> ## Documentation Index > Fetch the complete documentation index at: https://docs.modellix.ai/llms.txt > Use this file to discover all available pages before exploring further. # Nano Banana 2.1 > [Core Function] Nano Banana 2.1 is Google's fast text-to-image model on Gemini 3.6 Flash, exposed as google/nano-banana-2.1. [Strengths] It keeps Flash-level speed at 1K, 2K, and 4K, with stronger visual quality, text rendering, and real-world knowledge than Nano Banana 2. thinkingLevel trades latency for quality and defaults to medium. Optional systemInstruction is omitted when blank. enableWebSearch turns on Google Search grounding (web and image search) only when true. [Best For] High-volume image production, posters and diagrams with readable text, localized text, and rapid iteration on new text-to-image work. [Limitations] Do NOT use this model for image or video editing, 512-pixel output, audio input, or reference images. This endpoint accepts a prompt only. seed, temperature, topP, topK, and logprobs are rejected. [Routing] Use google/nano-banana-2.1 for new text-to-image work. Use google/nano-banana-2 when the caller needs the 512 resolution of Gemini 3.1 Flash Image. Use google/nano-banana-2.1-edit when the user supplies images or a video. Use google/nano-banana-pro when the user wants the highest-end professional stills. ## OpenAPI ````yaml /media-model-api/google/google-t2i.json post /google/nano-banana-2.1 openapi: 3.1.0 info: description: The text-to-image models API from Google (Gemini / Nano Banana series). version: 1.0.0 contact: name: Modellix Support email: support@modellix.ai title: Google Text-to-Image Models API servers: - url: https://api.modellix.ai/api/v1 description: The text-to-image models API from Google. security: - bearerAuth: [] paths: /google/nano-banana-2.1: post: summary: Nano Banana 2.1 description: >- [Core Function] Nano Banana 2.1 is Google's fast text-to-image model on Gemini 3.6 Flash, exposed as google/nano-banana-2.1. [Strengths] It keeps Flash-level speed at 1K, 2K, and 4K, with stronger visual quality, text rendering, and real-world knowledge than Nano Banana 2. thinkingLevel trades latency for quality and defaults to medium. Optional systemInstruction is omitted when blank. enableWebSearch turns on Google Search grounding (web and image search) only when true. [Best For] High-volume image production, posters and diagrams with readable text, localized text, and rapid iteration on new text-to-image work. [Limitations] Do NOT use this model for image or video editing, 512-pixel output, audio input, or reference images. This endpoint accepts a prompt only. seed, temperature, topP, topK, and logprobs are rejected. [Routing] Use google/nano-banana-2.1 for new text-to-image work. Use google/nano-banana-2 when the caller needs the 512 resolution of Gemini 3.1 Flash Image. Use google/nano-banana-2.1-edit when the user supplies images or a video. Use google/nano-banana-pro when the user wants the highest-end professional stills. operationId: nanoBanana21T2IAsync requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/NanoBanana21Request' examples: text_only: summary: Text-to-image value: prompt: A colorful abstract painting with flowing shapes with_options: summary: With aspect ratio and resolution value: prompt: Minimalist geometric art with bold colors aspectRatio: '9:21' imageSize: 2K thinkingLevel: medium responses: '200': description: Task submitted successfully content: application/json: schema: $ref: '#/components/schemas/AsyncTaskResponse' example: code: 0 message: success data: status: pending task_id: task-nb21 model_id: google/nano-banana-2.1 get_result: method: GET url: https://api.modellix.ai/api/v1/tasks/task-nb21 '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '429': $ref: '#/components/responses/TooManyRequests' '500': $ref: '#/components/responses/InternalServerError' components: schemas: NanoBanana21Request: type: object required: - prompt properties: prompt: type: string description: Image description text minLength: 1 example: A colorful abstract painting with flowing shapes aspectRatio: type: string description: Image aspect ratio. Defaults to 1:1. default: '1:1' enum: - '1:1' - '3:2' - '2:3' - '3:4' - '1:4' - '4:1' - '4:3' - '4:5' - '5:4' - '1:8' - '8:1' - '9:16' - '16:9' - '21:9' - '9:21' example: '1:1' imageSize: type: string description: Output image resolution. Defaults to 1K. 512 is not supported. default: 1K enum: - 1K - 2K - 4K example: 1K thinkingLevel: type: string description: >- Thinking effort. minimal is fastest; high spends more thinking. Defaults to medium. default: medium enum: - minimal - medium - high example: medium systemInstruction: type: string description: >- Optional system instruction. Omitted when empty. Not sent upstream when blank. enableWebSearch: type: boolean description: >- When true, enables Google Search grounding with web search and image search. Image search cannot be used to look up people. Omitted or false does not send the tool. Search uses extra tokens. AsyncTaskResponse: type: object required: - code - message - data properties: code: type: integer description: Response code, 0 indicates success example: 0 message: type: string description: Response message example: success data: type: object required: - status - task_id - model_id properties: status: type: string enum: - pending - processing description: Task status example: pending task_id: type: string description: Unique task identifier for polling example: task-abc123 model_id: type: string description: Model ID in `provider/model` format example: google/nano-banana get_result: type: object description: API information to query the task result properties: method: type: string description: HTTP method example: GET url: type: string description: Full URL to query the task result example: https://api.modellix.ai/api/v1/tasks/task-abc123 description: Detailed data about the submitted asynchronous task. ErrorResponse: type: object required: - code - message properties: code: type: integer description: Error code (equals HTTP status code) example: 400 message: type: string description: 'Error message in format ''Category: detail''' example: 'Invalid parameters: parameter ''prompt'' is required' responses: BadRequest: description: Invalid request parameters content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: code: 400 message: 'Invalid parameters: parameter ''prompt'' is required' Unauthorized: description: Unauthorized - Invalid or missing API Key content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: code: 401 message: 'Authentication failed: invalid API key' TooManyRequests: description: Too many requests - Rate limit exceeded headers: X-RateLimit-Limit: description: Maximum requests per minute schema: type: integer example: 100 X-RateLimit-Remaining: description: Remaining quota in current window schema: type: integer example: 0 X-RateLimit-Reset: description: Rate limit window reset time (Unix timestamp) schema: type: integer example: 1704067260 content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: code: 429 message: >- Rate limit exceeded: 100 requests per minute, retry after 60 seconds InternalServerError: description: Internal server error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: code: 500 message: Internal server error securitySchemes: bearerAuth: type: http scheme: bearer description: 'API Key authentication. Format: `Bearer YOUR_API_KEY`.' ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.