On 2026-10-06 Google officially launched Nano Banana 2.1 and marked it GA in the Gemini API changelog as gemini-nano-banana-2.1. It is based on Gemini 3.6 Flash and is rolling out across the Gemini app, AI Studio, Search AI Mode, Flow, Stitch, Google Ads and Gemini Enterprise Agent Platform. Image output is priced at $30 per 1M tokens (Nano Banana 2: $60), which works out to $0.0336 per 1K image and $0.0504 per 2K image, about half the old price. The model card's side-by-side human eval puts text-to-image Elo at 1050, ahead of Nano Banana 2 (990) and Nano Banana Pro (935). gemini-3.1-flash-image is now deprecated, with no shutdown date announced. This confirms the silent Flow rollout we reported earlier.
Key Takeaways
- ✓Per-image price: 1K $0.0336 (was $0.067, -50%), 2K $0.0504 (was $0.101, -50%), 4K $0.113 (was $0.151, -25%); Batch halves it again to $0.0168 per 1K image (pricing)
- ✓Text side got pricier: input $1.50/1M tokens (was $0.50), text+thinking output $7.50 (was $3), so re-check costs for long prompts and many reference images
- ✓Human-eval Elo (model card): T2I overall 1050 vs NB2 990 vs Pro 935; multi-character consistency 1106 vs 978 vs 1011; infographic factuality 0.521 vs 0.179 vs 0.265
- ✓Specs: up to 14 reference images (4 characters + 10 objects), fixed 2K/4K tiling artifacts at 1:8/8:1, Google Web + Image Search grounding, thinking levels minimal/medium/high
- ✓Migration: gemini-3.1-flash-image is deprecated (no shutdown date yet); 131,072-token input limit; no function calling, structured outputs or caching (model docs)
Key Decision Metrics at a Glance
Turn your technical choice into a development budget
Compare 40 dev plans & simulate token costs vs $20/mo subscriptions
Project Links & Resources
Direct AccessIn-Depth Technical Analysis
Nano Banana 2.1 is Google's official successor to Nano Banana 2 (gemini-3.1-flash-image). It is based on Gemini 3.6 Flash, launched on 2026-10-06 and went straight to GA in the Gemini API as gemini-nano-banana-2.1. It ships across the Gemini app, AI Studio, Search AI Mode, Flow, Stitch, Google Ads and Gemini Enterprise Agent Platform. This officially confirms the silent Flow rollout spotted a day earlier.
What changed: improved realism at 1K/2K/4K (default 1K); fixed tiling artifacts on 1:4/4:1/1:8/8:1 at 2K/4K; better text rendering and infographic layout; multi-image fusion with up to 14 references (4 characters, 10 objects); grounding with Google Web and Image Search; and configurable thinking (minimal / medium default / high). API limits: 131,072 input tokens, 32,768 output tokens. Batch is supported. Function calling, structured outputs and caching are not.
Benchmarks (Google's own side-by-side human eval, thinking mode): T2I overall preference Elo 1050 vs 990 for Nano Banana 2 and 935 for Nano Banana Pro; general editing 1026 vs 938/939; multi-character consistency 1106 vs 978/1011; infographic factuality 0.521 vs 0.179/0.265. There are no third-party replications yet.
Pricing: image output $30/1M tokens (down from $60), i.e. $0.0336 / $0.0504 / $0.113 per 1K/2K/4K image, with Batch at half that. Text input rises to $1.50/1M (from $0.50) and text+thinking output to $7.50 (from $3). Migration is a model-ID swap; the old ID is deprecated with no shutdown date announced yet.
Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.