Nano Banana 2 Serverless API

Fast photorealistic images — ideal for marketing and ads.

~33.17s
POST /v2/nano-banana-2 · submit + poll
 1# pip install "segmind>=1.1.0"
 2# export SEGMIND_API_KEY="YOUR_API_KEY"
 3import segmind
 4
 5# Async (v2): submit to the queue and block until COMPLETED.
 6# run() returns the final result dict (600s deadline, 1.0s poll by default).
 7result = segmind.run(
 8    "nano-banana-2",
 9    seed=420875,
10    prompt="A professional photograph of a beautifully crafted hand-painted gold leaf sign on a glass window pane. The central focus is the text 'MEXITALY' rendered in an elegant, red and gold script font. Below it, in larger, bold, gold beveled letters with a deep red shadow and gold outline, are the words 'TORNABUONI'. Underneath, in smaller, teal and cream script lettering, is 'Strada64', followed by 'BarandRestaurant' on the final line in the same teal and cream script style. The entire text composition is framed by intricate gold and teal decorative flourishes and stylized star motifs. The reflection of a warm, bustling European street, specifically Via de' Tornabuoni in Florence with its historic architecture and pedestrian crowds at twilight, is visible through the glass pane, adding depth to the image. The glass itself has a slight texture. The perspective is a straight-on medium shot, capturing the details of the lettering and the atmospheric reflection.",
11    image_urls=[],
12    web_search=False,
13    aspect_ratio="1:1",
14    output_format="jpg",
15    thinking_level="minimal",
16    safety_tolerance=4,
17    output_resolution="1K",
18    response_modalities="TEXT_AND_IMAGE",
19)
20print(result["status"])                      # COMPLETED
21print(result.get("output"))                  # model output (e.g. media URL)
22print(result["metrics"]["inference_time"])   # server compute seconds
23
24# --- Or submit + poll manually (track request_id, control the cadence) ---
25from segmind import SegmindClient, InferenceFailed, InferenceTimeout
26
27client = SegmindClient()                      # reads SEGMIND_API_KEY
28payload = {
29    "seed": 420875,
30    "prompt": "A professional photograph of a beautifully crafted hand-painted gold leaf sign on a glass window pane. The central focus is the text 'MEXITALY' rendered in an elegant, red and gold script font. Below it, in larger, bold, gold beveled letters with a deep red shadow and gold outline, are the words 'TORNABUONI'. Underneath, in smaller, teal and cream script lettering, is 'Strada64', followed by 'BarandRestaurant' on the final line in the same teal and cream script style. The entire text composition is framed by intricate gold and teal decorative flourishes and stylized star motifs. The reflection of a warm, bustling European street, specifically Via de' Tornabuoni in Florence with its historic architecture and pedestrian crowds at twilight, is visible through the glass pane, adding depth to the image. The glass itself has a slight texture. The perspective is a straight-on medium shot, capturing the details of the lettering and the atmospheric reflection.",
31    "image_urls": [],
32    "web_search": False,
33    "aspect_ratio": "1:1",
34    "output_format": "jpg",
35    "thinking_level": "minimal",
36    "safety_tolerance": 4,
37    "output_resolution": "1K",
38    "response_modalities": "TEXT_AND_IMAGE",
39}
40job = client.submit_async("nano-banana-2", **payload)
41print(job.request_id)                         # available immediately
42try:
43    result = job.wait(timeout=600, interval=1.0)
44except InferenceTimeout as e:
45    print("still running:", e.request_id)
46except InferenceFailed as e:
47    print("failed:", e.detail)

API Endpoint

POSThttps://api.segmind.com/v1/nano-banana-2

Parameters

promptrequired
string

Image Prompt

Default: "A professional photograph of a beautifully crafted hand-painted gold leaf sign on a glass window pane. The central focus is the text 'MEXITALY' rendered in an elegant, red and gold script font. Below it, in larger, bold, gold beveled letters with a deep red shadow and gold outline, are the words 'TORNABUONI'. Underneath, in smaller, teal and cream script lettering, is 'Strada64', followed by 'BarandRestaurant' on the final line in the same teal and cream script style. The entire text composition is framed by intricate gold and teal decorative flourishes and stylized star motifs. The reflection of a warm, bustling European street, specifically Via de' Tornabuoni in Florence with its historic architecture and pedestrian crowds at twilight, is visible through the glass pane, adding depth to the image. The glass itself has a slight texture. The perspective is a straight-on medium shot, capturing the details of the lettering and the atmospheric reflection."
aspect_ratiooptional
string

Image shape. Auto lets model decide, 16:9 for cinematic.

Default: "1:1"
Allowed values (15 total):
"auto""1:1""2:3""3:2""4:3""3:4""4:5""5:4""16:9""9:16"+5 more
image_urlsoptional
string[]

Reference image URLs for style guidance. Up to 14 images.

output_formatoptional
string

Image file type. PNG for quality, WebP for web optimization.

Default: "jpg"
Allowed values :
"jpg""png"
output_resolutionoptional
string

Determine image clarity. Select '2K' for clarity in digital presentations.

Default: "1K"
Allowed values :
"512px""1K""2K""4K"
response_modalitiesoptional
string

Output type. IMAGE for image-only, TEXT_AND_IMAGE for both.

Default: "TEXT_AND_IMAGE"
Allowed values :
"TEXT_AND_IMAGE""IMAGE"
safety_toleranceoptional
integer

Content moderation level. 1 = strictest, 6 = least strict.

Default: 4
Allowed values :
123456
seedoptional
integer

Random seed for reproducible outputs. Same seed yields similar images.

Default: 420875
thinking_leveloptional
string

Reasoning depth. High for complex prompts, minimal for fast output.

Default: "minimal"
Allowed values :
"minimal""high"
web_searchoptional
boolean

Enable for real-time data. Recommended for news-related prompts.

Default: false

Response Type

Returns: Image

Asynchronous requests (v2)

Use Async for video, long-running (>~60s), or high-concurrency workloads; Sync is simplest for fast image & LLM calls. Async submits a request and you poll it to completion.

  1. 1
    POST /v2/nano-banana-2

    Submitreturns request_id, status_url, response_url

  2. 2
    GET /v2/requests/{id}/status

    Polluntil COMPLETED or FAILED

  3. 3
    GET /v2/requests/{id}

    Resultfinal response body

Status states

QUEUEDAccepted, waiting for a worker
PROCESSINGRunning on a worker
COMPLETEDDone — result body is ready
FAILEDErrored (incl. content/RAI blocks)
  • A FAILED request is served as HTTP 422 — the body still carries the error detail.
  • An unknown or expired request_id returns HTTP 404.
  • Results are retained for 1 hour, then expire.
  • Content / RAI blocks surface as FAILED, not a separate state.
  • Track completion by polling the status endpoint.

Common Error Codes

The API returns standard HTTP status codes. Detailed error messages are provided in the response body.

400

Bad Request

Invalid parameters or request format

401

Unauthorized

Missing or invalid API key

403

Forbidden

Insufficient permissions

404

Not Found

Model or endpoint not found

406

Insufficient Credits

Not enough credits to process request

429

Rate Limited

Too many requests

500

Server Error

Internal server error

502

Bad Gateway

Service temporarily unavailable

504

Timeout

Request timed out