gemini-3-pro-image (Nano Banana Pro): Gere imagens, edite referências e refine designs pela Flatkey. O exemplo usa contents/parts do Gemini, não um corpo intercambiável da Images API.
Gerado com Image 2
Somente prévia. Entre para enviar esta solicitação à Flatkey.
{
"model": "gemini-3-pro-image",
"contents": [
{
"role": "user",
"parts": [
{
"text": "Creative direction: Create a vertical museum-catalog infographic dissecting a Ming-dynasty hanfu. Place a central woman in a pale robe, exploded garment components and construction views on the left, fabric, weave, and pattern swatches on the right, and a step-by-step dressing sequence along the bottom. Use a restrained cream, navy, muted red, and ink palette with precise Chinese annotation hierarchy and generous archival margins.\n\nComposition, material and finish: Use a strict museum-plate grid with aligned callout leaders and consistent scale within each garment view. Distinguish weave, embroidery and seam construction without turning fabric into metal. Keep the same robe and wearer across every detail and dressing step. Preserve negative space between diagrams and Chinese labels; avoid invented historical claims, mismatched fastenings and watermarks."
}
]
}
],
"generationConfig": {
"responseModalities": [
"TEXT",
"IMAGE"
],
"imageConfig": {
"aspectRatio": "1:1",
"imageSize": "1K"
}
}
}Desempenho da API
A telemetria de solicitações da Flatkey para gemini-3-pro-image aparecerá aqui quando houver tráfego de produção suficiente.
Atividade da API
Acompanhe o volume de solicitações e a atividade de inferência bem-sucedida de gemini-3-pro-image no período mais recente.
gemini-3-pro-image preços
Os cartões mostram as tarifas atuais de tokens de entrada e saída da Flatkey. Tarifa por token não é preço fixo por imagem: configurações, referências e saída afetam o consumo. Preços e cotas gratuitas diretas do Google não se aplicam automaticamente.
Use o mesmo saldo e a mesma chave de API Flatkey para modelos de imagem, vídeo, áudio e texto.
A rota gemini-3-pro-image de Google aceita texto · imagem. Categorias do catálogo: Marketing.
Descreva assunto, composição, luz e texto. Defina controles de saída nos campos da solicitação, não apenas no prompt.
Adicione referências e indique o que preservar e alterar. Respeite os limites da matriz de parâmetros.
Escolha apenas proporções e tamanhos oferecidos no Playground. Flash, Flash Lite e Pro têm limites diferentes.
Mantenha o ID exato e a estrutura contents/parts do exemplo. Teste uma solicitação pequena antes de processar lotes.
Comparar
Compare os fatos do catálogo de gemini-3-pro-image com a referência da geração anterior antes de alterar sua integração.
| Capacidade | Geração anterior | gemini-3-pro-image |
|---|---|---|
| Provedor | Não verificado neste instantâneo do catálogo | |
| Modalidades | Não verificado neste instantâneo do catálogo | texto · imagem |
| Contexto | Não verificado neste instantâneo do catálogo | A janela de contexto não está listada no catálogo |
| Endpoint da API | Não verificado neste instantâneo do catálogo | /v1beta/models/gemini-3-pro-image:generateContent |
| Cobrança | Não verificado neste instantâneo do catálogo | $2/$12 per 1M tokens |
Confira fluxos, custo atual e o contrato exato de parâmetros da Flatkey.
Calculada com a configuração atual e a tarifa do catálogo quando há preço unitário fixo.
A cobrança final depende da solicitação e do grupo; preços por tokens ou faixas não viram uma estimativa fixa.
Use apenas fluxos disponíveis. A Flatkey mantém um ID público e o corpo escolhe a entrada.
Gere uma imagem a partir de texto.
gemini-3-pro-image/v1beta/models/gemini-3-pro-image:generateContentUse referências para editar ou variar imagens.
gemini-3-pro-image/v1beta/models/gemini-3-pro-image:generateContentValores da mesma configuração usada no Playground.
aspect_ratioProporção1:1 · 2:3 · 3:2 · 3:4 · 4:3 · 4:5 · 5:4 · 9:16 · 16:9 · 21:9
Padrão: 1:1image_sizeTamanho1K · 2K · 4K
Padrão: 1KimageLimite de referências4 arquivos
Endpoint: /v1beta/models/gemini-3-pro-image:generateContentUse o mesmo contrato no Playground e na API e trate validação, saldo, estado e resultado.
Validar modelo, prompt, referências e saída.
Enviar a solicitação de imagem.
Ler o resultado ou tarefa assíncrona.
Armazenar arquivo e metadados.
Bloqueie valores e referências incompatíveis.
Trate chave, saldo, limites e grupo separadamente.
Identifique o prompt ou mídia a substituir.
Guarde o task ID, limite tentativas e não trate timeout como sucesso.
Biblioteca de prompts
Comece com um prompt de gemini-3-pro-image para geração de imagens e ajuste os campos de solicitação exibidos no playground.
Gerado com Image 2
Scene: A 16:9 underwater game loadout screen on a sea floor. An armored diver stands on a circular pedestal holding a glowing cyan sword, with submerged ruins behind and a weapon-swap panel on the right. Lock the diver silhouette, sword, aquatic lighting, pedestal, and interface hierarchy for an exact equipment-switch frame. No readable words, logos, invented stats, or watermark. Composition and rendering: Deliver one 16:9 game-interface keyframe. Separate the character, held equipment and HUD into clear depth layers; keep slot spacing and icon scale consistent, with the selected item visually dominant. Preserve the scene-specific game art style. Let material edges catch the existing light without letting interface glow obscure the silhouette. Keep all equipment fully inside the frame. Avoid: warped perspective, malformed anatomy, merged objects, inconsistent shadows, excessive sharpening and watermarks. Follow the scene-specific text and branding restrictions above.
