Nano Banana Pro (Gemini 3 Pro Image)
Google DeepMind's flagship image model built on Gemini 3 Pro, known for legible multilingual text,4K output, and studio-grade conversational editing.
Nano Banana Pro, officially Gemini 3 Pro Image, is Google DeepMind's professional-grade image generation and editing model built on the Gemini 3 Pro architecture. It sits at the top of Google's image lineup, aimed at professional and commercial creators who need studio-quality visual output rather than quick drafts.
Its strongest capability is text rendering: it produces legible, well-typeset text across multiple languages and fonts, which makes posters, UI labels and localized campaign assets practical. Through conversation you can adjust lighting, camera angle, depth of field and color grading while keeping the original composition, hold up to five characters or fourteen objects consistent across scenes, and ground content in current information via Google Search.
It generates at 1K, 2K and 4K across aspect ratios such as 1:1, 16:9, 9:16 and 21:9, blends up to fourteen reference images, supports multi-turn editing, and embeds an invisible SynthID watermark in every output. Typical work includes marketing visuals, design refinement, instructional infographics and character-consistent illustration series.
Updated:
MODEL ID
gemini-3-pro-image- Context
- 131.072K
- Max output
- 32.768K
- Input
- image / text
- Output
- image / text
Providers
2 providersCompare API prices across providers. Select a provider to view all charges and conditions.
| $2 | $12 | $0.2 | $0.2 | |
| $2 | $12 | $0.2 | $0.2 |
Reasoning
- Always enabled
- Yes
API reference
Model-specific protocol details are not published. Check the API reference for integration requirements.
API reference →Supported parameters
- include_reasoning
- max_tokens
- reasoning
- response_format
- seed
- stop
- structured_outputs
- temperature
- tool_choice
- tools
- top_p
Frequently asked questions
What is Nano Banana Pro (Gemini 3 Pro Image)?
Nano Banana Pro, officially Gemini 3 Pro Image, is Google DeepMind's professional-grade image generation and editing model built on the Gemini 3 Pro architecture. It sits at the top of Google's image lineup, aimed at professional and commercial creators who need studio-quality visual output rather than quick drafts. Its strongest capability is text rendering: it produces legible, well-typeset text across multiple languages and fonts, which makes posters, UI labels and localized campaign assets practical. Through conversation you can adjust lighting, camera angle, depth of field and color grading while keeping the original composition, hold up to five characters or fourteen objects consistent across scenes, and ground content in current information via Google Search. It generates at 1K, 2K and 4K across aspect ratios such as 1:1, 16:9, 9:16 and 21:9, blends up to fourteen reference images, supports multi-turn editing, and embeds an invisible SynthID watermark in every output. Typical work includes marketing visuals, design refinement, instructional infographics and character-consistent illustration series.
How is usage billed?
Your bill depends on the provider you use, its prices and your usage. Longer inputs or other conditions may have different prices.
