LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Nano Banana 2

google·google/gemini-3.1-flash-image·GA·Closed·gemini-flash series·Image gen
Image model for prompt-driven generation, editing, and visual design workflows

Specs & pricing

Input / output per 1M tokens
Official price·Google
$0.50 / $3.00
Blended $1.13 · Cache read —
Lowest paid·RequestyGateway
$0.50 / $2.00
Blended $0.88 · 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
TextImageVideoPDF

Nano Banana 2 by google is offered by 12 providers on this page. Public prices are shown for 11 of them. Its official list price is $0.50 per 1M input tokens and $3.00 per 1M output tokens. The lowest paid channel is Requesty at $0.50 / $2.00 per 1M, about 1.3× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.

The context window is 131,072 tokens at the reference host, but hosts report different limits, from 32,768 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, Video, 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.

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
$0.045
Unit rate: $0.045/image
Google Vertex AI · 512
Official source ↗

Official image generation pricing4 tariffs

Google Vertex AI ↗GlobalChecked 2026-11-10
Billed mediaConditionsOfficial price
Output images
512
$0.045 / image
Output images
1K
$0.067 / image
Output images
2K
$0.10 / image
Output images
4K
$0.15 / 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 providers11 with public prices

  • ProviderInput / Output
  • RequestyGateway
    $0.50 / $2.00
    Context 131,072Output limit 32,768
  • VertexOfficialCloud
    $0.50 / $3.00
    Cache read $0.05Context 131,072Output limit 32,768
  • GoogleOfficialFirst-party
    $0.50 / $3.00
    Context 131,072Output limit 32,768
  • Merge GatewayGateway
    $0.50 / $3.00
    Context 32,768 ⚠Output limit 32,768
  • OpenRouterGateway
    $0.50 / $3.00
    Context 131,072Output limit 32,768
  • AIHubMixGateway
    $0.50 / $3.00
    Context 131,072Output limit 32,768
  • Eden AIGateway
    $0.50 / $3.00
    Context 131,072Output limit 32,768
  • Eden AIGateway
    $0.50 / $3.00
    Context 65,536 ⚠Output limit 32,768
  • Kilo GatewayGateway
    $0.50 / $3.00
    Cache read $0.05Context 131,072Output limit 32,768
  • Vercel AI GatewayCloud
    $0.50 / $3.00
    Cache read $0.05Context 131,072Output limit 32,768
  • AbacusGateway
    $0.50 / $3.00
    Context 1,048,576 ⚠Output limit 32,768deprecated
  • KenariGateway
    nano-banana-2
    — / —
    Context 131,072Output limit 32,768hostTable.undisclosed
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
RequestyGateway$0.50$2.00——131,07232,768
VertexOfficialCloud$0.50$3.00$0.05—131,07232,768
GoogleOfficialFirst-party$0.50$3.00——131,07232,768
Merge GatewayGateway$0.50$3.00——32,768 ⚠32,768
OpenRouterGateway$0.50$3.00——131,07232,768
AIHubMixGateway$0.50$3.00——131,07232,768
Eden AIGateway$0.50$3.00——131,07232,768
Eden AIGateway$0.50$3.00——65,536 ⚠32,768
Kilo GatewayGateway$0.50$3.00$0.05—131,07232,768
Vercel AI GatewayCloud$0.50$3.00$0.05—131,07232,768
AbacusGateway$0.50$3.00——1,048,576 ⚠32,768deprecated
Kenari
nano-banana-2
Gateway————131,07232,768hostTable.undisclosed

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 = noneeffort = loweffort = mediumeffort = higheffort = maxeffort = minimalToggle (on / off)

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

2 / 12 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1Vertex · Official$196.00
2Kilo Gateway$196.00
3Vercel AI Gateway$196.00
4Requesty$200.00
5Google · Official$250.00
6Merge Gateway$250.00
The cheapest paid channel is official.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$60.00$02026-08-082026-11-16
2026-11-16Input list $0.50Output list $3.00Min blended $0.88

Artificial Analysis arenas2 arenas

Text to imageGemini 3.1 Flash Image1144±10#13 of 116
Image editingGemini 3.1 Flash Image1125±12#18 of 86

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

Nano Banana 2.1same series$1.50 / $7.50Gemini 3.8 Flash TTSsame series—Gemini 3.8 Livesame series—GLM-5.3-Flashcheaper alternative$0.15 / $0.50DeepSeek V4.1 Flash 1017cheaper alternative$0.15 / $0.60GPT-5.6 Lunacheaper alternative$0.20 / $1.20MiniMax-M3cheaper alternative$0.30 / $1.20Gemini 3 Pro Previewsame lab—Nano Banana 2 Previewsame lab—
Data partly from models.dev (MIT) · Google official docs ↗