🎁 Sign up, get $1. Join Discord, get $5！
Models
Experience Center
Activity
Docs
Resource
Console
G

Gemini 2.5 Flash Image

GoogleModel IDgemini-2.5-flash-image
G

Gemini 2.5 Flash Image

GoogleModel IDgemini-2.5-flash-image

Gemini 2.5 Flash Image, also known as Nano Banana, is Google's high-speed native image generation and conversational editing model optimized for high-volume, low-latency creative workflows and multimodal image understanding.

ModeImage / Text → Image / Text
Input price$0.1 / request
Output priceUnknown
Context length32768 tokens

Capabilities & limits

Use cases
Not available
Model capabilities
Not available
Model Brand
Google
Input modality
Image / Text
Output modality
Image / Text
Max output
32768 tokens

Pricing

ProviderBilling typePrice summary
G
Gemini-Balanced
Per call
Input price$0.1per request
Completion price—
Cache read price—
Cache write price—
G
Gemini-Custom
Per call
Input price$0.1per request
Completion price—
Cache read price—
Cache write price—

Integration

Code Example

curl http://127.0.0.1:4179/v1beta/models/gemini-2.5-flash-image:generateContent \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2.5-flash-image",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'

Replace <YOUR_API_KEY> with the API key generated on your token management page.

Authentication

All requests must include the Authorization: Bearer <TOKEN> header.

Endpoint Path

POST
google-generate-content

Supported Parameters

ParameterTypeDefaultDescription
integer-This sets the upper limit for the number of tokens the model can generate in response. It won't produce more than this limit. The maximum value is the context length minus the prompt length.
map-Forces the model to produce specific output format. Setting to `{ "type": "json_object" }` enables JSON mode, which guarantees the message the model generates is valid JSON. **Note**: when using JSON mode, you should also instruct the model to produce JSON yourself via a system or user message.
integer-If specified, the inferencing will sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed for some models.
array-Stop generation immediately if the model encounter any token specified in the stop array.
boolean-If the model can return structured outputs using response\_format json\_schema.
float1.0This setting influences the variety in the model's responses. Lower values lead to more predictable and typical responses, while higher values encourage more diverse and less common responses. At 0, the model always gives the same response for a given input.
float1.0This setting limits the model's choices to a percentage of likely tokens: only the top tokens whose probabilities add up to P. A lower value makes the model's responses more predictable, while the default setting allows for a full range of token choices. Think of it like a dynamic Top-K.

Rate Limits

RPM

No rate limits configured

RPM = requests per minute.