OpenRouter
Gemini 3.1 Flash Image, a.k.a. $0.50 per million input tokens, $3 per million output tokens. 131,072 token context window, maximum output of 65,536 tokens. Higher uptime with 2 providers.
Model details
Nano Banana 2 is the public alias for Google's Gemini 3.1 Flash Image, an image generation and editing model positioned as a speed-and-quality bridge between lighter and higher-fidelity predecessors. Google DeepMind describes it as combining production-ready visual specifications, improved instruction-following, and subject consistency with what it calls "Flash speed," while real-time web grounding lets outputs reflect current information. The model is rolling out across the Gemini app, Google Search, AI Studio, Vertex AI, Flow, and Google Ads, signaling an intent to serve both consumer creative workflows and enterprise production pipelines that need dependable turnaround without sacrificing adherence to nuanced prompts.
Independent coverage highlights 4K image output alongside Pro-level visual quality, framing Nano Banana 2 as a practical option for iterative creative work where rapid refinement matters. On OpenRouter the canonical listing is available alongside an earlier preview slug, with routing across multiple underlying providers to improve uptime, and a context window in the 131K-token range that supports image-and-text prompts of substantial length. Aspect ratios can be controlled through the image-generation configuration API, making the model well suited for design teams and developers who need consistent, production-grade assets at Flash-tier latency and cost efficiency.
Transparent token rates
Rates are shown per one million tokens. Combined means one million input plus one million output tokens.
OpenRouter
Gemini 3.1 Flash Image, a.k.a. $0.50 per million input tokens, $3 per million output tokens. 131,072 token context window, maximum output of 65,536 tokens. Higher uptime with 2 providers.
This exact model name is also listed by 8 other providers.