,000,000-token context window (about 1.0M tokens) — the maximum amount of text it can consider at once.

How much does Gemini 2.5 Flash cost?

Via the Google API, Gemini 2.5 Flash costs $0.10 per 1M input tokens and $0.40 per 1M output tokens (web-verified June 2026). Output tokens cost more, so the length of the model's reply usually drives the bill.

Is Gemini 2.5 Flash multimodal?

Yes — Gemini 2.5 Flash accepts Text, Images, Audio, Video as input, not just text.

Is Gemini 2.5 Flash open-weight?

No — Gemini 2.5 Flash is available only through the Google API, not as downloadable weights.