Nano Banana 2.1
Last verified October 12, 2026 · Google pricing ↗$1.50/1M input · $30.00/1M output · 131K context · Google
Nano Banana 2.1 costs $1.50 per 1M input tokens and $30.00 per 1M output tokens from Google, with a 131K-token context window. A typical chat reply (1,500 tokens in, 400 out) costs $0.014, or $142.50 per 10,000 requests. On that workload it is cheaper than 22 of the 175 other buyable models tracked here.
Count Tokens
—
Tokens
—
Input Cost
—
Output Cost
Estimate Monthly Cost
Monthly Cost Estimator
Quick:
<$0.0001/mo
Pick a preset above or enter custom usage
What Nano Banana 2.1 Costs Per Request
At $1.50 per 1M input and $30.00 per 1M output tokens, before caching or batch discounts.
| Workload | Input / output tokens | Per request | Per 10,000 requests |
|---|---|---|---|
| Chat reply | 1,500 / 400 | $0.014 | $142.50 |
| RAG answer over retrieved docs | 8,000 / 600 | $0.030 | $300.00 |
| Coding-agent step | 30,000 / 2,000 | $0.105 | $1050.00 |
Nano Banana 2.1 vs Similarly Priced Models
Nearest buyable models by price, with the RAG answer above (8,000 in / 600 out) priced on each.
| Model | Input /1M | Output /1M | Context | RAG answer |
|---|---|---|---|---|
| Nano Banana 2.1 Google | $1.50 | $30.00 | 131K | $0.030 |
| Gemini 3.1 Flash Lite Image Google | $0.250 | $30.00 | 131K | $0.020 |
| Claude Opus 5 Anthropic | $5.00 | $25.00 | 1.0M | $0.055 |
| GPT-5.5 OpenAI | $5.00 | $30.00 | 1.1M | $0.058 |
Alternatives to Nano Banana 2.1
Cheaper Alternative
Claude Opus 5
$5.00 in · $25.00 out · Anthropic
5% cheaper with same or larger context
Premium UpgradeGPT-5.5
$5.00 in · $30.00 out · OpenAI
Upgrade with 1050K context and 128K max output
Same ProviderGemini 3.1 Flash Lite Image
$0.250 in · $30.00 out · Google
4% cheaper in Google ecosystem
Pricing Details
GoogleImage generation model, GA 2026-10-06, model ID gemini-nano-banana-2.1 (Google dropped the gemini-3.x-flash-image naming). Replaces Gemini 3.1 Flash Image (Nano Banana 2), which the changelog deprecated the same day with no shutdown date. The stored output rate is the IMAGE output rate of $30.00/1M, half Nano Banana 2's $60. Every other line went UP: input $1.50/1M (3x NB2's $0.50) and text plus thinking output $7.50/1M (2.5x NB2's $3.00). Per image from Google's pricing footnote: 1,120 tokens at 1K = $0.0336, 1,680 at 2K = $0.0504, 3,780 at 4K = $0.113. The 4K count is 50% higher than NB2's 2,520, so 4K saves only 25% ($0.151 to $0.113) while 1K and 2K halve. Some coverage quotes $0.0756 at 4K, which is NB2's 2,520 tokens at the new rate and is wrong. 512px output is supported but has no published price. At 1K the per-image price equals Nano Banana 2 Lite's $0.0336 to the cent, though Lite's input ($0.25) and text ($1.50) rates are 6x and 5x lower. Batch halves every line: $0.75 input, $3.75 text, $15.00 image, so $0.0168 / $0.0252 / $0.0567 per image. No context-caching rate listed. No free tier. Thinking on by default at medium (minimal / medium / high), billed at the $7.50 text rate, so per-image figures are a floor. Break-even against NB2 at 1K: a request needs 33,600 input tokens or about 7,470 thinking tokens before the extra input and text cost erases the image saving. Up to 10 object, 4 character and 3 style reference images per the image-generation docs. Aspect ratios 1:1 to 21:9. SynthID on every image; Google Search grounding supported ($14/1,000 after 5,000 free/month). LMArena text-to-image (2026-10-07, early, 5,310 votes): 1328, 6th, against NB2 1262 (11th), NB2 Lite 1250 (15th), Nano Banana Pro 1248 (16th) and GPT Image 2.5 Sunburst 1425 (1st). Google's own Elo figures (1,050 vs 990 for NB2) appear only in press coverage. Estimated tokens.
Input / 1M tokens
$1.5
Output / 1M tokens
$30
Context Window
131K
Max Output
33K
Price History
No price change recorded since 2026-10-12, when this site started tracking this model; it launched on 2026-10-06.
Frequently Asked Questions
Common questions about Nano Banana 2.1 pricing and usage
How much does Nano Banana 2.1 cost?
Nano Banana 2.1 costs $1.5 per 1 million input tokens and $30 per 1 million output tokens. This pricing is set by Google.
What tokenizer does Nano Banana 2.1 use?
Nano Banana 2.1 uses the cl100k_base tokenizer. This tokenizer has a vocabulary of ~100,000 tokens and is widely used across many models.
What is Nano Banana 2.1's context window?
Nano Banana 2.1 supports a context window of 131K tokens (131,072 tokens). The maximum output length is 33K tokens.
How does Nano Banana 2.1 compare to other models?
On an 8,000-token-in, 600-token-out RAG answer, Nano Banana 2.1 costs $0.030 per request. The nearest-priced alternatives cost: Gemini 3.1 Flash Lite Image (Google) $0.020, Claude Opus 5 (Anthropic) $0.055, GPT-5.5 (OpenAI) $0.058. The table above lists their full rates and context windows.
How do I count tokens for Nano Banana 2.1?
Use the token counter at the top of this page or visit the homepage calculator. Paste your text and it will show the exact token count and cost for Nano Banana 2.1 using the cl100k_base tokenizer.