GoogleImage modelVérification
Nano Banana 2.1 API
nano-banana-2-1-image-to-image-stableGoogle's Nano Banana 2.1 combines text and image inputs for image generation and editing, with attention to visual design and multi-reference workflows.
- Text to image
- Image to image
- Up to 14 input images
- 1K, 2K or 4K output
Lancez Nano Banana 2.1 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
modelNano Banana 2.1Image to imagenano-banana-2-1-image-to-image-stable
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": "nano-banana-2-1-image-to-image-stable","input": {"aspectRatio": "1:1","resolution": "1k","thinkingLevel": "medium"}}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 Nano Banana 2.1
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.
- 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 Nano Banana 2.1
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
nano-banana-2-1-text-to-image-stableText to image; Texte; 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-stableImage to image; Texte, image; 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-economyText to image; Texte; 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-economyImage to image; Texte, image; 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
| Variant | Tâche | Entrée | Resolution | Aspect ratios | Extra fields |
|---|---|---|---|---|---|
Text to imagePar défautnano-banana-2-1-text-to-image-stable | Text to image | Texte | 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 |
Image to imagenano-banana-2-1-image-to-image-stable | Image to image | Texte, image | 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 |
Text to imagenano-banana-2-1-text-to-image-economy | Text to image | Texte | 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 | — |
Image to imagenano-banana-2-1-image-to-image-economy | