> ## Documentation Index > Fetch the complete documentation index at: https://docs.anyfast.ai/llms.txt > Use this file to discover all available pages before exploring further. # gemini-3.1-flash-image-stream > Generate images using Gemini 3.1 Flash Image in streaming mode via SSE. The endpoint returns newline-delimited Server-Sent Events. Thinking chunks (thought=true) arrive first, followed by the image chunk containing inlineData, and finally a usage metadata chunk. ## OpenAPI ````yaml api-reference/model-api/google/openapi/gemini-3.1-flash-image-stream/openapi.yaml POST /v1beta/models/gemini-3.1-flash-image:streamGenerateContent openapi: 3.1.0 info: title: Gemini 3.1 Flash Image (Stream) description: Google Gemini 3.1 Flash Image streaming image generation via Anyfast proxy version: 1.0.0 servers: - url: https://www.anyfast.ai security: [] paths: /v1beta/models/gemini-3.1-flash-image:streamGenerateContent: post: summary: Image Generation (Streaming) description: > Generate images using Gemini 3.1 Flash Image in streaming mode via SSE. The endpoint returns newline-delimited Server-Sent Events. Thinking chunks (thought=true) arrive first, followed by the image chunk containing inlineData, and finally a usage metadata chunk. operationId: Gemini31FlashImageStreamGenerateContent parameters: - name: key in: query description: API Key required: true schema: type: string example: YOUR_API_KEY - name: alt in: query description: >- Set to sse for explicit Server-Sent Events mode (optional, streaming is the default behaviour of this endpoint) required: false schema: type: string enum: - sse example: sse requestBody: required: true content: application/json: schema: type: object required: - contents - generationConfig properties: contents: type: array description: > Array of conversation turns. Each turn has a role and parts. A part can be a text prompt, or an inline_data image (base64). To use a reference image, include both a text part and an inline_data part in the same parts array. items: type: object properties: role: type: string enum: - user - model example: user parts: type: array description: > List of content parts. Combine text and inline_data in the same array to send a prompt alongside a reference image. items: type: object properties: text: type: string description: Text prompt example: Generate an image of a sunset over mountains inline_data: type: object description: > Reference image encoded as base64 (snake_case in request body). Note: in the streaming response, the field is inlineData (camelCase). properties: mime_type: type: string description: >- MIME type of the image. Supported: image/jpeg, image/png, image/webp enum: - image/jpeg - image/png - image/webp example: image/jpeg data: type: string description: Base64-encoded image data. example: >- iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNk+M9QDwADhgGAWjR9awAAAABJRU5ErkJggg== example: - role: user parts: - text: Generate an image of a sunset over mountains generationConfig: type: object required: - responseModalities properties: responseModalities: type: array description: > Output modalities. Use ["IMAGE"] for image-only output, or ["TEXT", "IMAGE"] to receive both a caption and the image. items: type: string enum: - TEXT - IMAGE example: - TEXT - IMAGE imageConfig: type: object description: Image generation configuration properties: aspectRatio: type: string description: Desired aspect ratio of the generated image. enum: - '1:1' - '4:3' - '3:4' - '16:9' - '9:16' example: '16:9' imageSize: type: string description: > Resolution of the generated image. 1K ≈ 1024px, 2K ≈ 2048px, 4K ≈ 4096px on the long edge. enum: - 1K - 2K - 4K example: 1K responses: '200': description: > Streaming SSE response. Each line starts with "data:" followed by a JSON chunk. Three chunk types are delivered in order: (1) Thinking chunks — parts[0].thought is true; (2) Image chunk — parts[0].inlineData contains mimeType and base64 data (camelCase); (3) Final usage chunk — top-level usageMetadata with thoughtsTokenCount. content: application/json: schema: $ref: '#/components/schemas/StreamChunk' example: candidates: - content: role: model parts: - inlineData: mimeType: image/png data: >- iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNk+M9QDwADhgGAWjR9awAAAABJRU5ErkJggg== usageMetadata: trafficType: ON_DEMAND modelVersion: gemini-3.1-flash-image '400': description: Invalid request content: application/json: schema: $ref: '#/components/schemas/Error' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error' '429': description: Rate limit exceeded content: application/json: schema: $ref: '#/components/schemas/Error' components: schemas: StreamChunk: type: object description: > A single SSE chunk. Three variants are possible: thinking chunk (parts[].thought=true), image chunk (parts[].inlineData), or usage chunk (no candidates). properties: candidates: type: array description: >- Present in thinking and image chunks; absent in the final usage chunk. items: type: object properties: content: type: object properties: role: type: string example: model parts: type: array items: type: object properties: text: type: string description: Thinking text (present in thinking chunks) thought: type: boolean description: True when this part is an internal thinking chunk example: true inlineData: type: object description: > Generated image data (camelCase; present in image chunk only). Note: the request body uses inline_data (snake_case). properties: mimeType: type: string example: image/png data: type: string description: Base64-encoded generated image example: >- iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNk+M9QDwADhgGAWjR9awAAAABJRU5ErkJggg== usageMetadata: type: object description: >- Token usage. Final chunk contains full details including thoughtsTokenCount. properties: promptTokenCount: type: integer example: 8 candidatesTokenCount: type: integer example: 1120 totalTokenCount: type: integer example: 1392 thoughtsTokenCount: type: integer description: >- Number of tokens used for internal thinking (present in final usage chunk) example: 264 trafficType: type: string example: ON_DEMAND promptTokensDetails: type: array items: type: object properties: modality: type: string example: TEXT tokenCount: type: integer example: 8 candidatesTokensDetails: type: array items: type: object properties: modality: type: string example: IMAGE tokenCount: type: integer example: 1120 modelVersion: type: string example: gemini-3.1-flash-image createTime: type: string example: '2025-01-01T00:00:00Z' responseId: type: string example: abc123 Error: type: object properties: error: type: object properties: code: type: integer message: type: string status: type: string ````