gemini-3-pro-image

imagetext imagetext 131K context

$0.134 per image
6 providers
2 test samples

What we tested, and what came back

Each capability below is a fixed experiment: the same prompt and the same input images for every model we test. That's what makes these outputs comparable — and it's why the same bicycle shows up on every image model's page.

Each of these is a fixed experiment — the same prompt and the same input images for every model we test, so the outputs are directly comparable.

Renders a data-faithful infographic ✓ passed
We asked

“Create a clean infographic: a vertical bar chart titled 'HIFIBOTS USERS' with exactly three labeled bars: Jan = 10, Feb = 25, Mar = 40. Show each label and value as legible text.”

We gave it

Nothing — prompt only

It returned
a vision model was asked a yes/no question about the output 17s $0.16224 computed
Replaces a target object in place (prompt-based inpainting) ✓ passed
We asked

“In this image, replace the red square with a yellow star. Keep the blue circle exactly as it is.”

We gave it 1 reference image
Input fixture shapes.png
shapes.png
It returned
a vision model was asked a yes/no question about the output 16s $0.1422 computed
Stated by the provider — not tested by us
✓ aspect ratio control✓ multi reference✓ multi turn editing✓ reference image✓ style transfer✓ text in image✓ text to image✓ upscaling✗ background removal
Specs
max reference images
Blend up to 14 input images total; up to 6 high-fidelity object images; consistency of up to 5 people. GA docs table: up to 6 object + 5 character images
aspect ratios
max resolution
4K (supports 1K, 2K, and 4K)
watermark
SynthID (embedded directly into every image created or edited)
price per image
GA gemini-3-pro-image: $0.134 per 1K/2K image (1120 tokens), $0.24 per 4K (2000 tokens) standard; batch/flex $0.067 / $0.12; input $2.00/1M tokens
speed tier
medium
latency t2i s
15.5
latency i2i s
13.6
latency s
16.78372097015381

Sources: blog.google · ai.google.dev · ai.google.dev · ai.google.dev

Where to run it

The same model, priced by each provider that serves it. Cheapest first — the card's headline price is the best available anywhere, which is the wrong number for choosing where to actually send your traffic.

ProviderPriceContext
laozhang $0.09 / image
together $0.134 / imageGet a key ↗
openrouter $2 / $12 per 1M66KGet a key ↗
google $2 / $12 per 1M131KGet a key ↗ partner

Rows marked partner may earn us a commission. Ordering is by price only — it is never influenced by what a provider pays us.

See all google models we've tested →

How we test

Every claim is tagged by how we know it. Tested means we ran the model against a fixed prompt and checked the output — the images above are those runs. Researched means it's documented by the provider and cited. Nothing here is inferred.