> ## Documentation Index > Fetch the complete documentation index at: https://docs.shuyou.ai/llms.txt > Use this file to discover all available pages before exploring further. # Generate Content > Generate content with Google Vertex AI compatible generateContent API. ## OpenAPI ````yaml en/api-reference/language-series/vertexai/generate-content.json POST /v1beta/models/{model}:generateContent openapi: 3.1.0 info: title: Generate Content version: 1.0.0 servers: - url: https://api.shuyou.ai security: - bearerAuth: [] paths: /v1beta/models/{model}:generateContent: post: tags: - Google Vertex AI Compatible API summary: Generate Content operationId: generateContent parameters: - name: model in: path required: true schema: type: string example: gemini-3.5-flash description: >- Model ID in Google Native API format (e.g. `gemini-3.5-flash`, `gemini-2.5-flash`). requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/GenerateContentRequest' examples: simple_text: summary: Single-turn text value: contents: - role: user parts: - text: Please introduce yourself. multi_turn: summary: Multi-turn conversation value: contents: - role: user parts: - text: What is Python? - role: model parts: - text: >- Python is a high-level programming language known for readability. - role: user parts: - text: What are its main advantages? image_understanding: summary: Image URL input value: contents: - role: user parts: - text: Describe the scene and main elements in this image. - fileData: mimeType: image/jpeg fileUri: https://example.com/image.jpg with_generation_config: summary: With generationConfig value: contents: - role: user parts: - text: Write a short poem about the ocean. generationConfig: temperature: 0.7 maxOutputTokens: 512 topP: 0.9 responses: '200': description: Content generated successfully content: application/json: schema: $ref: '#/components/schemas/GenerateContentResponse' example: candidates: - content: role: model parts: - text: Hello! How can I help you today? finishReason: STOP index: 0 usageMetadata: promptTokenCount: 12 candidatesTokenCount: 18 totalTokenCount: 30 modelVersion: gemini-3.5-flash responseId: resp_example '400': description: Invalid request '401': description: Unauthorized '429': description: Rate limit exceeded components: schemas: GenerateContentRequest: type: object required: - contents properties: contents: type: array description: >- Conversation contents. Supports multi-turn dialogue and multimodal input. items: $ref: '#/components/schemas/Content' minItems: 1 systemInstruction: $ref: '#/components/schemas/Content' description: System instruction (optional). Use text parts only. generationConfig: $ref: '#/components/schemas/GenerationConfig' tools: type: array description: >- Tools the model may call (function calling, search, code execution, etc.). items: type: object toolConfig: type: object description: Tool configuration shared across all tools in the request. safetySettings: type: array items: $ref: '#/components/schemas/SafetySetting' description: Per-request safety settings for candidates. cachedContent: type: string description: Cached content resource name, e.g. `cachedContents/{id}`. GenerateContentResponse: type: object properties: candidates: type: array items: $ref: '#/components/schemas/Candidate' promptFeedback: type: object usageMetadata: $ref: '#/components/schemas/UsageMetadata' modelVersion: type: string responseId: type: string Content: type: object required: - parts properties: role: type: string enum: - user - model default: user description: '`user` for human input; `model` for prior model turns.' parts: type: array items: $ref: '#/components/schemas/Part' minItems: 1 GenerationConfig: type: object description: >- Generation parameters (sampling, length, structured output, modalities, thinking, etc.). properties: temperature: type: number minimum: 0 maximum: 2 topP: type: number minimum: 0 maximum: 1 topK: type: integer minimum: 1 candidateCount: type: integer minimum: 1 maxOutputTokens: type: integer minimum: 1 stopSequences: type: array items: type: string maxItems: 5 presencePenalty: type: number frequencyPenalty: type: number seed: type: integer responseMimeType: type: string description: e.g. text/plain, application/json example: application/json responseSchema: type: object description: >- Schema for structured output (set responseMimeType to application/json). responseJsonSchema: type: object description: JSON Schema alternative to responseSchema. responseLogprobs: type: boolean logprobs: type: integer minimum: 1 maximum: 20 responseModalities: type: array items: type: string enum: - TEXT - IMAGE - AUDIO description: Output modalities. IMAGE requires TEXT as well for image models. audioTimestamp: type: boolean thinkingConfig: type: object properties: thinkingBudget: type: integer description: Thinking token budget (Gemini 2.5). Use -1 for dynamic. thinkingLevel: type: string enum: - THINKING_LEVEL_UNSPECIFIED - MINIMAL - LOW - MEDIUM - HIGH description: >- Reasoning intensity (Gemini 3). Mutually exclusive with thinkingBudget. includeThoughts: type: boolean description: Return thought summary when available. mediaResolution: type: string enum: - MEDIA_RESOLUTION_UNSPECIFIED - MEDIA_RESOLUTION_LOW - MEDIA_RESOLUTION_MEDIUM - MEDIA_RESOLUTION_HIGH - MEDIA_RESOLUTION_ULTRA_HIGH speechConfig: type: object imageConfig: type: object properties: aspectRatio: type: string enum: - '1:1' - '2:3' - '3:2' - '3:4' - '4:3' - '9:16' - '16:9' - '21:9' imageSize: type: string enum: - 1K - 2K - 4K enableAffectiveDialog: type: boolean SafetySetting: type: object required: - category - threshold properties: category: type: string enum: - HARM_CATEGORY_HATE_SPEECH - HARM_CATEGORY_HARASSMENT - HARM_CATEGORY_SEXUALLY_EXPLICIT - HARM_CATEGORY_DANGEROUS_CONTENT threshold: type: string enum: - 'OFF' - BLOCK_NONE - BLOCK_ONLY_HIGH - BLOCK_MEDIUM_AND_ABOVE - BLOCK_LOW_AND_ABOVE method: type: string enum: - SEVERITY - PROBABILITY Candidate: type: object properties: content: $ref: '#/components/schemas/Content' finishReason: type: string enum: - STOP - MAX_TOKENS - SAFETY - RECITATION - OTHER - MALFORMED_FUNCTION_CALL index: type: integer safetyRatings: type: array items: type: object UsageMetadata: type: object properties: promptTokenCount: type: integer candidatesTokenCount: type: integer totalTokenCount: type: integer thoughtsTokenCount: type: integer cachedContentTokenCount: type: integer trafficType: type: string example: ON_DEMAND Part: description: >- Content part. Echo `thoughtSignature` from thinking models in the next turn when present. oneOf: - $ref: '#/components/schemas/TextPart' - $ref: '#/components/schemas/InlineDataPart' - $ref: '#/components/schemas/FileDataPart' - $ref: '#/components/schemas/FunctionCallPart' - $ref: '#/components/schemas/FunctionResponsePart' TextPart: type: object required: - text properties: text: type: string thought: type: boolean description: Whether this part is thought content. thoughtSignature: type: string description: >- Must be echoed back on the next request when returned by thinking models. InlineDataPart: type: object required: - inlineData properties: inlineData: type: object required: - mimeType - data properties: mimeType: type: string description: >- e.g. image/jpeg, image/png, application/pdf, audio/mp3, video/mp4 data: type: string description: Base64-encoded raw bytes. FileDataPart: type: object properties: fileData: type: object required: - mimeType - fileUri properties: mimeType: type: string example: image/jpeg fileUri: type: string format: uri description: Publicly accessible file URL. FunctionCallPart: type: object properties: functionCall: type: object properties: name: type: string args: type: object FunctionResponsePart: type: object properties: functionResponse: type: object properties: name: type: string response: type: object securitySchemes: bearerAuth: type: http scheme: bearer description: '`Authorization: Bearer YOUR_API_KEY`' ````