Agent Mag
SUBSCRIBE
Nano Banana 2 (Gemini 3.1 Flash Image Preview)
All models
GoogleGoogleGeminiReleased 2026-02-26

Nano Banana 2 (Gemini 3.1 Flash Image Preview)

66K context$0.500/M input$3.00/M output

Gemini 3.1 Flash Image Preview, also known as 'Nano Banana 2,' is Google's advanced image generation and editing model. It offers professional-level visual quality with fast and cost-efficient inference, enabling complex image creation and iterative edits. The model supports aspect ratio control via the image_config API parameter, making it versatile for various visual tasks.

What is Nano Banana 2 (Gemini 3.1 Flash Image Preview)?

Nano Banana 2 (Gemini 3.1 Flash Image Preview) is an AI model from Google that Agent Mag tracks for pricing, context window, modalities, benchmarks, and API compatibility. Builders can use this page to compare Nano Banana 2 (Gemini 3.1 Flash Image Preview) against other models for agent workflows and production deployments.

Model ID

Gemini 3.1 Flash Image Preview, also known as 'Nano Banana 2,' is Google's advanced image generation and editing model. It offers professional-level visual quality with fast and cost-efficient inference, enabling complex image creation and iterative edits. The model supports aspect ratio control via the image_config API parameter, making it versatile for various visual tasks.

Architecture & Specifications
Tokenizer
Gemini
License
Proprietary
Released
2026-02-26
Modalities
Input
imagetext
Output
imagetext
Supported Parameters
include_reasoningmax_tokensreasoningresponse_formatseedstopstructured_outputstemperaturetop_p
Strengths
  • Pro-level visual quality
  • Fast inference speed
  • Cost-efficient image generation
  • Supports iterative edits
  • Aspect ratio control via API
Limitations
  • Structured output error rate of 22.38%
  • Latency averages over 15 seconds depending on provider
  • Requires user IDs for anonymity
  • Moderation is the responsibility of the developer
Recommended Use Cases
Professional graphic design
Image generation for creative projects
Logo creation
Iterative image editing
Aspect ratio-specific visual tasks

More from Google

Gemma 4 26B A4B
262K ctx$0.060/M

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

Gemma 4 31B (free)
262K ctxFree

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

Gemma 4 31B
262K ctx$0.130/M

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

Gemma 4 26B A4B (free)
262K ctxFree

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

Related content

Browse the AI models directory

Compare pricing, local installs, context windows, and modality filters across the full model catalog.

Explore AI agent tools

Find frameworks, SDKs, and infrastructure tools that pair with this model in production workflows.

Read Agent Mag model and agent articles

See Agent Mag coverage of model benchmarks, agent frameworks, and deployment patterns.

Data enriched Apr 24, 2026. Pricing from OpenRouter API.