All modelsGoogle
Image generationStable
Nano Banana 2
Google's versatile image workhorse for fast generation, conversational edits, multiple references, grounded imagery, and outputs up to 4K.
Plain-English overview
What Nano Banana 2 actually is
Nano Banana 2 is the product name for Gemini 3.1 Flash Image. Google positions it between its lower-cost Lite model and premium Pro image model, with a balance of speed, consistency, world knowledge, and text rendering.
Resolution maps directly to image-token cost, making it straightforward to budget 0.5K, 1K, 2K, and 4K deliverables. Search grounding can add separate charges and should be enabled intentionally.
Good fit for
- Conversational image editing
- Multilingual text and social creative
- High-volume 1K–4K application workflows
Category comparison
The facts that matter for image models
These are provider-published specifications, not Cody benchmark scores. Follow the linked sources for current limits and endpoint-specific exceptions.
- Typical price basisA representative current provider price with its quality or resolution basis.
- $0.067 / 1K image
- Maximum outputMaximum documented resolution or pixel area for the listed route.
- 0.5K, 1K, 2K, 4K
- Core tasksWhether the model supports generation, editing, or both.
- Generation and conversational editing
- Reference imagesHow the model can use images to guide or edit an output.
- Multiple references and multi-turn edits
- Text & layoutProvider-documented positioning for typography and structured composition.
- Improved multilingual text rendering
- API accessDirect and notable third-party routes included in this guide.
- Gemini API, fal
API and provider access
Where to get Nano Banana 2
Availability
Regions and access stage
Available through the Gemini API and Google AI Studio paid tier; third-party hosts may provide additional routes.
Use Google's live Gemini API region list. Model and grounding features can vary by region.
Check live availabilityData and training
The route matters.
Google says paid Gemini API content is not used to improve its products. Unpaid-service terms differ, so confirm that the project is attached to an active billing account before sending confidential material.
This is a concise reading of the cited provider material, not legal advice. A third-party gateway can have different storage, routing, training, and residency terms from the model maker's direct API.
Read the provider policyFrequently asked questions
Nano Banana 2 FAQ
What is Nano Banana 2?
Google's versatile image workhorse for fast generation, conversational edits, multiple references, grounded imagery, and outputs up to 4K. Nano Banana 2 is the product name for Gemini 3.1 Flash Image. Google positions it between its lower-cost Lite model and premium Pro image model, with a balance of speed, consistency, world knowledge, and text rendering.
When was Nano Banana 2 released?
Nano Banana 2 was released on May 28, 2026 according to the cited provider materials.
Where can I access Nano Banana 2?
Available through the Gemini API and Google AI Studio paid tier; third-party hosts may provide additional routes. The access routes listed in this guide are Google, fal.
How much does Nano Banana 2 cost?
$0.067 / 1K image. Google paid-tier standard pricing: $0.045 at 0.5K, $0.067 at 1K, $0.101 at 2K, and $0.151 at 4K, plus applicable text/image input and text output tokens.
Where is Nano Banana 2 available?
Available through the Gemini API and Google AI Studio paid tier; third-party hosts may provide additional routes. Use Google's live Gemini API region list. Model and grounding features can vary by region.
Is my Nano Banana 2 API data used for training?
Google says paid Gemini API content is not used to improve its products. Unpaid-service terms differ, so confirm that the project is attached to an active billing account before sending confidential material. The policy belongs to the provider route and account terms, so verify it again before production use.
Research trail
Sources for this guide
Keep comparing
More image generation models
OpenAI · Stable
GPT-Image-2
OpenAI's current image model for detailed generation and editing, especially complex prompts, text-heavy visuals, and high-fidelity source images.
Read guideBlack Forest Labs · Stable
FLUX.2 Pro
Black Forest Labs' production-focused image model for scalable generation and editing, precise composition, and multi-reference creative workflows.
Read guideIdeogram · Stable
Ideogram 4.0
A design-oriented image model with open weights, multilingual typography, structured layout control, editable elements, and simple per-image API tiers.
Read guide