GoogleReasoningReleased 18 June 2026
Nano Banana Pro (Gemini 3 Pro Image) pricing, context and benchmark
Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro.
131K
Input context
33K
Output context
$2
Official input
$12
Official output
n/a
AA index
01 · Model Overview
Everything that matters, in one table
Context, pricing, cache, modalities and tooling, from the model registry and Artificial Analysis.
| Model | Nano Banana Pro (Gemini 3 Pro Image) |
| Model ID | google/gemini-3-pro-image |
| Provider | |
| Release date | 18 June 2026 |
| Status | Generally available |
| Input context | 131,072 tokens |
| Output context | 32,768 tokens |
| Official input pricing | $2 per 1M tokens |
| Official output pricing | $12 per 1M tokens |
| Cache read pricing | $0.2 per 1M tokens |
| Market input pricing | $2 per 1M (cheapest route) |
| Market output pricing | $12 per 1M (cheapest route) |
| Reasoning tokens | Billed as output at $12 per 1M |
| Input modalities | image · text |
| Output modalities | image · text |
| Reasoning control | Yes, effort levels exposed |
| Tool support | Functions, tool choice, structured outputs |
| Tokenizer | Gemini |
| Provider routes | 2 endpoints |
| Artificial Analysis index | Not published |
| Speed | Not published |
| Knowledge cutoff | Not publicly stated |
Input and output support
| Modality | Input | Output | Billed at |
|---|---|---|---|
| Text | ✓ yes | ✓ yes | $2 in |
| Image | ✓ yes | ✓ yes | $2 in |
| Audio | no | no | not supported |
| Video | no | no | not supported |
| File (PDF) | no | no | not supported |
02 · Overview
What is Nano Banana Pro (Gemini 3 Pro Image)?
Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro.
It extends the original Nano Banana with significantly improved multimodal reasoning, real-world grounding, and...
Nano Banana Pro (Gemini 3 Pro Image) carries a 131K token window, uses the Gemini tokenizer and is served by Google. On Hoodgen it sits in the Reasoning tier of the model menu next to its siblings, so you can switch mid conversation without losing the thread.
03 · Release
Release and what changed from the previous version
Released18 June 2026
| Property | Gemini 3.5 Flash | Nano Banana Pro (Gemini 3 Pro Image) | Change |
|---|---|---|---|
| Released | 2026 | 2026 | Same release window |
| Context | 1.05M | 131K | Changed |
| Max output | 66K | 33K | Changed |
| Input price | $1.5 | $2 | Higher |
| Output price | $9 | $12 | Higher |
| Input modalities | text, image, video, file, audio | image, text | Unchanged |
| AA index | n/a | n/a | Newer benchmark run |
04 · Capabilities
Features and capabilities
◈
Thinking control
Reasoning effort can be dialled per request, so one model covers deep analysis and fast chat.
⚙
Function calling
Tools, tool choice and parallel calls, which is what agent loops need to act on results.
{ }
Structured outputs
Schema constrained JSON with response_format, so no parse and retry loop in your code.
◉
Vision
Screenshots, charts and photographed documents are read at the text token rate.
⚡
Prompt caching
Cached input costs $0.2 per million instead of $2, so stable prefixes get cheaper.
⌁
Seeds
A seed can be pinned so the same prompt is reproducible across test runs.
05 · Reasoning
Thinking and reasoning capabilities
Nano Banana Pro (Gemini 3 Pro Image) can think before answering and exposes the effort level per request. Reasoning tokens bill as output at $12 per million, and the trace can be returned with include_reasoning.
| Level | First token | Cost per task | Best for |
|---|---|---|---|
| Measured | n/a | n/a | Artificial Analysis measures the default reasoning configuration |
| Low effort | Faster | Lower | Chat, autocomplete, classification |
| High effort | Slower | Higher | Debugging, planning, multi step agents |
07 · Use cases
What can you do with Nano Banana Pro (Gemini 3 Pro Image)?
