Black Forest LabsImage model检查中
FLUX 3 API
flux-3-klein-text-to-imageFLUX 3 Image and FLUX 3 Image Klein generate images from text and support reference-based editing.
- 文生图
- 图生图
- Up to 10 input images
- 1.5K, 2K or 4K output
- 格式选项
在 Playground 中运行 FLUX 3
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
modelFLUX 3Klein text to imageflux-3-klein-text-to-image
高级参数 (3)
input.seedRandom seed. Leave empty for random. 0–2147483647
input.stepsSampling steps 1-16, default 16. Fewer is faster but may lower quality; price unchanged. 1–16
input.safetyToleranceModeration tolerance, 0 strictest to 4, default 2. 0–4
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": "flux-3-klein-text-to-image","input": {"aspectRatio": "1:1","resolution": "1k","steps": 16,"outputFormat": "jpeg","safetyTolerance": 2}}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。
FLUX 3 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 FLUX 3 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
flux-3-text-to-image文生图; 文本; 768sq, 1K, 1.5K, 2K, 4K; 21:9, 2:1, 16:9, 3:2, 7:5, 4:3, 5:4, 1:1, 4:5, 3:4, 5:7, 2:3, 9:16, 1:2, 9:21
groundingflux-3-image-to-image图生图; 文本, 图像; 768sq, 1K, 1.5K, 2K, 4K; 21:9, 2:1, 16:9, 3:2, 7:5, 4:3, 5:4, 1:1, 4:5, 3:4, 5:7, 2:3, 9:16, 1:2, 9:21
groundingflux-3-klein-text-to-image文生图; 文本; 768sq, 1K, 1.5K, 2K, 4K; 21:9, 2:1, 16:9, 3:2, 7:5, 4:3, 5:4, 1:1, 4:5, 3:4, 5:7, 2:3, 9:16, 1:2, 9:21
seedstepsoutputFormatflux-3-klein-image-to-image图生图; 文本, 图像; 768sq, 1K, 1.5K, 2K, 4K; 21:9, 2:1, 16:9, 3:2, 7:5, 4:3, 5:4, 1:1, 4:5, 3:4, 5:7, 2:3, 9:16, 1:2, 9:21
seedstepsoutputFormat
| 版本 | 任务类型 | 输入 | 分辨率 | Aspect ratios | Extra fields |
|---|---|---|---|---|---|
文生图默认值flux-3-text-to-image | 文生图 | 文本 | 768sq, 1K, 1.5K, 2K, 4K | 21:9, 2:1, 16:9, 3:2, 7:5, 4:3, 5:4, 1:1, 4:5, 3:4, 5:7, 2:3, 9:16, 1:2, 9:21 | grounding |
图生图flux-3-image-to-image | 图生图 | 文本, 图像 | 768sq, 1K, 1.5K, 2K, 4K | 21:9, 2:1, 16:9, 3:2, 7:5, 4:3, 5:4, 1:1, 4:5, 3:4, 5:7, 2:3, 9:16, 1:2, 9:21 | grounding |
Klein text to imageflux-3-klein-text-to-image | 文生图 | 文本 | 768sq, 1K, 1.5K, 2K, 4K | 21:9, 2:1, 16:9, 3:2, 7:5, 4:3, 5:4, 1:1, 4:5, 3:4, 5:7, 2:3, 9:16, 1:2, 9:21 | seedstepsoutputFormat |
Klein image to imageflux-3-klein-image-to-image | 图生图 | 文本, 图像 | 768sq, 1K, 1.5K, 2K, 4K | 21:9, 2:1, 16:9, 3:2, 7:5, 4:3, 5:4, 1:1, 4:5, 3:4, 5:7, 2:3, 9:16, 1:2, 9:21 | seedstepsoutputFormat |
FLUX 3 能做什么
Black Forest Labs lists FLUX 3 Image and Image Klein as distinct image models. The manufacturer describes Klein as an open-weights member of the family for generation and multi-reference editing; its API or self-hosting terms should be checked separately.
