Nano Banana API

Capabilities

Pricing & credits

Each image costs 2 credits, including all supported resolutions and formats. Credits are reserved on acceptance, settled on success and refunded on failure. Generation times out after 30 minutes; refund_failed means refund recovery is pending.

Request idempotency is not supported. Each valid POST creates a new billable task. If a submission outcome is uncertain, query the returned taskId; retrying POST can create another task.

Authentication

Create an API key in the dashboard. The complete key is shown only once. Keep it on your server and send it as a Bearer token on every request.

https://api.seevio.ai

Authorization: Bearer sk_live_your_api_key
Content-Type: application/json

Set the SEEVIO_API_KEY environment variable before running these examples. JavaScript examples run on your server with Node.js; Python examples use the requests package.

Request body

Input parameters

Aspect ratio defaults to auto. Unknown fields, including output quantity, are rejected. Each request generates exactly one image.

Quickstart

Submit this minimal request, save the returned taskId, then use the task query example below. The credits value in the create response is the reserved amount.

curl --fail-with-body https://api.seevio.ai/v1/images/generations \
  -H "Authorization: Bearer $SEEVIO_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
  "model": "nano-banana",
  "input": {
    "prompt": "A minimalist ceramic teapot on a stone pedestal, soft studio lighting",
    "aspect_ratio": "1:1",
    "output_format": "png",
    "generation_type": "text-to-image"
  }
}'

Create task response example

{
  "taskId": "3f2aK9mR7xQp4TnZ8bLc6YwH",
  "credits": 2
}

Text to image

Generate one image asynchronously per request. Supports text-to-image and image-to-image generation with your Seevio API key.

curl --fail-with-body https://api.seevio.ai/v1/images/generations \
  -H "Authorization: Bearer $SEEVIO_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
  "model": "nano-banana",
  "input": {
    "prompt": "A minimalist ceramic teapot on a stone pedestal, soft studio lighting",
    "aspect_ratio": "1:1",
    "output_format": "png",
    "generation_type": "text-to-image"
  }
}'

Image to image

For image editing, set generation_type to image-to-image and provide image_urls. All other parameters use the same contract.

Replace example.com media URLs with your own publicly accessible HTTPS files. The sample URLs illustrate the request shape and are not downloadable sample assets.

curl --fail-with-body https://api.seevio.ai/v1/images/generations \
  -H "Authorization: Bearer $SEEVIO_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
  "model": "nano-banana",
  "input": {
    "prompt": "Change the teapot to matte sage green. Preserve its shape and the studio lighting.",
    "aspect_ratio": "1:1",
    "output_format": "png",
    "generation_type": "image-to-image",
    "image_urls": [
      "https://example.com/teapot.png"
    ]
  }
}'

Query a task

Replace the example ID with the taskId returned by creation. Queries only return tasks owned by the API key's user; inaccessible or unknown IDs return HTTP 404.

Poll every 10–20 seconds as a starting point, back off on HTTP 429 and stop when the status is completed or failed. Prefer webhooks for production. Each code example below performs one query.

curl --fail-with-body https://api.seevio.ai/v1/tasks/3f2aK9mR7xQp4TnZ8bLc6YwH \
  -H "Authorization: Bearer $SEEVIO_API_KEY"

Queued

{
  "id": "3f2aK9mR7xQp4TnZ8bLc6YwH",
  "created_at": 1789171200,
  "model": "nano-banana",
  "credits": 2,
  "status": "queued",
  "billing_status": "reserved",
  "failed_reason": null,
  "data": {
    "results": [],
    "image_expires_at": null,
    "processing_time": null
  }
}

Completed

{
  "id": "3f2aK9mR7xQp4TnZ8bLc6YwH",
  "created_at": 1789171200,
  "model": "nano-banana",
  "credits": 2,
  "status": "completed",
  "billing_status": "charged",
  "failed_reason": null,
  "data": {
    "results": [
      "https://cdn.seevio.ai/api/images/example.png"
    ],
    "image_expires_at": "2026-10-12T00:00:00.000Z",
    "processing_time": 12
  }
}

Failed

When the query returns status=failed, generation has ended unsuccessfully. Read failed_reason for the cause and billing_status for the refund outcome. In this example, refunded means the credits were returned. credits retains the original reserved amount, and the response does not include data.

