Gemini 3.1 Flash Image

Pricing — 1 offering(s)

Showing the active price and any recorded history. Full pricing history is available via the paid API — see API docs.

Capability profile

Operator guidance

Route here for fast, cheaper Gemini-native generation and editing with strong text rendering and real-world knowledge grounding. Step up to Gemini 3 Pro Image when quality/accuracy matters more than speed (see gemini-3-pro-image.yaml), or to Imagen 4 for a more conventional dedicated diffusion pipeline within the same Google Cloud/Vertex AI stack.

Use cases

• Fast iteration where in-image text and localization matter (marketing creative across languages)
• Character-consistent series work — up to 5 characters and 14 objects held consistent across generations, per DeepMind's own model page
• Combined generation + editing in one tool, without switching models

Limitations

• No independently published GenEval / T2I-CompBench score found — capability ratings above are vendor-stated, not third-party verified
• A widely-repeated press claim of a #1 Text-to-Image ranking on the Artificial Analysis Image Arena could not be independently confirmed this session (JS-rendered leaderboard, not fetchable) — deliberately not cited as a rating or in use_cases
• Architecture classification (diffusion-transformer) is the closest vocabulary match to secondary technical reporting, not a Google-confirmed specific

Citations

• Gemini 3.1 Flash Image — Nano Banana 2 (Google DeepMind's own model page)
• Nano Banana 2 launch post (Google's own blog)