naftiko: 1.0.0-alpha2 info: label: Google Gemini API description: Google's Gemini API provides access to generative AI models for text generation, multimodal understanding, and embedding creation. The API supports text, image, audio, and video inputs with configurable safety settings, generation parameters, and tool use capabilities. tags: - Google - Gemini - API created: '2026-05-06' modified: '2026-05-06' capability: consumes: - type: http namespace: google-gemini baseUri: https://generativelanguage.googleapis.com/v1beta description: Google Gemini API HTTP API. authentication: type: apikey in: query name: key value: '{{GOOGLE_GEMINI_TOKEN}}' resources: - name: models-model-generatecontent path: /models/{model}:generateContent operations: - name: generatecontent method: POST description: Google Gemini Generates a model response given an input GenerateContentRequest. Refer to the text generation guide for detailed usage information. Input capabilities differ between models, including tuned models. inputParameters: - name: model in: path type: string required: true description: 'The name of the Model to use for generating the completion. Format: models/{model}. Example: models/gemini-2.0-flash.' - name: key in: query type: string required: true description: API key for authentication. outputRawFormat: json outputParameters: - name: result type: object value: $. - name: models-model-streamgeneratecontent path: /models/{model}:streamGenerateContent operations: - name: streamgeneratecontent method: POST description: Google Gemini Generates a streamed response from the model given an input GenerateContentRequest. Returns a stream of GenerateContentResponse chunks using server-sent events. inputParameters: - name: model in: path type: string required: true description: 'The name of the Model to use for generating the completion. Format: models/{model}. Example: models/gemini-2.0-flash.' - name: key in: query type: string required: true description: API key for authentication. - name: alt in: query type: string description: Set to 'sse' for server-sent events streaming. outputRawFormat: json outputParameters: - name: result type: object value: $. - name: models-model-embedcontent path: /models/{model}:embedContent operations: - name: embedcontent method: POST description: Google Gemini Generates a text embedding vector from the input Content using the specified Gemini Embedding model. inputParameters: - name: model in: path type: string required: true description: 'The model name to use for embedding. Format: models/{model}. Example: models/gemini-embedding-001.' - name: key in: query type: string required: true description: API key for authentication. outputRawFormat: json outputParameters: - name: result type: object value: $. exposes: - type: rest port: 8080 namespace: google-gemini-rest description: REST adapter for Google Gemini API. resources: - path: /models/{model}:generateContent name: generatecontent operations: - method: POST name: generatecontent description: Google Gemini Generates a model response given an input GenerateContentRequest. Refer to the text generation guide for detailed usage information. Input capabilities differ between models, including tuned models. call: google-gemini.generatecontent with: model: rest.model outputParameters: - type: object mapping: $. - path: /models/{model}:streamGenerateContent name: streamgeneratecontent operations: - method: POST name: streamgeneratecontent description: Google Gemini Generates a streamed response from the model given an input GenerateContentRequest. Returns a stream of GenerateContentResponse chunks using server-sent events. call: google-gemini.streamgeneratecontent with: model: rest.model outputParameters: - type: object mapping: $. - path: /models/{model}:embedContent name: embedcontent operations: - method: POST name: embedcontent description: Google Gemini Generates a text embedding vector from the input Content using the specified Gemini Embedding model. call: google-gemini.embedcontent with: model: rest.model outputParameters: - type: object mapping: $. - type: mcp port: 9090 namespace: google-gemini-mcp transport: http description: MCP adapter for Google Gemini API for AI agent use. tools: - name: generatecontent description: Google Gemini Generates a model response given an input GenerateContentRequest. Refer to the text generation guide for detailed usage information. Input capabilities differ between models, including tuned models. hints: readOnly: false destructive: false idempotent: false call: google-gemini.generatecontent with: model: tools.model key: tools.key inputParameters: - name: model type: string description: 'The name of the Model to use for generating the completion. Format: models/{model}. Example: models/gemini-2.0-flash.' required: true - name: key type: string description: API key for authentication. required: true outputParameters: - type: object mapping: $. - name: streamgeneratecontent description: Google Gemini Generates a streamed response from the model given an input GenerateContentRequest. Returns a stream of GenerateContentResponse chunks using server-sent events. hints: readOnly: false destructive: false idempotent: false call: google-gemini.streamgeneratecontent with: model: tools.model key: tools.key alt: tools.alt inputParameters: - name: model type: string description: 'The name of the Model to use for generating the completion. Format: models/{model}. Example: models/gemini-2.0-flash.' required: true - name: key type: string description: API key for authentication. required: true - name: alt type: string description: Set to 'sse' for server-sent events streaming. outputParameters: - type: object mapping: $. - name: embedcontent description: Google Gemini Generates a text embedding vector from the input Content using the specified Gemini Embedding model. hints: readOnly: false destructive: false idempotent: false call: google-gemini.embedcontent with: model: tools.model key: tools.key inputParameters: - name: model type: string description: 'The model name to use for embedding. Format: models/{model}. Example: models/gemini-embedding-001.' required: true - name: key type: string description: API key for authentication. required: true outputParameters: - type: object mapping: $. binds: - namespace: env keys: GOOGLE_GEMINI_TOKEN: GOOGLE_GEMINI_TOKEN