Google rolls out Nano Banana 2.1 with 4K output at $0.076 per image
testingcatalog · x · 2026-10-06
Nano Banana 2.1, Google's high-quality image generation and editing model with enhanced factuality, visual fidelity, and multi-turn consistency, is now live on Google AI Studio, APIs, and Gemini.
- Image output priced at $30 per 1M tokens
- 1K (1024x1024): 1120 tokens ≈ $0.034/image
- 2K (2048x2044): 1680 tokens ≈ $0.050/image
- 4K (4096x4096): 2520 tokens ≈ $0.076/image
Compared to the previous version, inputs and text generation cost 2.5–3x more, while image output is 50% cheaper. Based on pricing, the poster suspects it's effectively a Pro-tier model.
Related event: Google Launches Nano Banana 2.1, Beating Predecessors at Lower Cost(4 posts)→
More from Models
- Blogger argues Anthropic stays a step ahead of OpenAI on taste and coding, if pricing holds — iruletheworldmo · 2026-10-07
- Open Source AI Week Kicks Off: Reflection Beam and Mistral Large 4 Launch — sophiamyang · 2026-10-07
- GeoGuess Bench: Claude Opus 5.5 tops 210-photo geolocation test, open models shine — nutlope · 2026-10-07
- Jon Durbin: Masked Pruning on Enforced-Sparse Models Could Curb Catastrophic Forgetting in SFT — jon_durbin · 2026-10-07
- Google launches EmbeddingGemma 2, a 740M open multimodal embedding model for on-device use — sundarpichai · 2026-10-07
- Mistral 'is so back': new model crushes cybersecurity, legal, agentic benchmarks — sophiamyang · 2026-10-06