The Orchestrator › Models › Google
Google: 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...
Specifications
| Provider | |
| Model ID | google/gemini-3-pro-image |
| Context window | 131K tokens (131,072) |
| Modalities | text + image → text + image |
| Tokenizer | Gemini |
| Router sources | OpenRouter, Vercel AI Gateway |
| Released | 2026-06-18 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | Mandatory |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | google/gemini-3-pro-image | $2.00 | $12.00 | 131K |
| standard | Vercel AI Gateway | google/gemini-3-pro-image | $2.00 | $12.00 | 66K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $2.00 | $12.00 | 66K |
| 2026-11-14 | $2.00 | $12.00 | 131K |
Capabilities
Vision (image input)Agentic tool useStructured outputsReasoning (always on)Controllable reasoningNo training on inputs (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
include_reasoning, max_tokens, reasoning, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_p