GoogleImage model检查中
Nano Banana 2.1 API
nano-banana-2-1-text-to-image-economyGoogle's Nano Banana 2.1 combines text and image inputs for image generation and editing, with attention to visual design and multi-reference workflows.
- 文生图
- 图生图
- Up to 14 input images
- 1K, 2K or 4K output
在 Playground 中运行 Nano Banana 2.1
The form is the request body: every field shows its key. Sign in to run it; a run is billed like an API task.
参数
modelNano Banana 2.1文生图nano-banana-2-1-text-to-image-economy
任务接收时预留额度,仅成功后扣费。失败任务释放预留额度;结果未确认时会保留额度,直到核实。
请求预览
{"model": "nano-banana-2-1-text-to-image-economy","input": {"aspectRatio": "1:1","resolution": "1k"}}网页 Playground 使用你的登录会话发送此请求体。在代码中请使用 API Key 发送相同内容。
结果
运行请求后,结果会显示在这里,并附上状态和费用。
Nano Banana 2.1 价格
各可用版本和规格的价格以美元显示,计费单位随费率注明;只有找到可匹配的官方标价时才显示参考价格。
- Charged only on success仅对成功任务扣费。失败任务释放预留额度;结果尚未确认的任务会保留额度,直到结果核实。
- Safe retries使用相同幂等密钥重试不会重复扣费。
- Price changes发送 expectedPriceMicros:若展示后价格发生变化,任务会以 PRICE_CHANGED 被拒绝。
对比 Nano Banana 2.1 各版本
每个变体都有独立的模型 ID 和输入参数。请先选择任务和版本;变体存在差异时会显示额外字段。
文生图默认值
nano-banana-2-1-text-to-image-stable文生图; 文本; 1K, 2K, 4K; 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9, 1:4, 4:1, 1:8, 8:1
thinkingLevelnano-banana-2-1-image-to-image-stable图生图; 文本, 图像; 1K, 2K, 4K; 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9, 1:4, 4:1, 1:8, 8:1
thinkingLevelnano-banana-2-1-text-to-image-economy文生图; 文本; 1K, 2K, 4K; 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9, 1:4, 4:1, 1:8, 8:1
nano-banana-2-1-image-to-image-economy图生图; 文本, 图像; 1K, 2K, 4K; 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9, 1:4, 4:1, 1:8, 8:1
| 版本 | 任务类型 | 输入 | 分辨率 | Aspect ratios | Extra fields |
|---|---|---|---|---|---|
文生图默认值nano-banana-2-1-text-to-image-stable | 文生图 | 文本 | 1K, 2K, 4K | 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9, 1:4, 4:1, 1:8, 8:1 | thinkingLevel |
图生图nano-banana-2-1-image-to-image-stable | 图生图 | 文本, 图像 | 1K, 2K, 4K | 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9, 1:4, 4:1, 1:8, 8:1 | thinkingLevel |
文生图nano-banana-2-1-text-to-image-economy | 文生图 | 文本 | 1K, 2K, 4K | 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9, 1:4, 4:1, 1:8, 8:1 | — |
图生图nano-banana-2-1-image-to-image-economy | 图生图 | 文本, 图像 | 1K, 2K, 4K | 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9, 1:4, 4:1, 1:8, 8:1 | — |
Nano Banana 2.1 能做什么
Google's Nano Banana 2.1 model card describes a Gemini 3-series image model based on Gemini 3.6 Flash. Google evaluates it for text-to-image design, general editing, character and product consistency, and multi-reference editing. These evaluations are manufacturer results, not guarantees for an individual request.
The Hermes catalog lists stable and economy channels for both text-to-image and image-to-image tasks. Their request schemas offer 1k, 2k and 4k resolution options; edit requests accept up to 14 reference images. The stable variants expose thinkingLevel; the economy variants do not list that field. Check the current status and price of the exact channel before running.
Google's model card notes that small or lengthy text can be blurry, character consistency is imperfect, and spatial or factual details may be wrong. Review generated lettering, identities and factual claims before publishing.
能力
1K, 2K or 4K output
Pick the output resolution: 1K, 2K or 4K.
resolutionEvery variant
14 aspect ratios
1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9, 1:4, 4:1, 1:8 or 8:1.
aspectRatioEvery variant
Up to 14 input images
Send up to 14 images in one request as HTTPS URLs or uploaded media references.
imageUrls版本: 图生图, 图生图
使用场景
Visual concepts
Explore illustration, product or poster ideas from a written prompt and choose an output aspect ratio.
