> ## Documentation Index > Fetch the complete documentation index at: https://docs.anyfast.ai/llms.txt > Use this file to discover all available pages before exploring further. # gemini-nano-banana-2.1 > Generates image and optional text content from text, image, video, or PDF input. ## OpenAPI ````yaml api-reference/model-api/google/openapi/gemini-nano-banana-2-1/openapi.yaml POST /v1beta/models/gemini-nano-banana-2.1:generateContent openapi: 3.1.0 info: title: Gemini Nano Banana 2.1 description: >- Generate and edit images with Gemini Nano Banana 2.1 through the AnyFast native Gemini API. version: 1.0.0 servers: - url: https://www.anyfast.ai security: [] paths: /v1beta/models/gemini-nano-banana-2.1:generateContent: post: summary: Generate or edit an image description: >- Generates image and optional text content from text, image, video, or PDF input. operationId: GeminiNanoBanana21GenerateContent parameters: - name: key in: query required: true description: AnyFast API key. schema: type: string example: YOUR_API_KEY requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/GenerateContentRequest' examples: textToImage: summary: Text to image value: contents: - role: user parts: - text: >- Create a clean 16:9 product poster for a translucent blue mechanical keyboard. generationConfig: responseModalities: - TEXT - IMAGE responseFormat: image: aspectRatio: '16:9' imageSize: 2K imageEditing: summary: Edit an image value: contents: - role: user parts: - text: >- Keep the product unchanged and replace the background with a warm wooden desk. - inline_data: mime_type: image/png data: YOUR_BASE64_IMAGE_DATA generationConfig: responseModalities: - IMAGE responseFormat: image: aspectRatio: '4:3' imageSize: 2K responses: '200': description: Content generated successfully. content: application/json: schema: $ref: '#/components/schemas/GenerateContentResponse' example: candidates: - content: role: model parts: - text: Here is the generated product poster. - inlineData: mimeType: image/png data: iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJ finishReason: STOP usageMetadata: promptTokenCount: 24 candidatesTokenCount: 1680 totalTokenCount: 1704 modelVersion: gemini-nano-banana-2.1 responseId: response_example '400': description: Invalid request. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '401': description: Invalid or missing API key. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '429': description: Rate limit exceeded. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' x-codeSamples: - lang: bash label: cURL source: > curl "https://www.anyfast.ai/v1beta/models/gemini-nano-banana-2.1:generateContent?key=YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "contents": [{ "role": "user", "parts": [{ "text": "Create a clean 16:9 product poster for a translucent blue mechanical keyboard." }] }], "generationConfig": { "responseModalities": ["TEXT", "IMAGE"], "thinkingConfig": {"thinkingLevel": "medium"}, "responseFormat": { "image": {"aspectRatio": "16:9", "imageSize": "2K"} } } }' components: schemas: GenerateContentRequest: type: object required: - contents properties: contents: type: array minItems: 1 description: Conversation turns containing prompts and reference media. items: $ref: '#/components/schemas/Content' generationConfig: $ref: '#/components/schemas/GenerationConfig' GenerateContentResponse: type: object properties: candidates: type: array items: $ref: '#/components/schemas/Candidate' promptFeedback: type: object additionalProperties: true usageMetadata: $ref: '#/components/schemas/UsageMetadata' modelVersion: type: string example: gemini-nano-banana-2.1 responseId: type: string ErrorResponse: type: object properties: error: type: object properties: code: type: integer message: type: string status: type: string Content: type: object required: - parts properties: role: type: string enum: - user - model default: user parts: type: array minItems: 1 items: $ref: '#/components/schemas/Part' GenerationConfig: type: object properties: responseModalities: type: array description: >- Return image only, or both text and image. The model defaults to text and image. minItems: 1 uniqueItems: true items: type: string enum: - TEXT - IMAGE example: - TEXT - IMAGE responseFormat: type: object properties: image: $ref: '#/components/schemas/ImageResponseFormat' thinkingConfig: $ref: '#/components/schemas/ThinkingConfig' Candidate: type: object properties: content: type: object properties: role: type: string example: model parts: type: array items: $ref: '#/components/schemas/ResponsePart' finishReason: type: string enum: - STOP - MAX_TOKENS - SAFETY - RECITATION - OTHER index: type: integer safetyRatings: type: array items: type: object additionalProperties: true UsageMetadata: type: object properties: promptTokenCount: type: integer candidatesTokenCount: type: integer totalTokenCount: type: integer thoughtsTokenCount: type: integer Part: type: object description: >- A text or media content part. Supply the field that matches the part type. properties: text: type: string description: Text prompt or editing instruction. inline_data: $ref: '#/components/schemas/InlineDataInput' file_data: $ref: '#/components/schemas/FileDataInput' video_metadata: $ref: '#/components/schemas/VideoMetadata' ImageResponseFormat: type: object properties: aspectRatio: type: string description: Output image aspect ratio. enum: - '1:1' - '1:4' - '1:8' - '2:3' - '3:2' - '3:4' - '4:1' - '4:3' - '4:5' - '5:4' - '8:1' - '9:16' - '16:9' - '21:9' example: '16:9' imageSize: type: string description: Output resolution. The default is 1K. enum: - 1K - 2K - 4K default: 1K ThinkingConfig: type: object properties: thinkingLevel: type: string description: Thinking effort. The default is medium. enum: - minimal - medium - high default: medium includeThoughts: type: boolean default: false description: Whether thought parts may be included in the response. ResponsePart: type: object properties: text: type: string inlineData: type: object required: - mimeType - data properties: mimeType: type: string example: image/png data: type: string format: byte description: Base64-encoded generated image. thought: type: boolean description: >- True when the part contains model thinking rather than the final answer. thoughtSignature: type: string description: >- Opaque signature that must be preserved when continuing a conversation. InlineDataInput: type: object required: - mime_type - data description: Base64-encoded inline image, video, or PDF data. properties: mime_type: type: string description: MIME type of the encoded content. example: image/png data: type: string format: byte description: Base64-encoded bytes without a data URL prefix. FileDataInput: type: object required: - mime_type - file_uri description: A file previously uploaded through the Gemini Files API. properties: mime_type: type: string example: application/pdf file_uri: type: string description: >- URI returned by the file upload operation or a supported public video URI. VideoMetadata: type: object description: Optional controls for video input sampling. properties: fps: type: number exclusiveMinimum: 0 example: 0.5 ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.