LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Nano Banana Pro

google·google/gemini-3-pro-image·GA·Closed·gemini-pro series·Image gen
Nano Banana Pro for higher-fidelity image generation and design-heavy edits

Nano Banana Pro by google is offered by 12 providers on this page. Its official list price is $2.00 per 1M input tokens and $120 per 1M output tokens.

The context window is 131,072 tokens at the reference host, but hosts report different limits, from 65,536 to 1,048,576, so the usable window depends on the provider you pick. It supports reasoning and structured output. Accepted input modalities are Text, Image, and PDF. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-01.

Specs & pricing

Input / output per 1M tokens
Official price·Google
$2.00 / $120
Blended $31.50 · Cache read —
Lowest paid·PoeGateway
$2.00 / $12.00
Blended $4.50 · 1× spread
Context
131,072
Output limit
32,768
Knowledge cutoff
2025-01
Released / updated
2026-05-28 / 2026-05-28
Capabilities
✓ ReasoningTool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDF

Estimate image generation

Direct tariff calculation

Select one official tariff and enter the directly billed image count or image-token quantity. Size and quality are selected in the tariff.

Estimated cost
$0.13
Unit rate: $0.13/image
Google Vertex AI · 1K / 2K
Official source ↗

Official image generation pricing2 tariffs

Google Vertex AI ↗GlobalChecked 2026-09-28
Billed mediaConditionsOfficial price
Output images
1K / 2K
$0.13 / image
Output images
4K
$0.24 / image

Image prices use the vendor's published billing unit. Text or image input tokens may be billed separately where the tariff notes this.

Available at 12 providers12 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Poe
google/nano-banana-pro
Gateway$2.00$12.00$0.20—65,536 ⚠—
Kilo GatewayGateway$2.00$12.00$0.20$0.3865,536 ⚠32,768
AbacusGateway$2.00$12.00$0.20—65,536 ⚠32,768
OpenRouterGateway$2.00$12.00$0.20$0.38131,07232,768
Vercel AI GatewayCloud$2.00$12.00$0.20—65,536 ⚠32,768
Eden AIGateway$2.00$12.00$0.20$0.3865,536 ⚠32,768
RequestyGateway$2.00$12.00$0.20$4.501,048,576 ⚠32,768
Eden AIGateway$2.00$12.00$0.20$0.3865,536 ⚠32,768
GoogleOfficial
gemini-3-pro-image-preview
First-party$2.00$120——131,07232,768
GoogleOfficialFirst-party$2.00$120——65,536 ⚠32,768
AIHubMixGateway$2.00$120——65,536 ⚠32,768
VertexOfficialCloud$2.00$120$0.20—65,536 ⚠32,768

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.

Reasoning control

effort = higheffort = loweffort = noneeffort = mediumeffort = max

Interleaved thinking (reasoning between tool calls) is declared by 1 of 12 providers.

4 / 12 providers expose no reasoning control (reasoning_options: []).

Your usage cost

1Poe$784.00
2Kilo Gateway$784.00
3Abacus$784.00
4OpenRouter$784.00
5Vercel AI Gateway$784.00
6Eden AI$784.00
9Vertex · Official$6,184.00
Switch to Poe to save $5,400.00/mo (87%)
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$120$02026-08-132026-09-072026-08-13 · Input list $2.002026-08-21 · Input list $2.002026-08-28 · Input list $2.002026-09-01 · Input list $2.002026-09-07 · Input list $2.002026-08-13 · Output list $1202026-08-21 · Output list $1202026-08-28 · Output list $1202026-09-01 · Output list $1202026-09-07 · Output list $1202026-08-13 · Min blended $4.502026-08-21 · Min blended $4.052026-08-28 · Min blended $4.502026-09-01 · Min blended $2.252026-09-07 · Min blended $4.50

Artificial Analysis arenas2 arenas

Text to imageGemini 3 Pro Image1102±8#11 of 166
Image editingGemini 3 Pro Image1099±8#13 of 80

Elo from human preference matchups run by Artificial Analysis. Each arena is anchored separately, so Elo is only comparable within one arena, against the other models on that board, and the 95% confidence interval (shown as ±) indicates how much of a gap is noise. Rank is over the whole arena, including models not listed here.

Related models

Gemini 3.5 Live Translate Previewsame series$3.50 / $21.00Gemini Pro Latestsame series$2.00 / $12.00Deep Research Max Preview (Apr-21-2026)same series$2.00 / $12.00GLM-5.2cheaper alternative$1.40 / $4.40Kimi K3cheaper alternative$3.00 / $15.00GPT OSS 120Bcheaper alternative$2.92 / $2.92GLM-5.3cheaper alternative$1.40 / $4.40
Data partly from models.dev (MIT) · Google official docs ↗