Aller au contenu

Black Forest LabsImage modelVérification

FLUX 3 API

Model IDflux-3-image-to-image

FLUX 3 Image and FLUX 3 Image Klein generate images from text and support reference-based editing.

  • Text to image
  • Image to image
  • Up to 10 input images
  • 1.5K, 2K or 4K output
  • Format options

Lancez FLUX 3 dans le playground

The form is the request body: every field shows its key. Sign in to run it; a run is billed like an API task.

Paramètres

Modèle
model

FLUX 3Image to imageflux-3-image-to-image

Obligatoire
input.imageUrls

Reference images, 1-10. One for single-image edit; multiple are referenced as Image 1 / Image 2 in order. Each image must be at most 16,777,216 pixels (about 4096x4096; total pixels, not side length), otherwise it is rejected. ≤ 10 items · HTTPS image URL or media:<uuid>

input.prompt

Scene description or edit instruction. No negative prompt; a bbox JSON array may be appended for layout or local edits. 1–20000 chars

input.resolution

Resolution tier, decides the price. 768sq ~768x768, 1k ~1MP, 1.5k ~2MP, 2k ~4MP, 4k ~16MP.

Options courantes
input.aspectRatio

Output aspect ratio. auto follows the first reference image when editing, or the prompt for text-to-image.

Avancé (2)
input.grounding

Allow web or image search before generation. On by default.

input.safetyTolerance

Moderation tolerance, 0 strictest to 4, default 2. 0–4

Estimated cost
Chargement du prix…

Les crédits sont réservés à l’acceptation d’une tâche et débités seulement en cas de succès. Une tâche échouée libère la réservation ; un résultat non confirmé reste réservé jusqu’à vérification.

Aperçu de la requête

{"model": "flux-3-image-to-image","input": {"aspectRatio": "auto","resolution": "1k","grounding": true,"safetyTolerance": 2}}

Le playground web envoie ce corps avec votre session connectée. Depuis votre code, envoyez le même corps avec une clé d’API.

Résultat

Run the request and the result appears here, with its status and cost.

Tarifs de FLUX 3

Prices are shown in USD for each available variant and specification. The billing unit is shown with its rate; an official reference appears only when a matching list price is published.

Chargement du prix…
  • Charged only on successOnly successful tasks are charged. Failed tasks release reserved credits; tasks with an unconfirmed outcome keep their reservation until the result is verified.
  • Safe retriesLes nouvelles tentatives idempotentes avec la même clé ne créent pas de second débit.
  • Price changesEnvoyez expectedPriceMicros pour rejeter la tâche avec PRICE_CHANGED si le prix a changé après son affichage.

Comparez les variantes de FLUX 3

Each variant has its own model ID and input schema. Pick the task first, then the tier. Additional fields are shown when variants differ.

  • Text to imagePar défaut

    flux-3-text-to-image

    Text to image; Texte; 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
  • Image to image

    flux-3-image-to-image

    Image to image; Texte, image; 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 image

    flux-3-klein-text-to-image

    Text to image; Texte; 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 image

    flux-3-klein-image-to-image

    Image to image; Texte, image; 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

Ce que FLUX 3 sait faire

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.

Capacités

  • Format options

    The request schema lists these formats. Availability and delivery depend on the variant.

    JPEG · PNG

    outputFormat

    Variantes: 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.

    resolution

    Every 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.

    aspectRatio

    Every variant

  • Up to 10 input images

    Send up to 10 images in one request as HTTPS URLs or uploaded media references.

    imageUrls

    Variantes: Image to image, Klein image to image

  • Seed

    Accepts a seed value.

    seed

    Variantes: Klein text to image, Klein image to image

Cas d’usage

  1. Create image concepts

    Describe a scene or visual brief and select a resolution and aspect ratio.

  2. Edit from references

    Supply reference images and a prompt that states what should change.

  3. Compare model variants

    Try standard or Klein when each is available, using the same prompt and output requirements.

Appelez FLUX 3 depuis votre code

Every image, video and music model uses the same asynchronous job API: submit a task, then poll for the result.

  1. 1

    Créez une clé d’API

    In the dashboard, with the jobs:create and jobs:read scopes. Clés d’API
  2. 2

    Soumettre une tâche

    POST /api/v1/jobs with the model ID and an input object. The response is 202 with a task ID.
  3. 3

    Poll for the result

    GET /api/v1/jobs/{id} until the status is succeeded, then download the output URLs.

Requête minimale

Required fields only, generated from the schema of Image to image. Set HERMES_API_KEY in your environment.

Model ID
flux-3-image-to-image
Point de terminaison
https://api.hermes-ai.net/api/v1/jobs
Full task API reference
# 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-image-to-image",
  "input": {
    "imageUrls": [
      "https://example.com/input.png"
    ],
    "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"

Paramètres d’entrée

Fields of Image to image (flux-3-image-to-image). Les champs inconnus sont rejetés avec INVALID_MODEL_INPUT.

ChampTypeObligatoirePar défautValeurs autorisées et contraintes
imageUrls
string[]obligatoire—

Reference images, 1-10. One for single-image edit; multiple are referenced as Image 1 / Image 2 in order. Each image must be at most 16,777,216 pixels (about 4096x4096; total pixels, not side length), otherwise it is rejected.

≤ 10 items, HTTPS image URL or media:<uuid>

prompt
stringobligatoire—

Scene description or edit instruction. No negative prompt; a bbox JSON array may be appended for layout or local edits.

1–20000 chars

aspectRatio
stringfacultatif"auto"

Output aspect ratio. auto follows the first reference image when editing, or the prompt for text-to-image.

Parmi: "auto", "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"

resolution
stringobligatoire"1k"

Resolution tier, decides the price. 768sq ~768x768, 1k ~1MP, 1.5k ~2MP, 2k ~4MP, 4k ~16MP.

Parmi: "768sq", "1k", "1.5k", "2k", "4k"

grounding
booleanfacultatiftrue

Allow web or image search before generation. On by default.

safetyTolerance
integerfacultatif2

Moderation tolerance, 0 strictest to 4, default 2.

0–4

Importez d’abord un fichier local

Remplacez l’URL d’exemple par la référence média renvoyée.

