{
  "id": 12429003,
  "title": "Nano Banana 2.1 Lançado: Metade do Preço do Nano Banana 2 e o Texto Finalmente Funciona",
  "url": "https://urgent.news/2026/10/06/nano-banana-2-1-lancado-metade-do-preco-do-nano-banana-2-e-o-texto",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-06T17:24:50.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/lucas_ferreira/nano-banana-21-lancado-metade-do-preco-do-nano-banana-2-e-o-texto-finalmente-funciona-2n9k"
  },
  "original_language": "pt",
  "account": "Google released Nano Banana 2.1 on October 6th, 2026, without fanfare. The model appeared in the Google Flow model selector on October 5th, disappeared, and returned the next day with a brief post on @GoogleAIStudio, claiming it \"outperforms our previous models in every aspect\". Pricing for image generation is the key factor for users.\n\nThe Nano Banana 2.1 costs half the price of Nano Banana 2 for all shared resolutions. Google's documentation lists \"precise text rendering\" as one of its improvements. This guide covers what changed, the cost, limitations, and how to test the model via API.\n\nSpecifications:\n- Model ID: gemini-nano-banana-2.1\n- Output resolutions: 1K, 2K, 4K\n- Inputs: Text, image, video without audio\n- Reference images: Up to 14\n- Thinking: Enabled by default and cannot be disabled on the API\n- Intermediate thinking outputs: Up to two, with no additional charges\n- Search grounding: Uses Google Web Search and Google Image Search\n\nImproved aspects:\n- Better design visual\n- Mask-based editing\n- Greater subject consistency\n- More natural images\n- Precise text rendering\n- Search grounding with Google Image Search\n\nText rendering specifics:\n- Generates readable, stylized text for infographics, menus, diagrams, and marketing assets\n- Precise text rendering is a specific improvement in version 2.1\n- This claim is from Google, not a measured result\n- No public benchmark of text rendering precision for version 2.1\n\nTesting:\n- Test real product prompts before migrating production traffic\n- Menu and menu cards\n- Product labels\n- Posters\n- Slides\n- Mockups\n- Infographics\n- Mask-based editing allows modifying specific parts of an image by describing them in the prompt, preserving the rest of the image. This \"semantic masking\" can be used for menus, labels, posters, slides, and infographics.",
  "summary": "O Google lançou o Nano Banana 2.1 em 6 de outubro de 2026, e o fez discretamente. Não houve um post de blog de lançamento nem um gráfico de benchmark. O modelo apareceu no seletor de modelos do Google Flow em 5 de outubro, desapareceu e depois voltou no dia seguinte com um breve post de @GoogleAIStudio dizendo que ele “supera nossos modelos anteriores em todos os aspectos.” Experimente o Apidog…",
  "key_points": [
    "Nano Banana 2.1 launched on October 6th, 2026, at half the price of Nano Banana 2",
    "Text rendering is a specific improvement in version 2.1, but no public benchmark provided"
  ],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}