Reference-based editing
Supply up to 14 images and describe what to preserve, replace or combine.
Text-rich layouts
Draft signage or infographics, then verify small text, spelling and factual details.
用代码调用 Nano Banana 2.1
Every image, video and music model uses the same asynchronous job API: submit a task, then poll for the result.
- 1
创建 API Key
In the dashboard, with the jobs:create and jobs:read scopes. API 密钥 - 2
提交任务
POST /api/v1/jobswith the model ID and an input object. The response is 202 with a task ID. - 3
Poll for the result
GET /api/v1/jobs/{id}until the status is succeeded, then download the output URLs.
最小请求
Required fields only, generated from the schema of 文生图. Set HERMES_API_KEY in your environment.
- 模型 ID
nano-banana-2-1-text-to-image-economy- 端点
https://api.hermes-ai.net/api/v1/jobs
# 1. Submit the task (asynchronous; returns 202 with a task id)
curl -X POST https://api.hermes-ai.net/api/v1/jobs \
-H "Authorization: Bearer $HERMES_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"model": "nano-banana-2-1-text-to-image-economy",
"input": {
"prompt": "A lighthouse on a rocky coast at sunrise, soft light",
"resolution": "1k"
}
}'
# 2. Poll until status is succeeded, failed or reconciliation_required
curl https://api.hermes-ai.net/api/v1/jobs/TASK_ID \
-H "Authorization: Bearer $HERMES_API_KEY"输入参数
Fields of 文生图 (nano-banana-2-1-text-to-image-economy). 未知字段会被拒绝并返回 INVALID_MODEL_INPUT。
| 字段 | 类型 | 必填 | 默认值 | 可选值与约束 |
|---|---|---|---|---|
prompt | string | 必填 | — | 1–20000 chars |
aspectRatio | string | 可选 | "1:1" | 可选值: |
resolution | string | 必填 | "1k" | 可选值: |
Headers, response, task statuses and errors
| 请求头 | 值 | 说明 |
|---|---|---|
Authorization | Bearer <API key> | 也可以通过 x-api-key 发送密钥。 |
Content-Type | application/json | |
Idempotency-Key | <unique string ≤128> | 必填。仅在重试完全相同的请求时复用。 |
| 字段 | 类型 | 说明 |
|---|---|---|
id | string | Hermes AI 任务 ID,用于轮询。 |
model | string | 模型 slug。 |
status | string | 参见任务状态。 |
errorCode | string | null | 任务失败或需要核对时设置。 |
priceMicros | integer | 接收时锁定的报价,美元微单位。 |
currency | "USD" | |
createdAt / updatedAt | string | ISO 8601 时间戳。 |
assets[] | array | { id, type, url?, text? }。url 为同源 /api/v1/results/<uuid> 链接。 |
replayed | boolean | 仅提交时返回。幂等重试命中时为 true。 |
| 状态 | 终态 | 含义 |
|---|---|---|
queued | 否 | 已接收,等待执行。 |
submitting | 否 | 正在提交给模型提供方。 |
running | 否 | 模型生成中。 |
succeeded | 是 | 已完成,结果位于 assets。 |
failed | 是 | 未产生结果,预留额度已释放。 |
reconciliation_required | 是 | 结果正在核实。请保留任务 ID,不要自动重新提交。 |
| HTTP | 代码 | 含义与处理方式 |
|---|---|---|
401 | AUTH_REQUIRED | 缺少或无效的 API Key 或会话。 |
403 | INSUFFICIENT_SCOPE | API Key 缺少此端点所需的权限。 |
403 | PERMISSION_DENIED | 此凭据无权执行该操作。 |
429 | API_KEY_RATE_LIMITED | 已达到 API Key 的频率限制,请遵循 Retry-After。 |
429 | API_KEY_USAGE_EXCEEDED | API Key 已达到使用上限,请创建新密钥。 |
400 | INVALID_REQUEST | 请求体不是 JSON 对象,或缺少必需值。 |
400 | INVALID_IDEMPOTENCY_KEY | Idempotency-Key 必须是 1–128 个可打印 ASCII 字符。 |
400 | INVALID_MODEL_INPUT | input 与模型 schema 不匹配(未知字段、缺少必填字段或值无效)。 |
400 / 413 | INPUT_TOO_LARGE | 请求体超过 256 KB。请先上传媒体并发送媒体引用。 |
404 | REQUEST_NOT_FOUND | No chat request with this ID belongs to your account. |
404 | MODEL_NOT_FOUND | 没有此 slug 对应的模型。 |
404 | JOB_NOT_FOUND | 你的账户中没有此 ID 的任务。 |
409 | IDEMPOTENCY_CONFLICT | 此 Idempotency-Key 已用于不同的输入。新请求请使用新密钥。 |
409 | PRICE_CHANGED | 价格与 expectedPriceMicros 不一致。请重新获取价格并确认。 |
409 | MODEL_PRICE_UNAVAILABLE | 此模型尚未配置价格,暂不可运行。 |
409 | PAYMENT_REVIEW_REQUIRED | 退款后余额不足。请联系支持或补足余额后再提交任务。 |
409 | INSUFFICIENT_CREDITS | 可用额度不足以支付此任务。 |
