Nano Banana Pro (Gemini 3 Pro Image Preview) API Pricing
Google · context window 66K · prices updated 2026-09-15
This is a dated/preview alias of Nano Banana Pro (Gemini 3 Pro Image) and currently carries identical pricing. The main page is kept up to date — this one exists so the exact model string resolves.
Where Nano Banana Pro (Gemini 3 Pro Image Preview) sits on price
At $12.00 per million output tokens, Nano Banana Pro (Gemini 3 Pro Image Preview) is a premium tier model — 5.8× the median output price of $2.08, which puts it cheaper than 18% and pricier than 82% of the models we track. It is the most expensive of the 38 Google models we track. Output costs 6.0× more than input here, so anything that makes the model write less — tighter instructions, structured output, lower max_tokens — moves the bill more than trimming the prompt.
Cached input is 90% cheaper. On an input-heavy workload you need roughly a 28% cache-hit rate to take 25% off the input line — reachable for chatbots and agents that resend the same system prompt and history.
What real workloads cost on Nano Banana Pro (Gemini 3 Pro Image Preview)
These three workloads are the ones teams actually run on a premium-priced model — a $12.00/1M model is not bought for the same job as one ten times the price.
| Workload | Per request | Per month |
|---|---|---|
| Support chatbot — 500 conversations/day (5K in / 1.4K out) Conversation history re-sent each turn — the classic prompt-caching win. | $0.0268 | $402 |
| Coding agent — 300 sessions/day (60K in / 12K out) Multi-step loops re-read the same files; caching matters more than raw price. | $0.264 | $2376 |
| Small app — 1K requests/day (500 in / 150 out) The baseline most side projects actually run at. | $0.0028 | $84.00 |
Model your exact traffic in the API cost calculator — it preloads Nano Banana Pro (Gemini 3 Pro Image Preview) with caching and batch options.
Nano Banana Pro (Gemini 3 Pro Image Preview) price history
Nano Banana Pro (Gemini 3 Pro Image Preview)'s price has not moved since we began tracking it on Aug 2, 2026 — 44 days of stability in a market where 78 of the 334 models we track have repriced over the same period, including 6 of Google's own 38 models.
Change-points from our daily price snapshots (tracking since Aug 2, 2026; intraday moves between snapshots are not captured).
Nano Banana Pro (Gemini 3 Pro Image Preview) vs GPT-5 Image
The closest-priced alternative from another vendor is GPT-5 Image (OpenAI) — 17% cheaper on output, with $8.00 more per million input tokens. When two models land this close on price, the decision is quality on your own workload, not the price sheet: run 50 real requests through both and compare.
See GPT-5 Image pricing →Cheaper alternatives
More Google models
Frequently asked questions
› How much does the Nano Banana Pro (Gemini 3 Pro Image Preview) API cost?
Nano Banana Pro (Gemini 3 Pro Image Preview) costs $2.00 per million input tokens and $12.00 per million output tokens, with cached input at $0.2 per million (90% cheaper). That works out to roughly 83,333 output tokens per dollar.
› What does the support chatbot workload cost on Nano Banana Pro (Gemini 3 Pro Image Preview)?
Support chatbot — 500 conversations/day (5K in / 1.4K out) costs about $0.0268 per request and $402 per month on Nano Banana Pro (Gemini 3 Pro Image Preview). Conversation history re-sent each turn — the classic prompt-caching win.
› What does it cost to fill Nano Banana Pro (Gemini 3 Pro Image Preview)'s 66K context window?
Sending 66K of input in a single request costs $0.1311 at $2.00 per million tokens — before any output. With prompt caching that same fill drops to about $0.0131 on repeat requests. This is why large context windows are cheap to advertise and expensive to actually use.
› Is Nano Banana Pro (Gemini 3 Pro Image Preview) worth the price?
Nano Banana Pro (Gemini 3 Pro Image Preview) sits in the middle of the market (38 of 38 by price within Google). The honest test is a routing experiment: send the same 200 real requests to this model and to a tier below, and compare failure rate against the price gap — most teams find a majority of traffic never needed the pricier model.