Nano Banana 2.1

New

GoogleReleased Oct 6, 2026

Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro.

Try it in the estimate Compare

Input, per 1M tokens: $1.20$1.10 for holders
Output, per 1M tokens: $6.00$5.52 for holders
Context: 66K tokens
Tokens this week: None yet

Price

Prices for the AI credit you buy. $BINF holders pay up to 8% less.

Charge	Price	Holders	Per
Inputper 1M tokens	$1.20	$1.10	per 1M tokens
Outputper 1M tokens	$6.00	$5.52	per 1M tokens
Web searcheach	$0.011	$0.010	each

Price history

The price per million tokens, by day.

Unchanged since Oct 6, 2026: $1.20 in and $6.00 out per million tokens.

Usage through bInference

Every call our agents make to this model, by day. Counts only: no prompt or answer is stored.

Last 7 days: 0
Last 30 days: 0
All time: 0

InputOutputReasoning

Where it runs

The hosts serving this model now, and how often each answered over the last day.

How to use it

Two settings: our address and your agent’s key. The model is set in each call.

import OpenAI from "openai";const client = new OpenAI({  baseURL: "https://binference.io/api/v1",Address  apiKey: process.env.BINF_API_KEY,Key});const reply = await client.chat.completions.create({  model: "google/gemini-nano-banana-2.1",  messages: [{ role: "user", content: "Summarize today's trades" }],  max_tokens: 1024,});

curl https://binference.io/api/v1/chat/completions \Address  -H "Authorization: Bearer $BINF_API_KEY" \Key  -H "Content-Type: application/json" \  -d '{    "model": "google/gemini-nano-banana-2.1",    "messages": [{ "role": "user", "content": "Hello" }],    "max_tokens": 1024  }'

Step-by-step setup for every app, in the docs

Common questions

More from Google

Gemini 3.8 FlashGoogle1M$0.60 in · $3.00 out$0.55 in · $2.76 out Gemini 3.7 FlashGoogle1M$0.60 in · $3.00 out$0.55 in · $2.76 out Gemini 3.6 FlashGoogle1M$0.60 in · $3.00 out$0.55 in · $2.76 out Gemini 3.5 Flash LiteGoogle1M$0.24 in · $2.00 out$0.22 in · $1.84 out

Price

Holders

Inputper 1M tokens

$1.20

$1.10

per 1M tokens

Outputper 1M tokens

$6.00

$5.52

per 1M tokens

Web searcheach

$0.011

$0.010

each

Host	Answered, last day	Context
Google AI Studio, answering	99.9%	66K

Host

Answered, last day

Context

Google AI Studio

99.9%

66K

import OpenAI from "openai";const client = new OpenAI({ baseURL: "https://binference.io/api/v1",Address apiKey: process.env.BINF_API_KEY,Key});const reply = await client.chat.completions.create({ model: "google/gemini-nano-banana-2.1", messages: [{ role: "user", content: "Summarize today's trades" }], max_tokens: 1024,});

curl https://binference.io/api/v1/chat/completions \Address -H "Authorization: Bearer $BINF_API_KEY" \Key -H "Content-Type: application/json" \ -d '{ "model": "google/gemini-nano-banana-2.1", "messages": [{ "role": "user", "content": "Hello" }], "max_tokens": 1024 }'

Nano Banana 2.1

Price

Price history

Usage through bInference

Where it runs

How to use it

Common questions

How much does Nano Banana 2.1 cost?

How does my agent use Nano Banana 2.1?

How much can Nano Banana 2.1 read at once?

What can Nano Banana 2.1 do?

Are my prompts stored?

More from Google

Nano Banana 2.1

Price

Price history

Usage through bInference

Where it runs

Where it runs

How to use it

Common questions

How much does Nano Banana 2.1 cost?

How does my agent use Nano Banana 2.1?

How much can Nano Banana 2.1 read at once?

What can Nano Banana 2.1 do?

Are my prompts stored?

More from Google

Where it runs