> ## Documentation Index > Fetch the complete documentation index at: https://docs.aitoearn.ai/llms.txt > Use this file to discover all available pages before exploring further. # Gemini Streaming Chat > Interface description: Compatible endpoint (streaming output, SSE) of the Gemini `:streamGenerateContent` API. The request and response formats follow the Gemini specification; authentication uses the `x-goog-api-key` header (carried by Gemini SDK by default). Existing Gemini SDK can be accessed by simply replacing the baseURL and API Key, and billing is based on AiToEarn points. Before calling this interface, please request the ["Conversation Model List"](/en/api-reference/get-api-ai-models-chat) interface (`GET /api/ai/models/chat`) to obtain the currently available model list. ## OpenAPI ````yaml /openapi/en/aitoearn.openapi.json post /api/ai/v1beta/models/{model}:streamGenerateContent openapi: 3.0.1 info: title: AiToEarn Open Platform API description: >- AiToEarn Open Platform API. You can switch between the China and international sites for testing. Business success is determined by whether the response body has code === 0. version: 1.0.0 contact: {} servers: - url: https://aitoearn.cn description: China site - url: https://aitoearn.ai description: International site security: [] tags: - name: AI Services - name: AI Services/Video Generation - name: AI Services/Image Generation - name: Channel Management - name: Channel Management/Accounts - name: Channel Management/Publishing - name: Channel Management/Platforms - name: Channel Management/Works - name: Channel Management/Account Groups - name: Channel Management/Authorization - name: Asset Management - name: AI Services/Large Language Models paths: /api/ai/v1beta/models/{model}:streamGenerateContent: post: tags: - AI Services/Large Language Models summary: Gemini Streaming Chat description: >- Interface description: Compatible endpoint (streaming output, SSE) of the Gemini `:streamGenerateContent` API. The request and response formats follow the Gemini specification; authentication uses the `x-goog-api-key` header (carried by Gemini SDK by default). Existing Gemini SDK can be accessed by simply replacing the baseURL and API Key, and billing is based on AiToEarn points. Before calling this interface, please request the ["Conversation Model List"](/en/api-reference/get-api-ai-models-chat) interface (`GET /api/ai/models/chat`) to obtain the currently available model list. operationId: RelayController_geminiStreamGenerateContent parameters: - name: model in: path description: >- Model ID. First call the ["Conversation Model List"](/en/api-reference/get-api-ai-models-chat) interface (`GET /api/ai/models/chat`) and pass in the `data[n].name` returned by it. required: true example: '' schema: type: string requestBody: content: application/json: schema: type: object properties: model: type: string description: >- Model ID, consistent with the path parameter `model`. The value comes from `data[n].name` returned by the ["Conversation Model List"](/en/api-reference/get-api-ai-models-chat) interface. contents: type: array items: type: object properties: role: type: string enum: - user - model description: >- Message role, used to distinguish different message sources parts: type: array items: anyOf: - type: object properties: text: type: string description: text fragment required: - text - type: object properties: inlineData: type: object properties: mimeType: type: string description: Embedded media type data: type: string description: media raw data required: - mimeType - data description: >- Embedded media byte data passed directly with the request required: - inlineData - type: object properties: fileData: type: object properties: mimeType: type: string description: Media type of file source data fileUri: type: string description: File or media resource URI required: - fileUri description: File media data referenced by URI required: - fileData description: >- An ordered list of content fragments within a single message required: - parts description: Contents list config: description: Generate configuration type: object properties: temperature: type: number description: >- Controls the randomness of the output. The higher the value, the more divergent it is. The lower the value, the more stable it is. topP: type: number description: >- Kernel sampling parameters, limiting the maximum cumulative probability of tokens considered during sampling. topK: type: number description: >- Top-K sampling parameters, limiting the number of highest probability tokens considered during sampling candidateCount: type: number description: The number of candidate answers to be returned maxOutputTokens: type: number description: Maximum number of output tokens for candidate answers responseLogprobs: type: boolean description: >- Whether to return token logarithmic probability information logprobs: type: number description: >- The number of high-probability candidate tokens returned in each decoding step, only takes effect when `responseLogprobs=true` presencePenalty: type: number description: >- There is a penalty that is used to reduce or increase the tendency of tokens to appear again. frequencyPenalty: type: number description: >- Frequency penalty, which suppresses or encourages repetition based on the number of occurrences of the token seed: type: number description: Decode random seeds to improve output reproducibility responseMimeType: type: string description: expected response type responseJsonSchema: description: >- JSON output structure constraints, usually used with `responseMimeType=application/json` additionalProperties: true required: - model - contents examples: {} required: true responses: '200': description: >- Native third-party protocol response or SSE data, not wrapped in the AiToEarn common response envelope. content: application/json: schema: type: object additionalProperties: true description: >- Native third-party protocol response, not wrapped in the AiToEarn common response envelope. examples: success: summary: Native third-party success response value: id: RelayController_geminiStreamGenerateContent_example object: response text/event-stream: schema: type: string description: SSE streaming response. deprecated: false security: - apikey-header-x-goog-api-key: [] components: securitySchemes: apikey-header-x-goog-api-key: type: apiKey in: header name: x-goog-api-key description: API Key header used by Gemini SDK-compatible endpoints. ````