An update to Nano Banana 2 ( Gemini 3.1 Flash Image ), it maintains Flash-level speed and cost efficiency while delivering significant improvements in visual quality, prompt adherence, multi-turn character consistency, and text rendering. It serves as the more efficient counterpart to Gemini 3 Pro Image (Nano Banana Pro). Key updates: Improved visual quality and realism across 1K , 2K , and 4K output resolutions (default 1K ) Fixed tiling artifacts on wide and panoramic aspect ratios ( 1:4 , 4:1 , 1:8 , 8:1 ) at 2K and 4K resolutions Enhanced text rendering and infographic layout accuracy Multi-image fusion supporting up to 14 reference images (character consistency for up to 4 characters and object fidelity for up to 10 objects) Grounding with Google Web and Image Search Configurable Thinking levels ( minimal , medium default, and high )
function_callinghttps://us-central1-aiplatform.googleapis.com/v1beta/models/{model}:generateContenthttps://us-central1-aiplatform.googleapis.com/v1beta/models/{model}:streamGenerateContent| Input | Cached input | Output | |
|---|---|---|---|
| Standard | $1.5 | — | $7.5 |
| Batch | $0.75 | — | $3.75 |
/v1/models/vertex/gemini-nano-banana-2.1An update to Nano Banana 2 ( Gemini 3.1 Flash Image ), it maintains Flash-level speed and cost efficiency while delivering significant improvements in visual quality, prompt adherence, multi-turn character consistency, and text rendering. It serves as the more efficient counterpart to Gemini 3 Pro Image (Nano Banana Pro). Key updates: Improved visual quality and realism across 1K , 2K , and 4K output resolutions (default 1K ) Fixed tiling artifacts on wide and panoramic aspect ratios ( 1:4 , 4:1 , 1:8 , 8:1 ) at 2K and 4K resolutions Enhanced text rendering and infographic layout accuracy Multi-image fusion supporting up to 14 reference images (character consistency for up to 4 characters and object fidelity for up to 10 objects) Grounding with Google Web and Image Search Configurable Thinking levels ( minimal , medium default, and high )