← Model list

Nano Banana Pro

google·google/gemini-3-pro-image·GA·Closed·gemini-pro series·Image gen·NEW

Nano Banana Pro for higher-fidelity image generation and design-heavy edits

At a glance
Official price$2.00 / $120 per 1M
Cache read $0.20 · Vertex
Lowest paid$1.80 / $10.80
Requesty Gateway · 1.1× spread
Context65,536
⚠ Providers report 65,536–1,048,576; the table below is authoritative
Output limit32,768
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDF
Knowledge cutoff2025-01
Released / updated2026-05-28 / 2026-05-28

Quality & performance

Artificial Analysis doesn't cover this model (267 of 2059 have data). Quality data comes from independent evals covering widely used models.

Available at 16 providers16 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
RequestyGateway$1.80
tiered >200K: $3.60
$10.80$0.18$4.051,048,57632,768
OpenRouterGateway$2.00$12.00$0.20$0.375131,07232,768
OpenRouter
google/gemini-3-pro-image-preview
Gateway$2.00$12.00$0.20$0.37565,53632,768
FastRouter
google/gemini-3-pro-image-preview
Gateway$2.00$12.0065,53632,768
Poe
google/nano-banana-pro
Gateway$2.00$12.00$0.2065,5360
Vercel AI GatewayCloud$2.00$12.00$0.2065,53632,768
Eden AIGateway$2.00$12.00$0.20$0.37565,53632,768
Eden AI
google/gemini-3-pro-image-preview
Gateway$2.00$12.00$0.20$0.37565,53632,768
Eden AIGateway$2.00$12.00$0.20$0.37565,53632,768
Kilo GatewayGateway$2.00$12.00$0.20$0.37565,53632,768
VertexOfficialFirst-party$2.00$120$0.2065,53632,768

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1Requesty$705.60
2OpenRouter$784.00
3OpenRouter$784.00
4Poe$784.00
5Vercel AI Gateway$784.00
6Eden AI$784.00
14Vertex · Official$6,184.00
Switch to Requesty to save $5,478.40/mo (89%)
Note: this is a gateway; verify availability and rate limits yourself.

Benchmark

No upstream benchmark data for this model. For quality, see the Artificial Analysis intelligence score above.

Reasoning control

effort = noneeffort = loweffort = mediumeffort = higheffort = maxbudget_tokens

8 / 16 providers expose no reasoning control (reasoning_options: []).

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$120$02026-08-132026-08-212026-08-13 · Input list $2.002026-08-21 · Input list $2.002026-08-13 · Output list $1202026-08-21 · Output list $1202026-08-13 · Min blended $4.502026-08-21 · Min blended $4.05