google

Google: Nano Banana (Gemini 2.5 Flash Image)

google/gemini-2.5-flash-image

The Gemini 2.5 Flash Image model is also known as Nano Banana. In Jevrouter, use its native image interface for generation and reference-image editing even though the upstream catalog lists both text and image outputs.

imagetext

Try in Playground ↗

Provider-supported parameters

These are upstream capabilities. Jevrouter supports the subset described in the API contract; chat input is currently text only.

naspect_ratioinput_references

Capabilities are imported from OpenRouter’s catalog. This does not mean every model has been independently tested by Jevrouter.

Catalog updated: 2026-09-22T08:51:50.371Z · Price version: cmub11bdg010tr82gu0y6vllu:1

Image prices & options

Prices use each provider’s billing unit. We reserve a conservative amount and settle from the usage receipt, releasing unused balance.

Google AI Studio

Usage	Unit	USD	Variant
input image	token	$5.4e-7	Default
output image	token	$0.000054	Default

{
  "n": {
    "type": "range",
    "min": 1,
    "max": 1
  },
  "aspect_ratio": {
    "type": "enum",
    "values": [
      "1:1",
      "2:3",
      "3:2",
      "3:4",
      "4:3",
      "4:5",
      "5:4",
      "9:16",
      "16:9",
      "21:9"
    ]
  },
  "input_references": {
    "type": "range",
    "min": 0,
    "max": 3
  }
}

Google AI Studio

Usage	Unit	USD	Variant
input image	token	$1.5e-7	Default
output image	token	$0.000015	Default

{
  "n": {
    "type": "range",
    "min": 1,
    "max": 1
  },
  "aspect_ratio": {
    "type": "enum",
    "values": [
      "1:1",
      "2:3",
      "3:2",
      "3:4",
      "4:3",
      "4:5",
      "5:4",
      "9:16",
      "16:9",
      "21:9"
    ]
  },
  "input_references": {
    "type": "range",
    "min": 0,
    "max": 3
  }
}

Google AI Studio

Usage	Unit	USD	Variant
input image	token	$3e-7	Default
output image	token	$0.00003	Default

{
  "n": {
    "type": "range",
    "min": 1,
    "max": 1
  },
  "aspect_ratio": {
    "type": "enum",
    "values": [
      "1:1",
      "2:3",
      "3:2",
      "3:4",
      "4:3",
      "4:5",
      "5:4",
      "9:16",
      "16:9",
      "21:9"
    ]
  },
  "input_references": {
    "type": "range",
    "min": 0,
    "max": 3
  }
}

Google Vertex

Usage	Unit	USD	Variant
input image	token	$3e-7	Default
output image	token	$0.00003	Default

{
  "n": {
    "type": "range",
    "min": 1,
    "max": 1
  },
  "aspect_ratio": {
    "type": "enum",
    "values": [
      "1:1",
      "2:3",
      "3:2",
      "3:4",
      "4:3",
      "4:5",
      "5:4",
      "9:16",
      "16:9",
      "21:9"
    ]
  },
  "input_references": {
    "type": "range",
    "min": 0,
    "max": 3
  }
}

JEVROUTER INTEGRATION NOTES · REVIEWED 2026-09-22

What to check in your application

Text-plus-image output capability in the upstream catalog does not expand Jevrouter's text chat request schema.
Send references with input_references on the Images endpoint, and inspect each endpoint's count limits.

Start with the example below, then test representative inputs against your own acceptance criteria.

Make a request

Some models require reference images. Check the input_references range above. Images return base64 data and a usage receipt.

curl --no-buffer https://api.jevrouter.io/v1/images \
  -H "Authorization: Bearer $JEVROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d @- <<'JSON'
{
  "model": "google/gemini-2.5-flash-image",
  "prompt": "An editorial illustration of a tiny greenhouse on a rooftop, warm morning light, muted green palette, no lettering.",
  "n": 1,
  "stream": true
}
JSON

Plan your integration

Generate and save images with Python →Estimate this model’s cost →Budgets, request status and safe retries →

Related models to evaluate

Use identical inputs and scoring rules. No ranking is implied by this selection.

OpenAI: GPT Image 1 Google: Nano Banana Pro (Gemini 3 Pro Image Preview)

Source: OpenRouter model catalog. Imported descriptions and capabilities are provider declarations, not independent benchmark results. Jevrouter currently uses OpenRouter as its managed upstream.