> ## Documentation Index
> Fetch the complete documentation index at: https://docs.pollo.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Nano Banana 2.1 API Documentation

> Nano Banana 2.1 API generates and edits images with improved realism, sharp text rendering, and clear infographic layouts. It keeps characters and objects consistent across reference images. Integrate the Nano Banana 2.1 API now.

Check out Nano Banana 2.1 API pricing [here](https://api.pollo.ai/pricing?modelName=nano-banana-2-1\&modelType=image), cheaper than Fal AI.


## OpenAPI

````yaml POST /v1/generation/google/nano-banana-2-1/image
openapi: 3.0.3
info:
  title: Pollo | AI Video Collection
  description: >-
    ✨RESTful API Document. Model discovery: GET /api/v1/model-specs (public,
    keyless).
  version: 1.0.0
servers:
  - url: https://pollo.ai/api/platform
security: []
externalDocs:
  url: https://pollo.ai/api/platform/api/openapi.json
paths:
  /v1/generation/google/nano-banana-2-1/image:
    post:
      tags:
        - Image
      summary: nano-banana-2-1
      operationId: v1-google/nano-banana-2-1/image
      parameters: []
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
                - input
              properties:
                input:
                  oneOf:
                    - type: object
                      properties:
                        images:
                          type: array
                          minItems: 1
                          items:
                            type: string
                            format: uri
                          maxItems: 14
                          description: >-
                            Reference image URLs (HTTP(S); base64 not allowed).
                            Supported formats: JPG/JPEG, PNG.
                        prompt:
                          type: string
                          maxLength: 20000
                          minLength: 1
                          description: Text prompt describing the content to generate.
                        aspectRatio:
                          type: string
                          enum:
                            - '1:1'
                            - '9:16'
                            - '16:9'
                            - '4:3'
                            - '3:4'
                            - '3:2'
                            - '2:3'
                            - '5:4'
                            - '4:5'
                            - '21:9'
                            - '1:4'
                            - '4:1'
                            - '8:1'
                            - '1:8'
                          default: '1:1'
                          description: Output aspect ratio, as width:height (e.g. 16:9).
                        resolution:
                          type: string
                          enum:
                            - 1K
                            - 2K
                            - 4K
                          default: 1K
                          description: >-
                            Output resolution of the generated media (e.g. 720p,
                            1080p, 2K, 4K). Values are case-insensitive.
                        thinkingLevel:
                          type: string
                          enum:
                            - minimal
                            - medium
                            - high
                          default: minimal
                          description: >-
                            How much the model reasons before generating the
                            image. Higher levels may improve quality but take
                            longer.
                      required:
                        - images
                        - prompt
                      title: Image To Image
                      description: >-
                        Constraints:

                        - image and images combined allow up to 14 unique
                        reference images
                    - type: object
                      properties:
                        prompt:
                          type: string
                          maxLength: 20000
                          minLength: 1
                          description: Text prompt describing the content to generate.
                        aspectRatio:
                          type: string
                          enum:
                            - '1:1'
                            - '9:16'
                            - '16:9'
                            - '4:3'
                            - '3:4'
                            - '3:2'
                            - '2:3'
                            - '5:4'
                            - '4:5'
                            - '21:9'
                            - '1:4'
                            - '4:1'
                            - '8:1'
                            - '1:8'
                          default: '1:1'
                          description: Output aspect ratio, as width:height (e.g. 16:9).
                        resolution:
                          type: string
                          enum:
                            - 1K
                            - 2K
                            - 4K
                          default: 1K
                          description: >-
                            Output resolution of the generated media (e.g. 720p,
                            1080p, 2K, 4K). Values are case-insensitive.
                        thinkingLevel:
                          type: string
                          enum:
                            - minimal
                            - medium
                            - high
                          default: minimal
                          description: >-
                            How much the model reasons before generating the
                            image. Higher levels may improve quality but take
