Gemini Flash
Fastest writing model. 163 tokens per second. Adjustable thinking.
Google's speed-optimised thinking model. 3x faster than Gemini Pro with chain-of-thought reasoning and adjustable thinking budgets. First token in under 200ms. 4x cheaper than Pro. Uses 20-30% fewer tokens, producing more concise output. Best for quick drafts and high-volume content.
Try these prompts
How it works
Describe your brief
Type what you need: a proposal, case study, specification, or creative copy.
Choose model and document type
Pick your writing model and document length. See the credit cost before you generate.
Draft generated in seconds
Your document is drafted and ready to review, edit, copy, or export. Iterate or switch models.
Ready to draft with Gemini Flash?
Jump into the Studio and start writing. Plans from £10/month.
Choose a PlanThe fastest AI writing model available.
Gemini Flash is the fastest writing model on Stensyl. At 163 tokens per second with first-token latency under 200ms, documents begin appearing almost instantly. For design professionals who use AI writing as part of a fast-moving workflow, not as an overnight batch process, that speed matters.
Speed does not mean shallow. Gemini Flash includes chain-of-thought reasoning with adjustable thinking budgets. For a quick concept note, it writes fast and concise. For a more structured brief outline, it applies more reasoning depth. The thinking budget adjusts to the complexity of the task, so you get the right balance of speed and depth without manual mode switching.
At 4x cheaper than Gemini Pro and using 20-30% fewer tokens, Flash produces more concise output by default. This is not a limitation. For quick drafts, social posts, meeting follow-ups, and brief outlines, conciseness is a feature. Less editing, less padding, more usable first drafts.
Sub-200ms first token
Gemini Flash starts writing before you have finished switching tabs. First-token latency under 200ms means the document is already appearing by the time you look at the output panel. For real-time workflows where AI writing is integrated into your minute-by-minute process, this responsiveness changes how you use the tool.
Concise by default
Flash uses 20-30% fewer tokens than Pro, producing tighter, more concise output. For quick drafts, social content, and short-form professional writing, this means less post-generation editing. The first draft is closer to the final version because it does not pad or over-explain.
High-volume content production
Flash makes it economical to use AI writing for every small task: social captions, email drafts, meeting summaries, elevator pitches, product descriptions. The tasks that individually seem too small to bother with add up to hours of saved time across a working week.
Questions about Gemini Flash.
Why Stensyl?
A small indie studio building creative tools the way they should be built. No VC theatre, no funnel games, no faceless support.
Ready to draft with Gemini Flash?
Professional document drafting. Plans from £10/month.