Google: Nano Banana (Gemini 2.5 Flash Image)
by GoogleGoogle: Nano Banana (Gemini 2.5 Flash Image) is a large language model from Google. It costs $0.300 per million input tokens and $2.50 per million output tokens. Its context window is 33K tokens.
- Input / 1M tokens
- $0.300
- Output / 1M tokens
- $2.50
- Cached input / 1M
- $0.030
- Context window
- 33K
On repeated prefixes
tokens
This model also charges $0.014 per search request
That is $14.00 per 1,000 requests, billed on top of the token prices above. On a typical 1,000-in / 500-out exchange the tokens cost $0.0015, so the search fee is 9.0× the token cost. Per-token rankings elsewhere ignore this entirely.
Who serves it cheapest
2 hosts serve Nano Banana (Gemini 2.5 Flash Image). Same weights, same API - the price difference is pure margin and routing.
| Provider | Input / 1M | Output / 1M | Context | Throughput | Uptime 24h |
|---|---|---|---|---|---|
| Google AI StudioCheapest | $0.150 | $1.25 | 33K | - | 100.0% |
| $0.300 | $2.50 | 33K | - | 100.0% |
The spread between Google AI Studio and Google is 2.0× for identical weights. Quantization and context limits differ, so check both columns before switching.
About Nano Banana (Gemini 2.5 Flash Image)
Gemini 2.5 Flash Image, a.k.a. "Nano Banana," is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image generation,...
Specifications
| Model ID | google/gemini-2.5-flash-image |
|---|---|
| Provider | |
| Context window | 33K tokens |
| Max output | 8K tokens |
| Input modalities | image, text |
| Output modalities | image, text |
| Knowledge cutoff | 2025-01-31 |
| Open weights | No |
| Released | October 7, 2025 |
Cheaper alternatives
Models that cost less than Nano Banana (Gemini 2.5 Flash Image) while keeping at least half its context window and every input modality it supports.
Frequently asked
How much does Google: Nano Banana (Gemini 2.5 Flash Image) cost?
$0.300 per million input tokens and $2.50 per million output tokens. Cached input reads cost $0.030 per million tokens.
What is the context window of Google: Nano Banana (Gemini 2.5 Flash Image)?
33K tokens, with up to 8K tokens of output per request.
Does Google: Nano Banana (Gemini 2.5 Flash Image) have extra fees beyond per-token pricing?
Yes. Google: Nano Banana (Gemini 2.5 Flash Image) charges $0.014 per search request - $14.00 per 1,000 requests - on top of $0.300 per million input tokens and $2.50 per million output tokens. On a typical 1,000-input / 500-output exchange the search fee alone is 9.0× the token cost.
Which provider serves Google: Nano Banana (Gemini 2.5 Flash Image) cheapest?
Google AI Studio at $0.150 per million input tokens - 2.0× cheaper than Google, the most expensive of the 2 hosts serving it.
Confirm against the source: Google official pricing.