Nano Banana Pro

Vendor: Google Model ID: nano-banana-pro Capability: 2048² · photorealism · extended detail pass · material accuracy Pricing: per image, pro photoreal tier (live rate) Nano Banana Pro adds an extended detail pass and material-refinement step to the base Nano Banana renderer. The result is sharper texture work, cleaner highlights on glass and metal, and better skin / fabric rendering at hero-image scales. The latency cost is real (~2× base Nano Banana); reach for Pro when the image is the deliverable, not when you’re iterating.

Request

curl https://llm.bytespike.ai/v1/images/generations \
  -H "x-api-key: $BYTESPIKE_API_KEY" \
  -H "content-type: application/json" \
  -d '{
    "model": "nano-banana-pro",
    "prompt": "Hero product shot of a luxury watch on dark velvet, dramatic side lighting",
    "size": "2048x2048",
    "n": 1
  }'

Body parameters

Field	Type	Required	Default	Notes
`model`	string	yes	—	`nano-banana-pro`
`prompt`	string	yes	—	English-tuned.
`size`	string	no	`2048x2048`	Supported: `1024x1024`, `2048x2048`, `2048x1536`, `1536x2048`.
`n`	integer	no	1	1–2 images.
`seed`	integer	no	—	Reproducibility supported.
`aspect_ratio`	string	no	—	`1:1` / `9:16` / `16:9` / `4:3` / `3:4`.
`quality`	string	no	`"standard"`	`"standard"` / `"hd"` — `"hd"` adds an additional detail pass.

Response

{
  "created": 1715174400,
  "data": [{"url": "https://cdn.bytespike.ai/img/...", "revised_prompt": "..."}]
}

URLs pre-signed, 24h expiry.

Code examples

curl https://llm.bytespike.ai/v1/images/generations \
  -H "x-api-key: $BYTESPIKE_API_KEY" \
  -H "content-type: application/json" \
  -d '{"model": "nano-banana-pro", "prompt": "Hero product shot...", "size": "2048x2048", "quality": "hd"}'

from openai import OpenAI

client = OpenAI(base_url="https://llm.bytespike.ai/v1", api_key="$BYTESPIKE_API_KEY")
resp = client.images.generate(
    model="nano-banana-pro",
    prompt="Hero product shot of a luxury watch on dark velvet, dramatic side lighting",
    size="2048x2048",
    quality="hd",
)
print(resp.data[0].url)

import OpenAI from "openai"

const client = new OpenAI({
  baseURL: "https://llm.bytespike.ai/v1",
  apiKey: process.env.BYTESPIKE_API_KEY,
})
const resp = await client.images.generate({
  model: "nano-banana-pro",
  prompt: "Hero product shot of a luxury watch on dark velvet, dramatic side lighting",
  size: "2048x2048",
  quality: "hd",
})
console.log(resp.data[0].url)

Errors

Code	Trigger	Billed?
400 / 401 / 402 / 403	Standard	No
451	Prompt blocked by upstream safety	No
5xx	Upstream issue	No (auto-retry)

When to use

Hero / campaign imagery where detail at print scale matters.
Product photography where material rendering is the brief.
For iteration / better text rendering inside the image, see Nano Banana 2.

Limits

Limit	Value
Max output resolution	2048×2048
Max images per call (`n`)	2
Supports init image (img2img)	No
Supports `quality` modifier	Yes (`standard` / `hd`)
Supports seed reproduction	Yes
Sync?	Yes (≤45s for `hd`)
Avg latency for 2048² standard	12-18s
Avg latency for 2048² hd	25-40s

API Reference

Protocol endpoints

OpenAI

Anthropic

DeepSeek

Moonshot

Zhipu

MiniMax

Image

Video

Account & billing

Utility

Request

Body parameters

Response

Code examples

Errors

When to use

Limits

​Request

​Body parameters

​Response

​Code examples

​Errors

​When to use

​Limits

Request

Body parameters

Response

Code examples

Errors

When to use

Limits