1,000K tokens
Context window
Google Gemini
Gemini Flash
Long input at low cost
65K tokens
Max output
Paid
Cost
mid 2025
Knowledge cutoff
text, image, audio, video
Modalities
Last verified 20 May 2026 Pricing is deliberately not listed here - check the vendor's own page. Report a correction
What it tends to refuse
Same categories as Pro
The cheapest way to read something huge. Multi-step reasoning is weaker than you would guess from the price.
Standing rules for this model go in System instruction, not in every message.
See the config files.
Written for Gemini
All 3- ErrorChatGPTGemini
This model's maximum context length is N tokens
The request is longer than the model can hold. Your prompt, the whole conversation history and the space reserved for the answer all count. The…
Tested on GPT-5 · May 2026
Teacher who checks where you are
Explains at your level and not the manual level. It asks one question first and builds on what you say you already know.
Tested on Gemini Pro · May 2026
- PromptUniversal
Summarise a meeting transcript into decisions and actions
Extracts decisions, owners and open questions from a raw transcript, and refuses to invent an owner where the transcript does not name one.