                            longer.
                      required:
                        - prompt
                      title: Text To Image
                webhookUrl:
                  type: string
                  format: uri
                  description: >-
                    Webhook URL (HTTP(S)) that receives status callbacks when
                    the generation succeeds or fails.
      responses:
        '200':
          description: Successful response
          content:
            application/json:
              schema:
                type: object
                properties:
                  taskId:
                    type: string
                  status:
                    type: string
                    enum:
                      - waiting
                      - succeed
                      - failed
                      - processing
                required:
                  - taskId
                  - status
                additionalProperties: false
        '400':
          $ref: '#/components/responses/ApiError400'
        '401':
          $ref: '#/components/responses/ApiError401'
        '403':
          $ref: '#/components/responses/ApiError403'
        '404':
          $ref: '#/components/responses/ApiError404'
        '429':
          $ref: '#/components/responses/ApiError429'
        '500':
          $ref: '#/components/responses/ApiError500'
        default:
          $ref: '#/components/responses/error'
      security:
        - ApiKeyAuth: []
components:
  responses:
    ApiError400:
      description: >-
        Invalid request — schema validation failed (`INPUT_VALIDATION_FAILED`,
        detail in `issues`), a cross-field constraint was violated
        (`INPUT_CONSTRAINT_VIOLATED`), or the input did not pass moderation
        (`MODERATION_*`).
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ApiError'
    ApiError401:
      description: >-
        Missing or invalid credential (`CREDENTIAL_*`, `CLI_TOKEN_EXPIRED`,
        `EMAIL_LOGIN_REQUIRED`).
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ApiError'
    ApiError403:
      description: >-
        Rejected — not enough credits (`CREDITS_INSUFFICIENT`), quota exhausted
        (`QUOTA_*`), plan required (`PLAN_FEATURE_REQUIRED`), account state
        (`ACCOUNT_*`), or no permission (`PERMISSION_DENIED`).
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ApiError'
    ApiError404:
      description: >-
        Nothing matched — unknown route, model (`MODEL_NOT_FOUND`), task
        (`TASK_NOT_FOUND`) or asset (`ASSET_NOT_FOUND`).
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ApiError'
    ApiError429:
      description: >-
        Rate limited (`RATE_LIMIT_*`). `RATE_LIMIT_MODERATION` means recent
        content was blocked — adjust the input rather than simply retrying.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ApiError'
    ApiError500:
      description: Unexpected server-side failure (`INTERNAL`).
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ApiError'
    error:
      description: >-
        Error response. Every failure on this API uses this shape; branch on
        `errorCode`.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ApiError'
  schemas:
    ApiError:
      type: object
      required:
        - errorCode
        - message
        - code
      additionalProperties: true
      properties:
        errorCode:
          type: string
          enum:
            - REJECTED
            - INTERNAL
            - CREDENTIAL_MISSING
            - CREDENTIAL_INVALID
            - CLI_TOKEN_EXPIRED
            - CLI_REFRESH_TOKEN_INVALID
            - PERMISSION_DENIED
            - ACCOUNT_SUSPENDED
            - ACCOUNT_DELETED
            - CREDITS_INSUFFICIENT
            - PLAN_FEATURE_REQUIRED
            - PARALLEL_TASK_LIMIT_REACHED
            - ACTIVITY_DAILY_LIMIT_REACHED
            - QUOTA_ELEMENT_FREE
            - QUOTA_ELEMENT_PAID
            - QUOTA_BRAND_KIT_FREE
            - QUOTA_BRAND_KIT_PAID
            - RATE_LIMIT_EXCEEDED
            - RATE_LIMIT_PRODUCT_EXTRACT
            - INPUT_VALIDATION_FAILED
            - INPUT_NOT_SUPPORTED_BY_MODEL
            - MODERATION_REJECTED
            - ASSET_DISABLED_BY_REVIEW
            - GENERATION_IN_PROGRESS
          description: >-
            Stable business error identifier — **the only field to branch on**.
            Codes are append-only: existing codes are never renamed or
            repurposed, but new ones are added over time, so treat this as an
            open set. Match the exact code you handle, else the family prefix
            (`MODERATION_`, `RATE_LIMIT_`, `QUOTA_`, `ACCOUNT_`, …), else fall
            back to the HTTP status.
        message:
          type: string
          description: >-
            Developer-facing text. Varies with locale and product copy — **never
            match on it**.
        code:
          type: string
          description: >-
            Transport-level code (tRPC / JSON-RPC naming). Deprecated for
            business logic; may be removed.
        requestId:
          type: string
          description: Correlation id — quote it when contacting support.
        issues:
          type: array
          description: >-
            Per-field validation detail. Present when `errorCode` is
            `INPUT_VALIDATION_FAILED`.
          items:
            type: object
            required:
              - message
            additionalProperties: true
            properties:
              message:
                type: string
              path:
                type: array
                items:
                  type: string
                description: Path to the offending field.
  securitySchemes:
    ApiKeyAuth:
      type: apiKey
      in: header
      name: x-api-key
      description: API key to authorize requests

````

This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.