Gemini 3 Pro Image (Nano Banana Pro)
Googlefamily · Geminiai.google.dev/gemini-api/docs/models/gemini-3-pr
A professional design engine with a reasoning core for studio-quality 4K visuals, complex layouts, and precise text rendering.
Updated 4 h ago · first seen 11 Sept 2026
model_01M293V7V8B9X6V6JJJTWEZ8PT
Overview
Identity
Identity block not returned by the API for this entity.
Openness
Openness not classified yet — no sourced evidence to place this model in the ontology.
Key facts
- Release date
Source:OpenRouter public model & pricing listingT2observed 12 h agomedium
- Status
Source:Google AI for Developers (Gemini API docs)T1observed 12 h agohigh
- Official page
Source:Google AI for Developers (Gemini API docs)T1observed 12 h agohigh
- API model id
Source:Google AI for Developers (Gemini API docs)T1observed 12 h agohigh
- Openrouter id
Source:OpenRouter public model & pricing listingT2observed 12 h agomedium
Architecture
- Tokenizer
Source:OpenRouter public model & pricing listingT2observed 12 h agomedium
Capabilities
Modalities
- Modalities
- imagetext
- Input
- imagetext
- Output
- imagetext
Capabilities
Tool calling
No
Google AI for Developers (Gemini API docs) · T1
Structured output
No
Google AI for Developers (Gemini API docs) · T1
Reasoning
Yes
Google AI for Developers (Gemini API docs) · T1
Vision
Yes
Google AI for Developers (Gemini API docs) · T1
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
Source:Google AI for Developers (Gemini API docs)T1observed 12 h agohigh
- Max output
Source:Google AI for Developers (Gemini API docs)T1observed 12 h agohigh
- Tokenizer
Source:OpenRouter public model & pricing listingT2observed 12 h agomedium
Providers & Pricing2
All offers in the price terminal →USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.
Price history
Output price · USD / 1M tokens 1 provider
- Google Gemini API
- Google Gemini APIfirst observed $1211 Sept 2026
Input price · USD / 1M tokens 1 provider
- Google Gemini API
- Google Gemini APIfirst observed $211 Sept 2026
Timeline3
Full timeline →Google Gemini API lists Gemini 3 Pro Image (Nano Banana Pro) at $2 in / $12 out per 1M tokens
openrouterNew model: Gemini 3 Pro Image (Nano Banana Pro) (Google)
googleGoogle Gemini API lists Gemini 3 Pro Image (Nano Banana Pro) at $2 in / $12 out per 1M tokens
google
Change history56
Viewing AI Atlas as of 12 Sept 2026 — attributes exactly as the atlas knew them on that day; later corrections are not shown.
Back to today →Attributes as of 12 Sept 2026 23 claims in force
- Family
- Gemini 3
- Release date
- 18 Jun 2026
- Status
- active
- Context window
- 65.5K tokens
- Max output
- 32.8K tokens
- Modalities
- image, text
- Input modalities
- image, text
- Output modalities
- image, text
- Tokenizer
- Gemini
- API model id
- gemini-3-pro-image
- Capabilities
- image_generation, reasoning, search_grounding
- Capabilities raw
- Image generation, Search grounding, Thinking
- Latest update
- 2025-11
- Openrouter id
- google/gemini-3-pro-image
- Openrouter listed at
- 18 Jun 2026
- Reasoning
- Yes
- Structured output
- No
- Supported parameters
- include_reasoning, max_tokens, reasoning, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_p
- Tool calling
- No
- Versions
- {"stable":["gemini-3-pro-image"]}
- Vision
- Yes
Familyfamily1
Release daterelease_date1
Statusstatus1
Context windowcontext_length5conflicting claims
Max outputmax_output_tokens1
Modalitiesmodalities1
Input modalitiesmodalities_input1
Output modalitiesmodalities_output1
Tokenizertokenizer1
API model idapi_model_id1
Official pageofficial_url1
Capabilitiescapabilities1
Descriptiondescription24
Latest updatelatest_update1
Openrouter idopenrouter_id1
Reasoningreasoning1
Structured outputstructured_output5conflicting claims
Supported parameterssupported_parameters1
Tool callingtool_calling5conflicting claims
Versionsversions1
Visionvision1
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
Provenance
Attributed facts
22
Source tiers
T1T217 / 5
Freshest observation
4 h ago
Conflicts
18 flagged
Source documents 4
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.
Data quality (65/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →