> ## Documentation Index > Fetch the complete documentation index at: https://docs.acedata.cloud/llms.txt > Use this file to discover all available pages before exploring further. # Gemini Generate Content ## OpenAPI ````yaml /openapi/gemini.json post /v1beta/models/{model}:generateContent openapi: 3.0.0 info: title: Gemini AI version: 1.0.0 description: API reference for Gemini AI on Ace Data Cloud. servers: - url: https://api.acedata.cloud description: Ace Data Cloud API security: - bearerAuth: [] paths: /v1beta/models/{model}:generateContent: post: summary: Gemini Generate Content operationId: GeminiGenerateContentAPIcreateV1betaModelsByModelgenerateContent parameters: - name: model in: path required: true schema: type: string enum: - gemini-3.8-flash - gemini-3.7-flash - gemini-3.6-flash - gemini-3.5-flash - gemini-3.5-flash-lite - gemini-3.1-flash-lite - gemini-3.1-pro-preview - gemini-3-flash-preview - gemini-2.5-pro - gemini-2.5-flash - gemini-2.5-flash-lite - gemini-3.1-flash-image - gemini-2.5-flash-image - gemini-3-pro-image example: gemini-2.5-flash description: V1Beta Models Model Generatecontent Param Model requestBody: required: true content: application/json: schema: type: object required: - contents properties: contents: type: array description: V1Beta Models Model Generatecontent Contents items: type: object required: - parts properties: role: type: string enum: - user - model description: V1Beta Models Model Generatecontent Contents Role parts: type: array description: V1Beta Models Model Generatecontent Contents Parts items: type: object properties: text: type: string description: >- V1Beta Models Model Generatecontent Contents Parts Text inlineData: type: object description: >- V1Beta Models Model Generatecontent Contents Parts Inlinedata properties: mimeType: type: string description: >- V1Beta Models Model Generatecontent Contents Parts Inlinedata Mimetype data: type: string description: >- V1Beta Models Model Generatecontent Contents Parts Inlinedata Data fileData: type: object description: >- V1Beta Models Model Generatecontent Contents Parts Filedata properties: mimeType: type: string fileUri: type: string functionCall: type: object description: >- V1Beta Models Model Generatecontent Contents Parts Functioncall properties: name: type: string args: type: object additionalProperties: true functionResponse: type: object description: >- V1Beta Models Model Generatecontent Contents Parts Functionresponse properties: name: type: string response: type: object additionalProperties: true systemInstruction: type: object description: V1Beta Models Model Generatecontent Systeminstruction properties: parts: type: array items: type: object properties: text: type: string generationConfig: type: object description: V1Beta Models Model Generatecontent Generationconfig properties: stopSequences: type: array items: type: string description: >- V1Beta Models Model Generatecontent Generationconfig Stopsequences responseMimeType: type: string description: >- V1Beta Models Model Generatecontent Generationconfig Responsemimetype enum: - text/plain - application/json - text/x.enum responseSchema: type: object description: >- V1Beta Models Model Generatecontent Generationconfig Responseschema additionalProperties: true responseModalities: type: array items: type: string enum: - TEXT - IMAGE description: >- V1Beta Models Model Generatecontent Generationconfig Responsemodalities candidateCount: type: integer description: >- V1Beta Models Model Generatecontent Generationconfig Candidatecount maxOutputTokens: type: integer description: >- V1Beta Models Model Generatecontent Generationconfig Maxoutputtokens temperature: type: number description: >- V1Beta Models Model Generatecontent Generationconfig Temperature minimum: 0 maximum: 2 topP: type: number description: >- V1Beta Models Model Generatecontent Generationconfig Topp topK: type: integer description: >- V1Beta Models Model Generatecontent Generationconfig Topk seed: type: integer description: >- V1Beta Models Model Generatecontent Generationconfig Seed presencePenalty: type: number description: >- V1Beta Models Model Generatecontent Generationconfig