Debugging and root cause
Multi file failures where the model has to hold a causal chain before answering.
Architecture and planning
Design docs, migration plans and trade off analysis over long context.
Data analysis
Spreadsheets and logs read in one pass, then summarised with the numbers quoted back.
Agentic coding
Repo wide changes that need plan, edit and verify loops.
08 · Cost levers
Prompt caching and how to cut the bill
Cached input bills at $0.2 per million instead of $2. Keep the system prompt and documents first and the changing question last, so every call hits the cache.
09 · Pricing
Nano Banana Pro (Gemini 3 Pro Image) pricing
Official pricing
List price
$2 / 1M in
$12 / 1M out
- $0.2 cached input
- 131K context
- image, text input
Cheapest route
$2 / 1M in
$12 / 1M out
- 2 routes on OpenRouter
- What Hoodgen routes to first
- Same model, lower bill
Market pricing, every route
| Provider | Tier | Input | Output | Cache read | Uptime 24h |
|---|---|---|---|---|---|
| Google AI Studio | standard | $2 | $12 | $0.2 | n/a |
| standard | $2 | $12 | $0.2 | 100.0% |
API pricing and cost calculator
| Rate | Per call | Total | Credits |
|---|---|---|---|
| Cheapest route | $0.0364 | $18.20 | 17290 |
| List price | $0.0364 | $18.20 | 17290 |
10 · Developers
API and developer information
| Model ID | google/gemini-3-pro-image |
| Endpoint | https://openrouter.ai/api/v1/chat/completions |
| Parameters | include_reasoning · max_tokens · reasoning · response_format · seed · stop · structured_outputs · temperature · tool_choice · tools · top_p |
| Streaming | Yes, server sent events |
| Modality string | text+image->text+image |
| Max prompt tokens | 131,072 |
| Max completion tokens | 32,768 |
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemini-3-pro-image",
"messages": [{ "role": "user", "content": "Summarise this document." }],
"max_tokens": 1024
}'11 · Limitations
Model limitations
| Output cap | 32,768 tokens per request. Long deliverables have to be chunked. |
| Benchmarks not published | Artificial Analysis does not publish an Intelligence Index for this release, so no benchmark score is claimed here. |
| Knowledge cutoff | The provider does not state a fixed cutoff for every release. Verify very recent events against search. |
12 · Comparison
Nano Banana Pro (Gemini 3 Pro Image) vs other Google models
| Model | Context | Input /1M | Output /1M | AA index | Released |
|---|---|---|---|---|---|
| Nano Banana Pro (Gemini 3 Pro Image) | 131K | $2 | $12 | n/a | 2026 |
| Gemini 3.1 Pro Preview | 1.05M | $2 | $12 | n/a | 2026 |
| Gemini 4 Argon | 1.05M | $2 | $10 | 50 | Oct 2026 |
| Gemini 4 Carbon | 1.05M | $2 | $10 | n/a | 2026 |
| Gemini 3.1 Pro Preview Custom Tools | 1.05M | $2 | $12 | n/a | 2026 |
| Nano Banana Pro (Gemini 3 Pro Image Preview) | 66K | $2 | $12 | n/a | 2025 |
13 · Privacy
Privacy and data policy
- On Hoodgen, prompts and attachments answer that request and stay in your conversation history so you can reopen it. They are not used to train models.
- Requests route through OpenRouter to Google and are covered by that provider's API terms.
- Do not paste secrets or personal data you would not send to any hosted model.
14 · FAQ
Nano Banana Pro (Gemini 3 Pro Image) questions, answered
Nano Banana Pro (Gemini 3 Pro Image) is a reasoning model from Google, released 18 June 2026. Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro.
✦
Start chatting with Nano Banana Pro (Gemini 3 Pro Image)
Free to try on Hoodgen AI, with a live credit estimate before every send. No API key, no setup.