Nano Banana 2.1
text+image->text+image
Nano Banana 2.1 is a compact variant, chosen for high throughput and low cost rather than absolute capability. Available via Google. 65,536-token context. Mid-tier pricing.
Nano Banana 2.1 is a multimodal AI model from Google. It costs $1.500 per million input tokens and $7.500 per million output tokens (blended $3.300/M), with a 65,536-token context window.
INPUT
$1.500/M
per million input tokens
OUTPUT
$7.500/M
per million output tokens
CONTEXT
65,536
tokens
What it is good at
- Sub-second latency
- Affordable at scale
- Good for routing & classification
- Multimodal: handles images alongside text
Typical use cases
- Routing & classification
- Bulk summarisation
- Realtime chat UX
Benchmarks
No published benchmark scores tracked for this model yet. Frontier and reasoning models from major providers have scores; smaller models and inference-host variants typically inherit the underlying open-weights score.
More from Google
See all 24 →Gemini 3.5 Pro
Frontier · 1,000,000 ctx
in $2.000/Mout $12.000/M
Gemini 3.6 Flash
Balanced · 1,050,000 ctx
in $1.500/Mout $7.500/M
Gemini 3.5 Flash
Balanced · 1,000,000 ctx
in $1.500/Mout $9.000/M
Gemini 3.1 Pro
Frontier · 1,000,000 ctx
in $2.000/Mout $12.000/M
Gemini 3 Pro
Frontier · 1,000,000 ctx
in $2.000/Mout $12.000/M
Gemini 3 Flash
Efficient · 1,000,000 ctx
in $0.500/Mout $3.000/M
Frequently asked questions
How much does Nano Banana 2.1 cost?
Nano Banana 2.1 costs $1.500 per million input tokens and $7.500 per million output tokens, for a blended reference rate of $3.300 per million tokens.
What is Nano Banana 2.1's context window?
Nano Banana 2.1 supports up to 65,536 tokens of context in a single request.
What is Nano Banana 2.1 best for?
Nano Banana 2.1 is well suited to Sub-second latency, Affordable at scale and Good for routing & classification.
Who makes Nano Banana 2.1?
Nano Banana 2.1 is developed and served by Google.