Nano Banana (API)

At a glance

Images

Content CredentialsA signed record (C2PA) of how the file was made, sealed so any change shows.

Google Cloud documentation lists Gemini image model IDs, including gemini-nano-banana-2.1 and gemini-3-pro-image, among models whose images or videos are automatically signed with Content Credentials by Google LLC. On November 20, 2025 Google said Nano Banana Pro images in Vertex AI would carry C2PA metadata, rolling out that week.

The Gemini API documentation does not mention Content Credentials.

Content Credentials, Gemini Enterprise Agent PlatformGoogle Cloud Documentation

Quoted passage How to Use Content Credentials; Supported models

If you generate a media file, such as an image, using a supported Google model, Content Credentials are automatically added and signed by Google LLC." "Content Credentials are supported by the following models. All images or videos created or modified using the listed models are automatically digitally signed by Google LLC. "Google Media Processing Services" is specified as the app or device used in the Content Credential. gemini-omni-1.1-flash-preview gemini-omni-flash-preview gemini-3.1-flash-lite-image gemini-3-pro-image gemini-nano-banana-2.1 gemini-3.1-flash-image gemini-2.5-flash-image virtual-try-on-001 veo-2.0-generate-001 veo-2.0-generate-exp veo-2.0-generate-preview veo-3.0-generate-preview veo-3.0-fast-generate-preview veo-3.0-generate-001 veo-3.0-fast-generate-001 veo-3.1-generate-preview veo-3.1-fast-generate-preview veo-3.1-generate-001 veo-3.1-fast-generate-001 veo-3.1-lite-generate-001 lyria-3-clip-preview lyria-3-pro-preview

How we’re bringing AI image verification to the Gemini appGoogle (The Keyword blog)

Quoted passage body, C2PA paragraph

As part of this, rolling out this week, images generated by Nano Banana Pro (Gemini 3 Pro Image) in the Gemini app , Vertex AI and Google Ads will have C2PA metadata embedded, providing further transparency into how these images were created. We look forward to expanding this capability to more products and surfaces in the coming months.

Invisible watermarkA signal woven into the pixels, frames, audio or wording, meant to survive copying.

Gemini API documentation says all images generated by its Nano Banana image models include a SynthID watermark.

Image generation (Nano Banana), Gemini APIGoogle AI for Developers

Quoted passage model list; Optional configurations

All generated images include a SynthID watermark .

AI label in metadataA plain metadata field (IPTC Digital Source Type) saying AI made the content. Anyone can add or remove it.

Not stated. None of Google's pages listed under Sources read says so.

No Google page read names an IPTC Digital Source Type term for its outputs.

Visible markA mark you can see, such as a logo or a sparkle in a corner.

Not stated. None of Google's pages listed under Sources read says so.

Tool named in metadataThe tool or model written into ordinary file fields, such as Software or Creator.

Google Cloud documentation says the Content Credentials name Google LLC as the signer and "Google Media Processing Services" as the app or device.

Content Credentials, Gemini Enterprise Agent PlatformGoogle Cloud Documentation

Quoted passage How to Use Content Credentials; Supported models

If you generate a media file, such as an image, using a supported Google model, Content Credentials are automatically added and signed by Google LLC." "Content Credentials are supported by the following models. All images or videos created or modified using the listed models are automatically digitally signed by Google LLC. "Google Media Processing Services" is specified as the app or device used in the Content Credential. gemini-omni-1.1-flash-preview gemini-omni-flash-preview gemini-3.1-flash-lite-image gemini-3-pro-image gemini-nano-banana-2.1 gemini-3.1-flash-image gemini-2.5-flash-image virtual-try-on-001 veo-2.0-generate-001 veo-2.0-generate-exp veo-2.0-generate-preview veo-3.0-generate-preview veo-3.0-fast-generate-preview veo-3.0-generate-001 veo-3.0-fast-generate-001 veo-3.1-generate-preview veo-3.1-fast-generate-preview veo-3.1-generate-001 veo-3.1-fast-generate-001 veo-3.1-lite-generate-001 lyria-3-clip-preview lyria-3-pro-preview

Limits and detection

Checking tool from the makerA way the maker offers to check a file for its traces.

Google says its SynthID Detector, launched in 2025, is open to everyone and checks whether an image, video or audio file was made with AI from Google or partners including OpenAI, NVIDIA and Kakao. Google said on October 7, 2026 that it is available globally in English.

Google SynthIDGoogle DeepMind

Quoted passage SynthID Detector

In 2025, we launched the SynthID Detector, a verification portal, to verify if a piece of content was watermarked with Google SynthID. After testing with journalists and media professionals and collecting their feedback, we’re expanding access to everyone. With the new SynthID Detector, anyone can easily check if an image, video, or audio file was made with AI from Google or our partners, including OpenAI, NVIDIA, Kakao, and soon, Apple.

We're making it easier to identify AI-generated content globally.Google (The Keyword blog, Africa edition)

Quoted passage body

Since launching Google SynthID in 2023, we've helped people identify AI-generated media using imperceptible watermarks across images, video, and audio. To date, we've watermarked over 180 billion images and videos, along with 240,000 years of audio content." "Last year, we introduced an early version of the SynthID Detector to help media professionals verify AI-generated content. Now, we’re expanding access to everyone – with the tool available globally in English starting today.

What the maker says about limitsIn the maker's own words.

Google Cloud documentation says C2PA does not classify media as real or fake, and that editing a C2PA file with a non-C2PA tool is treated as tampering and fails validation.

Content Credentials, Gemini Enterprise Agent PlatformGoogle Cloud Documentation

Quoted passage How to Use Content Credentials; Verify Content Credentials

Note that C2PA doesn't classify media as "real" or "fake". It focuses on authenticating the source of the information and ensures that the content hasn't been tampered with." "If the media file was created, edited, and published using only C2PA-aware tools, the Content Credentials are verifiable. Any modification to a C2PA-compliant media file using a non-C2PA tool is considered tampering, resulting in a validation failure.