POST /api/v1/media
curl -X POST https://api.hermes-ai.net/api/v1/media \
  -H "Authorization: Bearer $HERMES_API_KEY" \
  -H "Content-Type: image/png" \
  --data-binary @input.png
# → { "reference": "media:<uuid>", ... }  Use the reference in an image, video or audio field.
Headers, response, task statuses and errors
En-têteValeurRemarques
AuthorizationBearer <API key>Ou envoyez la clé dans x-api-key.
Content-Typeapplication/json
Idempotency-Key<unique string ≤128>Obligatoire. Ne le réutilisez que pour retenter la même requête.
ChampTypeRemarques
idstringID de tâche Hermes AI. Utilisez-le pour interroger.
modelstringSlug du modèle.
statusstringVoir les statuts de tâche.
errorCodestring | nullDéfini lorsqu’une tâche échoue ou doit être examinée.
priceMicrosintegerDevis fixé à l’admission, en micro-unités USD.
currency"USD"
createdAt / updatedAtstringHorodatages ISO 8601.
assets[]array{ id, type, url?, text? }. url est un lien /api/v1/results/<uuid> de même origine.
replayedbooleanSoumission uniquement. true lorsqu’une nouvelle tentative idempotente correspond.
StatutFinalSignification
queuednonAcceptée, en attente d’un worker.
submittingnonEn cours d’envoi au fournisseur du modèle.
runningnonLe modèle est en cours de génération.
succeededouiTerminée. Les résultats sont dans assets.
failedouiTerminée sans résultat. La réservation est libérée.
reconciliation_requiredouiThe result is being verified. Keep the task ID and do not resubmit automatically.
HTTPCodeSignification et action
401AUTH_REQUIREDClé d’API ou session manquante ou invalide.
403INSUFFICIENT_SCOPELa clé d’API n’a pas la portée requise par ce point de terminaison.
403PERMISSION_DENIEDCet identifiant ne peut pas effectuer cette opération.
429API_KEY_RATE_LIMITEDLa limite de débit de la clé d’API est atteinte. Respectez Retry-After.
429API_KEY_USAGE_EXCEEDEDLa clé d’API a atteint sa limite d’utilisation. Créez une nouvelle clé.
400INVALID_REQUESTLe corps n’est pas un objet JSON ou une valeur obligatoire manque.
400INVALID_IDEMPOTENCY_KEYIdempotency-Key doit comporter de 1 à 128 caractères ASCII imprimables.
400INVALID_MODEL_INPUTinput ne correspond pas au schéma du modèle (champ inconnu, champ obligatoire manquant ou valeur invalide).
400 / 413INPUT_TOO_LARGELe corps de la requête dépasse 256 Ko. Importez d’abord les médias et envoyez une référence média.
404REQUEST_NOT_FOUNDNo chat request with this ID belongs to your account.
404MODEL_NOT_FOUNDAucun modèle n’a ce slug.
404JOB_NOT_FOUNDAucune tâche avec cet ID n’appartient à votre compte.
409IDEMPOTENCY_CONFLICTCette Idempotency-Key a été utilisée avec une autre entrée. Utilisez une nouvelle clé pour une nouvelle requête.
409PRICE_CHANGEDLe prix diffère de expectedPriceMicros. Récupérez le prix et confirmez à nouveau.
409MODEL_PRICE_UNAVAILABLEAucun prix n’est encore configuré pour ce modèle ; il ne peut donc pas s’exécuter.
409PAYMENT_REVIEW_REQUIREDA refund left an uncovered balance. Contact support or cover the balance before submitting tasks.
409INSUFFICIENT_CREDITSLes crédits disponibles ne couvrent pas le prix de la tâche.
429RATE_LIMITEDTrop de soumissions de tâches par minute. Réessayez plus tard.
429EXPORT_RATE_LIMITEDToo many CSV exports this minute. Honor Retry-After.
429CONCURRENCY_LIMITEDTrop de tâches inachevées. Attendez qu’une tâche se termine.
503EXECUTION_UNAVAILABLEL’exécution n’est pas configurée pour ce modèle actuellement.
429UPSTREAM_RATE_LIMITEDThe model provider is rate limiting chat requests. Retry with backoff; nothing was charged.
502UPSTREAM_ERRORThe model provider failed the chat request. Nothing was charged; retry later.
503PLATFORM_BUDGET_EXCEEDEDThis model is temporarily unavailable. Try again later.
503EXECUTION_TEMPORARILY_UNAVAILABLEL’exécution est temporairement indisponible. Réessayez avec la même Idempotency-Key.
503AUTH_UNAVAILABLEL’authentification est temporairement indisponible. Réessayez plus tard.
503API_UNAVAILABLEL’API est temporairement indisponible. Réessayez plus tard.

FAQ de l’API FLUX 3

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?

FLUX 3 by Black Forest Labs handles texte vers image et la image vers image. The catalog lists 4 variants, each with its own model ID and input schema. Check the current availability before sending a request.

Which durations, resolutions and aspect ratios does FLUX 3 support?

Across its variants, FLUX 3 supports 768sq, 1K, 1.5K, 2K et la 4K resolution et la 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 et la 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 image 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. Les champs inconnus sont rejetés avec 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 text to image, Text to image et la Klein text to image differ in fields: Text to image adds grounding; Klein text to image adds seed, steps, outputFormat; for image to image, Image to image et la Klein image to image differ in fields: Image to image 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.