Gerado com Image 2
Scene: A televised basketball frame shows a red-uniform player taking a jump shot while a white-uniform defender contests it in an indoor arena. Include the hoop, overhead lights, crowd blur, and abstract red-and-gray lower-third panels without readable text. Keep the broadcast angle, ball arc, uniforms, and player spacing coherent; no real teams, athletes, logos, or watermark. Composition and rendering: Deliver one 16:9 broadcast still at the decisive instant. Use coherent perspective for the playing surface and equipment, readable separation between competitors, and a softer crowd behind the action. Keep the principal subject sharp, with directional blur limited to fast extremities and spray. Preserve the specified broadcast angle and reserve overlay areas clear of the action. Avoid: warped perspective, malformed anatomy, merged objects, inconsistent shadows, excessive sharpening and watermarks. Follow the scene-specific text and branding restrictions above.
Gerado com Image 2
Scene: A clear glass dropper bottle filled with pale gold serum stands on a white stone block in a warm cream room. Soft sunlight and large leaf shadows fall across the wall and the liquid, glass, metal collar, and surface catch subtle reflections. Preserve the bottle proportions and generous blank space; no readable branding, extra products, hands, or watermark. Composition and rendering: Deliver one 16:9 commercial product still. Keep the complete product silhouette inside generous crop-safe margins. Resolve edges, seams and material transitions precisely; shape highlights to describe volume without clipping bright surfaces or crushing dark details. Align reflections with the object and light source. Retain the stated camera angle and existing negative space; add no decorative props. Avoid: warped perspective, malformed anatomy, merged objects, inconsistent shadows, excessive sharpening and watermarks. Follow the scene-specific text and branding restrictions above.
Gerado com Image 2
Scene: At a rain-wet historic train platform, a young traveler in a dark cap and coat holds a brown suitcase while a steam train waits under a long canopy. Warm lamps recede into the blue night and reflect on the platform. Hold the traveler profile, suitcase, train direction, and wide composition for a continuous storyboard. No readable signs, logos, or watermark. Composition and rendering: Deliver one 16:9 storyboard keyframe, not a collage or an action sequence. Separate foreground, character plane and background through the existing light and atmospheric depth. Keep the stated pose and eyelines readable, and retain environmental landmarks for continuity. Match the described photographic, illustrated or puppet medium; give fabric and surfaces texture appropriate to that medium. Avoid: warped perspective, malformed anatomy, merged objects, inconsistent shadows, excessive sharpening and watermarks. Follow the scene-specific text and branding restrictions above.
Gerado com Image 2
Scene: On a small theater stage, a startled magician in black pulls a long rainbow cloth from a tall black trunk wrapped in more cloth. The audience is dim behind him, with red curtains and colored spotlights. Freeze the harmless reveal at the moment the fabric stretches between hand and trunk; preserve object weight, pose, and stage spacing. No readable words, logos, injury, or watermark. Composition and rendering: Deliver one 16:9 physical-comedy still at the described instant. Make the cause of the gag readable through body balance, grip and object spacing. Separate the reaction from the airborne props; retain believable gravity and contact points. Keep the face and important props sharp, with only restrained directional blur on fast edges. Preserve the stated lighting and room or stage layout. Avoid: warped perspective, malformed anatomy, merged objects, inconsistent shadows, excessive sharpening and watermarks. Follow the scene-specific text and branding restrictions above.
Gerado com Image 2
Scene: A sepia archival photograph shows four workers weaving cloth on wooden looms inside a rustic workshop, with yarn baskets and bright hillside scenery through the windows. Restore the paper texture, faces without sharpening them into modern portraits, loom construction, period clothing, and gentle film wear. No modern objects, readable signage, logos, captions, or watermark. Composition and restoration: Deliver one 16:9 archival-style still. Preserve the original framing, period-specific construction and restrained tonal range; retain monochrome, sepia or faded color as described. Recover modest detail in faces, clothing and architecture without synthetic sharpening. Keep fine grain and authentic aging consistent across the frame; repair damage without replacing historical features. Avoid: warped perspective, malformed anatomy, merged objects, inconsistent shadows, excessive sharpening and watermarks. Follow the scene-specific text and branding restrictions above.
Por que usar a API gemini-3-pro-image
Use um único gateway para gemini-3-pro-image, controles da conta e o restante do catálogo de modelos.
Mantenha o ID do modelo e o endpoint de gemini-3-pro-image explícitos usando a mesma chave Flatkey das demais cargas.
Veja as dimensões de cobrança atuais de gemini-3-pro-image antes do envio e confirme a estimativa final na conta.
Teste um prompt de gemini-3-pro-image no playground público e leve as mesmas configurações para uma integração autenticada.
Centralize chaves, cotas e roteamento de gemini-3-pro-image sem mudar o fluxo da aplicação voltado ao provedor.
API
Quatro formas de entrar, com a mesma chave e catálogo. Escolha uma para ver um exemplo executável.
curl https://router.flatkey.ai/v1beta/models/gemini-3-pro-image:generateContent \ -H "Content-Type: application/json" \ -H "Authorization: Bearer sk-***" \ -d '{"model":"gemini-3-pro-image","contents":[{"role":"user","parts":[{"text":"Crie com gemini-3-pro-image uma imagem de produto de alta qualidade: composição limpa, iluminação precisa, foco forte no produto e detalhes realistas."}]}],"generationConfig":{"responseModalities":["TEXT","IMAGE"],"imageConfig":{"aspectRatio":"1:1","imageSize":"1K"}}}'
Perguntas frequentes
Respostas sobre preços, capacidades, endpoints e limites do catálogo de gemini-3-pro-image.