Presencepenalty frequencyPenalty: type: number description: >- V1Beta Models Model Generatecontent Generationconfig Frequencypenalty thinkingConfig: type: object description: >- V1Beta Models Model Generatecontent Generationconfig Thinkingconfig properties: includeThoughts: type: boolean description: >- V1Beta Models Model Generatecontent Generationconfig Thinkingconfig Includethoughts thinkingBudget: type: integer description: >- V1Beta Models Model Generatecontent Generationconfig Thinkingconfig Thinkingbudget imageConfig: type: object description: >- V1Beta Models Model Generatecontent Generationconfig Imageconfig properties: aspectRatio: type: string description: >- V1Beta Models Model Generatecontent Generationconfig Imageconfig Aspectratio imageSize: type: string enum: - '512' - 1K - 2K - 4K description: >- V1Beta Models Model Generatecontent Generationconfig Imageconfig Imagesize tools: type: array description: V1Beta Models Model Generatecontent Tools items: type: object properties: functionDeclarations: type: array items: type: object properties: name: type: string description: type: string parameters: type: object additionalProperties: true required: - name toolConfig: type: object description: V1Beta Models Model Generatecontent Toolconfig properties: functionCallingConfig: type: object properties: mode: type: string enum: - MODE_UNSPECIFIED - AUTO - ANY - NONE allowedFunctionNames: type: array items: type: string safetySettings: type: array description: V1Beta Models Model Generatecontent Safetysettings items: type: object properties: category: type: string enum: - HARM_CATEGORY_HARASSMENT - HARM_CATEGORY_HATE_SPEECH - HARM_CATEGORY_SEXUALLY_EXPLICIT - HARM_CATEGORY_DANGEROUS_CONTENT - HARM_CATEGORY_CIVIC_INTEGRITY threshold: type: string enum: - BLOCK_NONE - BLOCK_ONLY_HIGH - BLOCK_MEDIUM_AND_ABOVE - BLOCK_LOW_AND_ABOVE - 'OFF' example: contents: - role: user parts: - text: 'Reply with exactly: Hello!' generationConfig: maxOutputTokens: 128 responses: '200': description: V1Beta Models Model Generatecontent Response 200 content: application/json: schema: type: object properties: candidates: type: array items: type: object properties: content: type: object properties: parts: type: array items: type: object properties: text: type: string thought: type: boolean description: >- V1Beta Models Model Generatecontent Response 200 Candidates Parts Thought role: type: string finishReason: type: string enum: - STOP - MAX_TOKENS - SAFETY - RECITATION - LANGUAGE - OTHER - BLOCKLIST - PROHIBITED_CONTENT - SPII - MALFORMED_FUNCTION_CALL index: type: integer safetyRatings: type: array items: type: object properties: category: type: string probability: type: string blocked: type: boolean usageMetadata: type: object properties: promptTokenCount: type: integer cachedContentTokenCount: type: integer candidatesTokenCount: type: integer totalTokenCount: type: integer thoughtsTokenCount: type: integer toolUsePromptTokenCount: type: integer promptTokensDetails: type: array items: type: object properties: modality: type: string tokenCount: type: integer candidatesTokensDetails: type: array items: type: object properties: modality: type: string tokenCount: type: integer cacheTokensDetails: type: array items: type: object properties: modality: type: string tokenCount: type: integer toolUsePromptTokensDetails: type: array items: type: object properties: modality: type: string tokenCount: type: integer usage: type: object description: V1Beta Models Model Generatecontent Response 200 Usage required: - prompt_tokens - completion_tokens properties: prompt_tokens: type: integer description: >- V1Beta Models Model Generatecontent Response 200 Usage Prompt Tokens completion_tokens: type: integer description: >- V1Beta Models Model Generatecontent Response 200 Usage Completion Tokens total_tokens: type: integer description: >- V1Beta Models Model Generatecontent Response 200 Usage Total Tokens prompt_tokens_details: type: object description: >- V1Beta Models Model Generatecontent Response 200 Usage Prompt Tokens Details properties: cached_tokens: type: integer text_tokens: type: integer description: >- V1Beta Models Model Generatecontent Response 200 Usage Text Tokens image_tokens: type: integer description: >- V1Beta Models Model Generatecontent Response 200 Usage Image Tokens video_tokens: type: integer description: >- V1Beta Models Model Generatecontent Response 200 Usage Video Tokens audio_tokens: type: integer description: >- V1Beta Models Model Generatecontent Response 200 Usage Audio Tokens cached_text_tokens: type: integer description: >- V1Beta Models Model Generatecontent Response 200 Usage Cached Text Tokens cached_image_tokens: type: integer description: >- V1Beta Models Model Generatecontent Response 200 Usage Cached Image Tokens cached_video_tokens: type: integer description: >- V1Beta Models Model Generatecontent Response 200 Usage Cached Video Tokens cached_audio_tokens: type: integer description: >- V1Beta Models Model Generatecontent Response 200 Usage Cached Audio Tokens modalities: type: array description: >- V1Beta Models Model Generatecontent Response 200 Usage Prompt Modalities items: type: object required: - modality - tokenCount properties: modality: type: string tokenCount: type: integer additionalProperties: false cached_modalities: type: array description: >- V1Beta Models Model Generatecontent Response 200 Usage Cached Modalities items: type: object required: - modality - tokenCount properties: modality: type: string tokenCount: type: integer additionalProperties: false additionalProperties: false completion_tokens_details: type: object description: >- V1Beta Models Model Generatecontent Response 200 Usage Completion Tokens Details properties: modalities: type: array description: >- V1Beta Models Model Generatecontent Response 200 Usage Completion Modalities items: type: object required: - modality - tokenCount properties: modality: type: string tokenCount: type: integer additionalProperties: false additionalProperties: false thoughts_tokens: type: integer description: >- V1Beta Models Model Generatecontent Response 200 Usage Thoughts Tokens tool_use_prompt_tokens: type: integer description: >- V1Beta Models Model Generatecontent Response 200 Usage Tool Use Prompt Tokens tool_use_prompt_tokens_details: type: object description: >- V1Beta Models Model Generatecontent Response 200 Usage Tool Use Prompt Tokens Details properties: modalities: type: array description: >- V1Beta Models Model Generatecontent Response 200 Usage Tool Use Prompt Modalities items: type: object required: - modality - tokenCount properties: modality: type: string tokenCount: type: integer additionalProperties: false additionalProperties: false cost: type: object description: >- V1Beta Models Model Generatecontent Response 200 Usage Cost required: - amount - currency properties: amount: type: number description: >- V1Beta Models Model Generatecontent Response 200 Usage Cost Amount currency: type: string description: >- V1Beta Models Model Generatecontent Response 200 Usage Cost Currency list_amount: type: number description: >- V1Beta Models Model Generatecontent Response 200 Usage Cost List Amount additionalProperties: false additionalProperties: false modelVersion: type: string responseId: type: string example: candidates: - content: role: model parts: - text: Hello! finishReason: STOP usageMetadata: candidatesTokenCount: 2 candidatesTokensDetails: - modality: TEXT tokenCount: 2 promptTokenCount: 260 promptTokensDetails: - modality: TEXT tokenCount: 260 thoughtsTokenCount: 22 totalTokenCount: 284 usage: prompt_tokens: 260 completion_tokens: 2 total_tokens: 284 completion_tokens_details: modalities: - modality: TEXT tokenCount: 2 prompt_tokens_details: modalities: - modality: TEXT tokenCount: 260 thoughts_tokens: 22 cost: amount: 0.0001953617424 currency: credit list_amount: 0.00021234972 modelVersion: gemini-3.1-flash-lite model: gemini-3.1-flash-lite '400': description: V1Beta Models Model Generatecontent Response 400 content: application/json: schema: type: object properties: error: type: object properties: code: type: integer message: type: string status: type: string security: - bearerAuth: [] components: securitySchemes: bearerAuth: type: http scheme: bearer description: API token from https://platform.acedata.cloud ````