All models
Google
Gemini 2.5 Flash
Google's 2025 hybrid reasoning Flash with a controllable thinking budget, 1M context and text, image, video and audio input. Still a cheap, fast option for summaries and everyday chat. Gemini 3.8 Flash is newer and smarter but costs about twice as much.
MainstreamThe big labs' models with their own safety filters. Best for work, code and research.
Quick
Intelligence
~1.12 credits
Estimated price per message
1M tokens
Context window
Text, Images, Video, Audio
Reads
Gemini 2.5 Flash is a legacy model. Its successor, Gemini 3.8 Flash, is faster or cheaper - and chats that used Gemini 2.5 Flash move to it automatically.
See Gemini 3.8 FlashThe facts
Made by
Google
Content tier
MainstreamThe big labs' models with their own safety filters. Best for work, code and research.
Intelligence
Quick
Estimated price per message
~1.12 credits≈ 89 messages for $1
Context window
1M tokens≈ 1,613 pages of text in one go
Reads
Text, Images, Video, Audio
Writes
Text
Tool use
Yes - search, memory, code and more
Served via
OpenRouter, Unbottled AI
Status
Legacy
A typical message: 16K tokens in, 1.5K out. Short replies cost less. Models served via OpenRouter bill the real provider cost plus our markup, so actual charges vary. 1 credit = $0.01.
Compare Gemini 2.5 Flash
Same facts, side by side.
Try Gemini 2.5 Flash now.
No subscription. Free credits to start. The chat opens with Gemini 2.5 Flash selected and a prompt ready - just send.