All the models in one place
Run Gemini 3.1 Flash and every other model on Glif from one chat. One account, one balance, no API keys to wire up.
Gemini 3.1 Flash
Glif default
Fast image generation and editing with readable text and up to 4K output.
Pricing details
- Cost depends on resolution: 6.08 credits (512px), 9.05 credits (1K), 13.64 credits (2K), 20.39 credits (4K).
Rated by blind team votes and an AI judge
As of
Score 68 · #2 of 14 in Text-to-image
90% range 60–76
Score out of 100: how often people would pick this model's output over an average model's on the same tests. 50 is average.
How we score
On text-to-image: Wins 36 / Losses 16 / Ties 6 from 58 team votes, plus 15 AI judge scores.
Every model runs the same Glif tests. Team members see two outputs side by side without the model names and pick the one that better fits the test, or call it a tie. An AI judge also scores every output from 0 to 10.
A Bradley-Terry fit turns all those head-to-head results into one rating per model. Ties count as half a win, and each AI judge score counts as half a vote.
The score is the predicted chance people prefer this model's output to the average model's on the same board, so 50 is average. A board is one kind of task, like text-to-image. Scores only compare models on the same board.
The 90% range comes from resampling the votes and refitting many times. Overlapping ranges are close to a tie. A model ranks once it has 20 votes' worth of ratings on a board. Until then it shows no score, only how close it is.
Other boards
Product photography: 75 · #3 of 14
Character consistency: 60 · #7 of 15
Image-to-image: 59 · #2 of 3
Surgical image editing: 54 · #8 of 14
Brand and text rendering: Needs more ratings (11 of 20)
Image upscaling: Needs more ratings (6 of 20)
Multi-image reference: Needs more ratings (2 of 20)
Test outputs
Compare all modelsGemini 3.1 Flash in practice
What it does and when to use it.
Model summary
Gemini 3.1 Flash Image, also called Nano Banana 2, is Google’s image generation and editing model. It supports multiple reference images, text in images, and output up to 4K. Use it for posters, diagrams, compositions built from references, and repeated edits to an image.
Capabilities
Text to image
Image to image
Multi image reference
Text rendering
Suggested use cases
- Create posters, diagrams, and layouts containing text
- Build compositions guided by multiple reference images
- Edit an image's objects, colors, or visual style
Related models
Explore other options from the same family.