6 models · image
Nano Banana API
Nano Banana is a family of AI image models made by Google. varg runs 6 of them on one API key: Nano Banana 2.1, Nano Banana 2, Nano Banana 2 Edit and 3 more. Between them they cover text to image and image to image; they return images.
- Price
- From $0.04 per run Nano Banana 2 Lite
- Nano Banana 2.1
- From $0.05 per run
- Made by
- Flagship id
nano_banana_2_1
Every Nano Banana model runs on one varg API key and one credit balance, the same as every other model here. You pay the provider's price, with no markup.
curl -X POST https://api.varg.ai/v2/tools/image/call \
-H "Authorization: Bearer $VARG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nano_banana_2_1",
"prompt": "An infographic poster explaining how a coffee bean becomes espresso, five labelled steps, clean flat illustration.",
"aspect_ratio": "3:4"
}'Nano Banana models and prices
Nano Banana on varg starts from $0.04 per run (Nano Banana 2 Lite). Prices are in US dollars and are the provider's own, with no markup. A "from" price is the cheapest request the catalog states for that model; each model's page has every rate and input. The descriptions are the catalog's own, shortened.
| Model | Catalog description | Takes | Price | Typical time |
|---|---|---|---|---|
Nano Banana 2.1nano_ | Nano Banana 2.1 by Google. Top-ranked image generation and editing: sharper layouts and text, consistent subjects, 1K-4K and extreme aspect ratios. | Text to image, Image to image | From $0.05 per runfrom $0.05/image | ~20 s |
Nano Banana 2nano_ | Google Gemini 2 Flash Image. Fast, cost-effective image generation. | Text to image, Image to image | From $0.06 per runfrom $0.045/image | ~15 s |
Nano Banana 2 Editnano_ | Google Gemini 2 Flash image editing. Reference-based generation. | Image to image | From $0.06 per runfrom $0.06/image | ~15 s |
Nano Banana 2 Litenano_ | Google Nano Banana 2 Lite. Text-to-image and image editing. | Text to image, Image to image | From $0.04 per run$0.034/image | ~10 s |
Nano Banana Pronano_ | Google Gemini 3 Pro Image. Text-to-image generation. | Text to image, Image to image | From $0.14 per runfrom $0.134/image | ~15 s |
Nano Banana Pro Editnano_ | Google Gemini 3 Pro Image editing. Reference-based generation. | Image to image | From $0.15 per runfrom $0.15/image | ~15 s |
Call the Nano Banana API
The call below runs Nano Banana 2.1. For another Nano Banana model, put its id from the table in "model"; the rest of the request keeps its shape.
REST
POST https://api.varg.ai/v2/tools/image/call with Authorization: Bearer $VARG_API_KEY. It answers 202 with a job right away; poll GET /v2/jobs/{id} until its status is completed, then read output.outputs[0].url.
curl -X POST https://api.varg.ai/v2/tools/image/call \
-H "Authorization: Bearer $VARG_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nano_banana_2_1",
"prompt": "An infographic poster explaining how a coffee bean becomes espresso, five labelled steps, clean flat illustration.",
"aspect_ratio": "3:4"
}'From Claude, ChatGPT or Cursor (MCP)
The varg MCP server, https://mcp.varg.ai/mcp, runs Nano Banana 2.1 with call_tool. Sign in with varg, no API key to paste. How to connect it
claude mcp add --transport http varg https://mcp.varg.ai/mcp{
"tool": "image",
"input": {
"model": "nano_banana_2_1",
"prompt": "An infographic poster explaining how a coffee bean becomes espresso, five labelled steps, clean flat illustration.",
"aspect_ratio": "3:4"
},
"wait": true
}From a terminal (CLI)
vargai is the varg command line: every tool of the MCP server is a command. Install and log in
curl -fsSL https://varg.ai/install | sh
vargai call_tool --tool image '{"model":"nano_banana_2_1","prompt":"An infographic poster explaining how a coffee bean becomes espresso, five labelled steps, clean flat illustration.","aspect_ratio":"3:4"}'How billing works
Every model is billed at its provider's price with no markup, from one credit balance: 1 credit is $0.01. varg's fee is on the top-up, not on the run: 5.5% of the credits you buy ($0.80 at the least), or 8% for a team workspace. Pricing
Nano Banana compared
Price, limits and inputs side by side, from the same catalog as this page.
How to use Nano Banana
Step-by-step pages on varg how to.
Nano Banana API: questions
- How much does the Nano Banana API cost on varg?
- The lowest price the catalog states in the Nano Banana family is from $0.04 per run ($0.034/image), on Nano Banana 2 Lite. Every model is billed at its provider's price with no markup, from one credit balance: 1 credit is $0.01. For the exact price of a request before you run it, send the same body to POST https://api.varg.ai/v2/estimate.
- Which Nano Banana models are on varg?
- 6: Nano Banana 2.1 (from $0.05 per run), Nano Banana 2 (from $0.06 per run), Nano Banana 2 Edit (from $0.06 per run), Nano Banana 2 Lite (from $0.04 per run), Nano Banana Pro (from $0.14 per run) and Nano Banana Pro Edit (from $0.15 per run). Each has its own page with the parameters and a call to copy.
- Which Nano Banana models take an image?
- All 6: Nano Banana 2.1, Nano Banana 2, Nano Banana 2 Edit, Nano Banana 2 Lite, Nano Banana Pro and Nano Banana Pro Edit. The catalog lists image to image for them; pass the image as a URL in "files".
- How long do Nano Banana requests take?
- Typically from about 10 s (Nano Banana 2 Lite) to about 20 s (Nano Banana 2.1), by the catalog's estimates for each model's fastest route. The API answers at once with a job id, so nothing waits on an open connection while it runs.
- How do I call the Nano Banana API?
- Send POST https://api.varg.ai/v2/tools/image/call with the header "Authorization: Bearer $VARG_API_KEY" and a JSON body that includes "model", for example "model": "nano_banana_2_1". The call answers 202 with a job right away. Poll GET https://api.varg.ai/v2/jobs/{id} until "status" is "completed", then read output.outputs[0].url, or pass options.webhook_url to be called back.
- Can I use Nano Banana from Claude, ChatGPT or Cursor?
- Yes. Add the varg MCP server (https://mcp.varg.ai/mcp) to Claude, ChatGPT, Cursor or any other MCP client and sign in with varg, with no API key to paste. The agent runs a model with call_tool, passing tool "image" and the model id, for example "model": "nano_banana_2_1".
More model APIs
Same API key, same request shape: change the model string to switch.
For AI agents: each model above has its full spec as Markdown at varg.ai/models/nano_banana_2_1.md (swap the id), and every model is listed in varg.ai/models/llms.txt.