The Hermes catalog groups standard and Klein text-to-image and image-to-image variants on this page. Their schemas list output tiers from 768sq through 4k; edit variants accept up to ten reference images. The standard variants also list a grounding option. Check the selected variant's status and price before making a request.
Black Forest Labs also describes bounding-box editing for its FLUX 3 Image product. Those controls are not listed in these Hermes request schemas; consult the selected variant's parameters rather than assuming every manufacturer feature is exposed here.
能力
格式选项
请求参数列出了这些格式;具体可用性和结果交付取决于所选变体。
JPEG · PNG
outputFormat版本: Klein text to image, Klein image to image
1.5K, 2K or 4K output
Pick the output resolution: 768sq, 1K, 1.5K, 2K or 4K.
resolutionEvery variant
15 aspect ratios
21:9, 2:1, 16:9, 3:2, 7:5, 4:3, 5:4, 1:1, 4:5, 3:4, 5:7, 2:3, 9:16, 1:2 or 9:21.
aspectRatioEvery variant
Up to 10 input images
Send up to 10 images in one request as HTTPS URLs or uploaded media references.
imageUrls版本: 图生图, Klein image to image
随机种子
Accepts a seed value.
seed版本: Klein text to image, Klein image to image
使用场景
Create image concepts
Describe a scene or visual brief and select a resolution and aspect ratio.
Edit from references
Supply reference images and a prompt that states what should change.
Compare model variants
Try standard or Klein when each is available, using the same prompt and output requirements.
用代码调用 FLUX 3
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 Klein text to image. Set HERMES_API_KEY in your environment.
- 模型 ID
flux-3-klein-text-to-image- 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": "flux-3-klein-text-to-image",
"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 Klein text to image (flux-3-klein-text-to-image). 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 | — | Scene description or edit instruction. No negative prompt; a bbox JSON array may be appended for layout or local edits. 1–20000 chars |
aspectRatio | string | 可选 | "1:1" | Output aspect ratio. auto follows the first reference image when editing, or the prompt for text-to-image. 可选值: |
resolution | string | 必填 | "1k" | Resolution tier, decides the price. 768sq ~768x768, 1k ~1MP, 1.5k ~2MP, 2k ~4MP, 4k ~16MP. 可选值: |
seed | integer | 可选 | — | Random seed. Leave empty for random. 0–2147483647 |
steps | integer | 可选 | 16 | Sampling steps 1-16, default 16. Fewer is faster but may lower quality; price unchanged. 1–16 |
outputFormat | string | 可选 | "jpeg" | Output image format. 可选值: |
safetyTolerance | integer | 可选 | 2 | Moderation tolerance, 0 strictest to 4, default 2. 0–4 |
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。 |
FLUX 3 API 常见问题
Answers built from the model's schema and the Hermes AI API contract.
Does this page cover FLUX 3 Video?
No. This family page covers image variants. FLUX 3 Video has separate text-to-video, image-to-video and continuation variants.
Can I use the manufacturer's bounding-box editor here?
The manufacturer describes bounding-box controls on its product page, but they are not exposed in the current Hermes schemas for these variants.
What can the FLUX 3 API do?
Black Forest Labs 的 FLUX 3 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 FLUX 3 support?
Across its variants, FLUX 3 supports 768sq, 1K, 1.5K, 2K 和 4K resolution 和 aspect ratios 21:9, 2:1, 16:9, 3:2, 7:5, 4:3, 5:4, 1:1, 4:5, 3:4, 5:7, 2:3, 9:16, 1:2 和 9:21. Each variant accepts its own subset; the variants table on this page lists them.
What input does FLUX 3 accept?
A text prompt of up to 20,000 characters, plus 图像 input (up to 10 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 FLUX 3 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 FLUX 3 variant should I choose?
For 文生图, 文生图 和 Klein text to image differ in fields: 文生图 adds grounding; Klein text to image adds seed, steps, outputFormat; for 图生图, 图生图 和 Klein image to image differ in fields: 图生图 adds grounding; Klein image to image adds seed, steps, outputFormat. Pick the task first, then compare the tiers in the variants table.
How do I call the FLUX 3 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 FLUX 3 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.