# Nano Banana 2 | Lite | Edit Nano Banana 2 Lite brings next-generation image editing that's fast, cost-efficient, and delivers sharper, higher-quality edits with rapid generation. ## API Information - **Model Slug:** nano-banana-2-lite-edit - **Branded URL:** https://www.eachlabs.ai/google/nano-banana-2-lite/nano-banana-2-lite-edit - **Provider:** Google - **Category:** Image to Image - **Output Type:** array - **Status:** active - **Base Cost:** $0.25–$30.00 per million tokens, depending on token type - **Estimated Processing Time:** 5 seconds - **Interactive Demo:** https://www.eachlabs.ai/ai-models/nano-banana-2-lite-edit ## Pricing - **Charge Type:** dynamic - **Estimate:** $0.25–$30.00 per million tokens, depending on token type - **Pricing Details:** candidates tokens: $30.00 - **Pricing Details:** prompt tokens: $0.25 ## Input Schema | Parameter | Type | Required | Default | Constraints | Description | |-----------|------|----------|---------|-------------|-------------| | prompt | string | Yes | - | - | Edit instructions describing the desired changes to the provided image(s). | | image_urls | array | Yes | - | - | URLs of the images to edit. Minimum 1, maximum 10. | | aspect_ratio | string | No | Auto | Auto, 1:1, 1:4, 4:1, 1:8, 8:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9 | The aspect ratio of the output image. Select 'Auto' to preserve the input image's natural aspect ratio. | | output_format | string | No | png | jpeg, png, webp | Output image format. Gemini always returns PNG; the pipeline converts to the requested format before upload. | | num_images | integer | No | 1 | 1–4 | Number of edited versions to generate. Each version is a separate API call with a 1-image token budget. | | temperature | number | No | - | 0.1–2 | Controls randomness in generation (0.1–2.0). Lower values produce more deterministic results. | | top_p | number | No | - | 0.05–1 | Nucleus sampling threshold (0.05–1.0). Tokens are sampled from the smallest set whose cumulative probability exceeds this value. Leave unset to use the model default. | | thinking_level | string | No | - | minimal, high | Controls the model's internal reasoning depth. 'minimal' uses light reasoning; 'high' improves instruction-following on complex edits at the cost of latency. Leave unset to use the model default. | ## Example Request ```bash curl -X POST https://api.eachlabs.ai/v1/prediction/ \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "nano-banana-2-lite-edit", "input": { "image_urls": [ "https://cdn-us.eachlabs.ai/defaults/707c9c9f827b4be8870350c4c604e060.png" ], "prompt": "Design a modern, stylish tech office branded for \"each::labs\", using the provided each::labs logo and brand colors, with floor-to-ceiling windows overlooking San Francisco and the Golden Gate Bridge. The office must be completely empty — no people, no humans, no staff or visitors anywhere in the scene.Through the large windows, show a stunning panoramic view of the Golden Gate Bridge and the San Francisco bay at golden hour, warm sunset light pouring into the office.Place the full each::labs logo prominently on the main reception wall behind the front desk — it must read the complete wordmark \"each::labs\" in white, exactly as in the provided logo image, with the signature \"::\" rendered as four small orange-red squares (two stacked pairs), not circles. Do not crop, cut off, or alter the logo — show the entire \"each::labs\" name clearly and correctly.Incorporate the brand's color palette — deep navy/midnight blue, crimson red, with the orange-red accent — throughout the space: accent walls, lighting, furniture, and decor. Include a sleek marble reception desk, modern lounge seating, glass meeting rooms, indoor plants, polished concrete floors, and warm modern lighting.The mood is professional, premium, innovative — a high-end AI/tech startup headquarters in San Francisco, shown empty with no people, with the Golden Gate Bridge visible through the windows.Style: photorealistic interior design photography, professional architectural visualization, cinematic golden-hour lighting, high detail, 4K." } }' ``` ## Output Schema Response returned by `GET /v1/prediction/{id}` when the job completes: ```json { "status": "success", "predictionID": "string", "output": "array", "metrics": { "predict_time": "number (seconds)" } } ``` ## Polling ```bash curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \ -H "Authorization: Bearer YOUR_API_KEY" ``` | Status | Meaning | |--------|---------| | `processing` | Still running — poll again | | `success` | Done — read `output` | | `error` | Failed — read `message` / `details` | ## Webhook (alternative to polling) Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends: ```json { "exec_id": "prediction-uuid", "status": "succeeded", "output": "https://...", "error": "" } ``` `status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds. ## Errors Error body: `{ "status": "error", "message": "...", "details": "..." }` | Code | Meaning | |------|---------| | `400` | Invalid input | | `401` | Missing / invalid `Authorization` bearer token | | `404` | Unknown model or prediction id | | `429` | Rate limit — 100 creates / min, 10 concurrent per key | | `5xx` | Retry with backoff | ## Overview **Nano Banana 2 | Lite | Edit Overview** **Nano Banana 2 | Lite | Edit** is Google’s fast image-editing model for turning an uploaded image into a modified result through natural-language instructions. It is designed for users who need quick visual iteration, not just one-off generation, and it emphasizes speed, cost efficiency, and reliable edit control. Google positions it as **Gemini 3.1 Flash-Lite Image**, which is the official family name behind this model. Within the Nano Banana family, this model stands out for rapid editing workflows, strong character consistency, and legible text rendering while keeping turnaround times low. It is a practical fit for each::labs users who need the **Nano Banana 2 | Lite | Edit API** for fast drafts, ad variations, concept edits, and high-volume image-to-image tasks. ## Usage Notes - API Base URL: `https://api.eachlabs.ai/v1` - Authentication: send `Authorization: Bearer YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys. - File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected. - For structured parameters (arrays / objects) send real JSON values, not stringified payloads. - Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally. - Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.