> ## Documentation Index > Fetch the complete documentation index at: https://docs.aihubmax.com/llms.txt > Use this file to discover all available pages before exploring further. # Gemini Format - Generate Content > - Universal generateContent API reference for all Gemini-native-format compatible models - Minimized parameters for quick start - Text conversation: single-turn or multi-turn contextual dialogue - Multimodal input: supports mixed text + image/audio/video input - Generation config: control temperature, topP, topK, maxOutputTokens via generationConfig ## OpenAPI ````yaml openapi/en/gemini-format-generate-content.json POST /v1beta/models/{model}:generateContent openapi: 3.1.0 info: title: Gemini Format - Generate Content version: '1.0' servers: - url: https://api.aihubmax.com security: - BearerAuth: [] paths: /v1beta/models/{model}:generateContent: post: tags: - Text Series > Gemini Format summary: Gemini Format - Generate Content description: > - Universal generateContent API reference for all Gemini-native-format compatible models - Minimized parameters for quick start - Text conversation: single-turn or multi-turn contextual dialogue - Multimodal input: supports mixed text + image/audio/video input - Generation config: control temperature, topP, topK, maxOutputTokens via generationConfig operationId: gemini-format-generate-content parameters: - name: model in: path required: true schema: type: string example: gemini-2.5-flash description: Model name, e.g. gemini-2.5-flash requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/GenerateContentRequest' examples: single-turn: summary: Single-turn conversation description: Basic single-turn Q&A value: contents: - role: user parts: - text: >- Explain the core principles of the Transformer architecture multi-turn: summary: Multi-turn conversation description: With system instruction and multi-turn context value: contents: - role: user parts: - text: I want to learn Kubernetes. Where should I start? - role: model parts: - text: >- Recommended learning path for Kubernetes: 1. First master Docker container basics 2. Learn K8s core concepts (Pod, Service, Deployment) 3. Set up a local cluster (minikube/kind) Do you have any Docker experience? - role: user parts: - text: >- I have basic Docker experience, used docker-compose before systemInstruction: parts: - text: >- You are a DevOps technical mentor, skilled at creating step-by-step learning plans with-image: summary: With image description: Send an image for model analysis (multimodal input) value: contents: - role: user parts: - text: Describe the content of this image - inlineData: mimeType: image/jpeg data: BASE64_ENCODED_IMAGE_DATA with-generation-config: summary: Custom generation config description: Control generation parameters via generationConfig value: contents: - role: user parts: - text: >- Output the names and characteristics of three programming languages in JSON format generationConfig: temperature: 0.2 maxOutputTokens: 1024 responseMimeType: application/json with-youtube-video: summary: With YouTube video description: >- Use a YouTube link as video input (video must be public). `mimeType` can be omitted. value: contents: - role: user parts: - text: Summarize the main content of this video - fileData: fileUri: https://www.youtube.com/watch?v=9hE5-98ZeCg with-image-url: summary: With image URL description: >- Reference an image via public HTTPS URL (avoids base64 encoding overhead) value: contents: - role: user parts: - text: Describe this image - fileData: fileUri: https://example.com/photo.jpg mimeType: image/jpeg with-pdf-url: summary: With PDF URL description: Reference a PDF file via public HTTPS URL value: contents: - role: user parts: - text: Summarize this document - fileData: fileUri: https://example.com/report.pdf mimeType: application/pdf responses: '200': $ref: '#/components/responses/GenerateContentSuccess' '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '402': $ref: '#/components/responses/PaymentRequired' '403': $ref: '#/components/responses/Forbidden' '429': $ref: '#/components/responses/TooManyRequests' '500': $ref: '#/components/responses/InternalServerError' components: schemas: GenerateContentRequest: type: object required: - contents properties: contents: type: array description: List of conversation contents items: type: object required: - role - parts properties: role: type: string description: Role of the message sender enum: - user - model parts: type: array description: List of content parts items: type: object properties: text: type: string description: Text content inlineData: type: object description: >- Inline binary data (base64 encoded). Applicable for: images, audio, PDF, video (base64). Video file size <= 100MB. required: - mimeType - data properties: mimeType: type: string description: >- IANA standard MIME type (Gemini natively supported list): - **Images**: image/png, image/jpeg, image/webp, image/heic, image/heif - **Audio**: audio/wav, audio/mp3, audio/aiff, audio/aac, audio/ogg, audio/flac - **Video**: video/mp4, video/mpeg, video/quicktime, video/avi, video/x-flv, video/mpg, video/webm, video/wmv, video/3gpp - **Documents**: application/pdf (supports visual understanding: charts/layouts/images), text/plain, text/markdown, text/html, text/xml (extracted as plain text only) > Available MIME types depend on the selected model/channel capabilities; some channels do not support video base64. examples: - image/png - image/jpeg - image/webp - image/heic - image/heif - audio/wav - audio/mp3 - audio/aiff - audio/aac - audio/ogg - audio/flac - video/mp4 - video/mpeg - video/quicktime - video/avi - video/x-flv - video/mpg - video/webm - video/wmv - video/3gpp - application/pdf - text/plain - text/markdown - text/html - text/xml data: type: string description: Base64-encoded binary data fileData: type: object description: >- URL reference. Applicable for: YouTube videos, public HTTPS URLs (images / PDF / video). `mimeType` can be omitted for YouTube. required: - fileUri properties: fileUri: type: string description: 'Resource URI: YouTube URL or public HTTPS URL' examples: - https://www.youtube.com/watch?v=9hE5-98ZeCg - https://example.com/photo.jpg - https://example.com/report.pdf mimeType: type: string description: >- IANA standard MIME type (same list as inlineData): - **Images**: image/png, image/jpeg, image/webp, image/heic, image/heif - **Audio**: audio/wav, audio/mp3, audio/aiff, audio/aac, audio/ogg, audio/flac - **Video**: video/mp4, video/mpeg, video/quicktime, video/avi, video/x-flv, video/mpg, video/webm, video/wmv, video/3gpp - **Documents**: application/pdf (supports visual understanding: charts/layouts/images), text/plain, text/markdown, text/html, text/xml (extracted as plain text only) > `mimeType` can be omitted for YouTube links; explicitly declaring it is recommended for other public HTTPS URLs. examples: - image/png - image/jpeg - image/webp - image/heic - image/heif - audio/wav - audio/mp3 - audio/aiff - audio/aac - audio/ogg - audio/flac - video/mp4 - video/mpeg - video/quicktime - video/avi - video/x-flv - video/mpg - video/webm - video/wmv - video/3gpp - application/pdf - text/plain - text/markdown - text/html - text/xml description: >- Content part, choose one of: text / inlineData / fileData. **Multimodal input support**: - Text: `text` - Image / Audio / PDF (base64 inline): `inlineData{mimeType, data}` - Image / PDF (public HTTPS URL): `fileData{fileUri, mimeType}` - Video: see "Video input" below **Video input (depending on model/channel capabilities) supports 3 forms**: 1. **YouTube link**: `fileData{fileUri:"https://www.youtube.com/watch?v=..."}`, `mimeType` can be omitted; video must be **public** (private / unlisted not supported) 2. **Public HTTPS URL**: `fileData{fileUri:"https://...", mimeType:"video/mp4"}`; video file size <= **100MB** (calculated by post-download base64 encoded size) 3. **Inline base64**: `inlineData{mimeType:"video/mp4", data:""}`, size <= **100MB** > Different models / channels support different video forms; some channels currently only support YouTube links. For videos exceeding 100MB, please contact the administrator for a dedicated upload endpoint. systemInstruction: type: object description: System instruction properties: parts: type: array description: System instruction content parts items: type: object properties: text: type: string description: System instruction text generationConfig: type: object description: Generation configuration properties: temperature: type: number description: Sampling temperature minimum: 0 maximum: 2 topP: type: number description: Nucleus sampling parameter minimum: 0 maximum: 1 topK: type: integer description: Top-K sampling parameter maxOutputTokens: type: integer description: Maximum number of output tokens responseMimeType: type: string description: Response MIME type, e.g. text/plain or application/json responseSchema: type: object description: >- Response JSON Schema (used when responseMimeType is application/json) tools: type: array description: List of available tools items: type: object properties: functionDeclarations: type: array description: List of function declarations items: type: object properties: name: type: string description: Function name description: type: string description: Function description parameters: type: object description: JSON Schema for function parameters safetySettings: type: array description: Safety settings items: type: object properties: category: type: string description: Safety category enum: - HARM_CATEGORY_HARASSMENT - HARM_CATEGORY_HATE_SPEECH - HARM_CATEGORY_SEXUALLY_EXPLICIT - HARM_CATEGORY_DANGEROUS_CONTENT threshold: type: string description: Safety threshold enum: - BLOCK_NONE - BLOCK_LOW_AND_ABOVE - BLOCK_MEDIUM_AND_ABOVE - BLOCK_ONLY_HIGH GenerateContentResponse: type: object properties: candidates: type: array description: List of candidate results items: type: object properties: content: type: object description: Generated content properties: parts: type: array items: type: object properties: text: type: string description: Generated text content example: Hello! How can I help you today? role: type: string description: Role enum: - model finishReason: type: string description: Reason for stopping generation enum: - STOP - MAX_TOKENS - SAFETY - RECITATION - OTHER example: STOP safetyRatings: type: array description: List of safety ratings items: type: object properties: category: type: string description: Safety category probability: type: string description: Probability level usageMetadata: type: object description: Usage statistics properties: promptTokenCount: type: integer description: Prompt token count example: 25 candidatesTokenCount: type: integer description: Candidates token count example: 150 totalTokenCount: type: integer description: Total token count example: 175 ErrorResponse400: type: object properties: error: type: object properties: message: type: string example: Invalid request parameters type: type: string example: invalid_request_error ErrorResponse401: type: object properties: error: type: object properties: message: type: string example: Invalid API Key type: type: string example: authentication_error ErrorResponse403: type: object properties: error: type: object properties: message: type: string example: Access denied type: type: string example: permission_error ErrorResponse429: type: object properties: error: type: object properties: message: type: string example: Rate limit exceeded type: type: string example: rate_limit_error ErrorResponse500: type: object properties: error: type: object properties: message: type: string example: Internal server error type: type: string example: server_error responses: GenerateContentSuccess: description: Content generation response content: application/json: schema: $ref: '#/components/schemas/GenerateContentResponse' BadRequest: description: Bad request content: application/json: schema: $ref: '#/components/schemas/ErrorResponse400' Unauthorized: description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/ErrorResponse401' PaymentRequired: description: Insufficient balance content: application/json: schema: $ref: '#/components/schemas/ErrorResponse400' Forbidden: description: Forbidden content: application/json: schema: $ref: '#/components/schemas/ErrorResponse403' TooManyRequests: description: Too many requests content: application/json: schema: $ref: '#/components/schemas/ErrorResponse429' InternalServerError: description: Internal server error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse500' securitySchemes: BearerAuth: type: http scheme: bearer description: | ## All endpoints require Bearer Token authentication ## Add the following to your request header: `Authorization: Bearer YOUR_API_KEY` ````