{
  "id": "3f2aK9mR7xQp4TnZ8bLc6YwH",
  "created_at": 1789171200,
  "model": "nano-banana",
  "credits": 2,
  "status": "failed",
  "billing_status": "refunded",
  "failed_reason": "Image generation failed."
}

Result links are provided for 30 days after storage. After expiry, results is empty.

Webhooks

Set callback_url in the create request to receive a JSON POST when the task completes or fails. Return a 2xx response within 15 seconds. Failed deliveries are retried; process repeated deliveries idempotently by task ID.

Your callback endpoint must accept POST requests with a JSON request body (Content-Type: application/json).

Create a task with a callback

curl --fail-with-body https://api.seevio.ai/v1/images/generations \
  -H "Authorization: Bearer $SEEVIO_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
  "model": "nano-banana",
  "input": {
    "prompt": "A minimalist ceramic teapot on a stone pedestal, soft studio lighting",
    "aspect_ratio": "1:1",
    "output_format": "png",
    "generation_type": "text-to-image"
  },
  "callback_url": "https://example.com/webhooks/seevio"
}'

Callbacks use the task query response structure; refunded failure notifications also include top-level credits_refunded. Use id to identify the task and status to distinguish completed from failed. Notifications may repeat: process them idempotently by id and status. Callbacks are unsigned; verify the task with the authenticated query endpoint. Delivery failure does not refund a successful task.

Task completed: successful callback payload

created_at is the event creation time; task_created_at is the task creation time in Unix seconds. Examples show the recommended fields; responses may contain additional fields.

{
  "id": "3f2aK9mR7xQp4TnZ8bLc6YwH",
  "created_at": 1789171212,
  "model": "nano-banana",
  "credits": 2,
  "status": "completed",
  "billing_status": "charged",
  "failed_reason": null,
  "data": {
    "results": [
      "https://cdn.seevio.ai/api/images/example.png"
    ],
    "image_expires_at": "2026-10-12T00:00:00.000Z",
    "processing_time": 12
  },
  "task_created_at": 1789171200
}

Task failed: failure callback payload

{
  "id": "3f2aK9mR7xQp4TnZ8bLc6YwH",
  "created_at": 1789171212,
  "model": "nano-banana",
  "credits": 2,
  "status": "failed",
  "billing_status": "refunded",
  "failed_reason": "Image generation failed.",
  "task_created_at": 1789171200,
  "credits_refunded": 2
}

Receiver example

export async function POST(request: Request) {
  const callbackData = await request.json();

  if (callbackData.status === "completed") {
    const imageUrls = callbackData.data.results;
    // Save the image URLs and mark this task as completed in your application.
    console.log(callbackData.id, imageUrls);
  }

  if (callbackData.status === "failed") {
    const { failed_reason, credits_refunded } = callbackData;
    // Record the failure reason and refunded credits for this task.
    console.error(callbackData.id, failed_reason, credits_refunded);
  }

  return new Response(null, { status: 200 });
}

This Next.js example reads the JSON callback body and handles completed and failed tasks directly. Add persistence and task-ID deduplication for your application; queue slow work before acknowledging the callback.

Errors

HTTP errors have an error object with code and message. A successfully accepted task can still fail later; query the task or handle its failure callback.

{
  "error": {
    "code": "invalid_request",
    "message": "input.prompt is required."
  }
}

Errors use error.code and error.message: 400 invalid_request, 401 invalid_api_key, 402 insufficient_credits, 403 forbidden, 404 not_found, 429 rate_limited, 500 internal_error. Insufficient provider balance is not a customer 402 error.

Rate limits

Create tasks: each API key allows up to 100 requests per minute by default. Custom rate limits are not currently available.

Query tasks: each API key allows up to 120 requests per minute by default. Query requests and task creation requests are counted separately.

Image and video creation requests share the same API key rate limit.

HTTP 429 includes Retry-After: 60 for creation and Retry-After: 5 for queries. Use backoff and avoid polling more frequently than necessary.

HTTP/1.1 429 Too Many Requests
Content-Type: application/json
Retry-After: 60

{
  "error": {
    "code": "rate_limited",
    "message": "Rate limit exceeded."
  }
}