429 | RATE_LIMITED | 每分钟提交次数过多,请稍后重试。 |
429 | EXPORT_RATE_LIMITED | 本分钟内导出 CSV 次数过多,请按 Retry-After 等待后重试。 |
429 | CONCURRENCY_LIMITED | 未完成任务过多,请等待任务完成。 |
503 | EXECUTION_UNAVAILABLE | 此模型当前未配置执行能力。 |
429 | UPSTREAM_RATE_LIMITED | The model provider is rate limiting chat requests. Retry with backoff; nothing was charged. |
502 | UPSTREAM_ERROR | The model provider failed the chat request. Nothing was charged; retry later. |
503 | PLATFORM_BUDGET_EXCEEDED | 此模型暂时不可用,请稍后重试。 |
503 | EXECUTION_TEMPORARILY_UNAVAILABLE | 执行暂时不可用,请使用相同的 Idempotency-Key 重试。 |
503 | AUTH_UNAVAILABLE | 身份验证暂时不可用,请稍后重试。 |
503 | API_UNAVAILABLE | API 暂时不可用,请稍后重试。 |
Nano Banana 2.1 API 常见问题
Answers built from the model's schema and the Hermes AI API contract.
What is the difference between stable and economy?
They are separate catalog channels with their own model IDs and prices. In the current request schemas, stable variants also expose thinkingLevel; economy variants do not. Availability and execution behavior can differ, so check each channel before choosing it.
Does the model always preserve a character or render text correctly?
No. Google lists imperfect character consistency and blurred small or lengthy text among the model's limitations. Compare outputs and verify details before use.
What can the Nano Banana 2.1 API do?
Google 的 Nano Banana 2.1 支持文生图 和 图生图。目录列有4 variants, each,每个变体都有自己的模型 ID 和输入参数。提交请求前请先确认当前可用状态。
Which durations, resolutions and aspect ratios does Nano Banana 2.1 support?
Across its variants, Nano Banana 2.1 supports 1K, 2K 和 4K resolution 和 aspect ratios 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 5:4, 4:5, 21:9, 1:4, 4:1, 1:8 和 8:1. Each variant accepts its own subset; the variants table on this page lists them.
What input does Nano Banana 2.1 accept?
A text prompt of up to 20,000 characters, plus 图像 input (up to 14 images per request). Media fields take a public HTTPS URL or a media:<uuid> reference returned by POST /api/v1/media, so local files can be uploaded first. 未知字段会被拒绝并返回 INVALID_MODEL_INPUT。
How is Nano Banana 2.1 priced and billed?
You pay per successful task from prepaid credits, with no subscription. The price depends on the variant and the specification you choose, such as resolution or duration; see the pricing table on this page or the pricing page. Credits are reserved when a task is accepted and charged only when it succeeds; a failed task returns the reservation to your balance.
Which Nano Banana 2.1 variant should I choose?
For 文生图, 文生图 和 文生图 differ in fields: 文生图 adds thinkingLevel; for 图生图, 图生图 和 图生图 differ in fields: 图生图 adds thinkingLevel. Pick the task first, then compare the tiers in the variants table.
How do I call the Nano Banana 2.1 API from code?
Send POST https://api.hermes-ai.net/api/v1/jobs with the variant's model ID and an input object, then poll GET /api/v1/jobs/{id} until the status is succeeded or failed. The API section has cURL, JavaScript and Python examples generated from the schema.
Can I try Nano Banana 2.1 without writing code?
Yes. Sign in and use the playground on this page: it sends the same request as the API with your session and charges the same price. Code needs an API key from the dashboard.
What happens when a task fails or I hit a rate limit?
A failed task is not charged and its reserved credits are returned. Too many submissions per minute return 429 RATE_LIMITED, and too many unfinished tasks return 429 CONCURRENCY_LIMITED; retry later or wait for a task to finish.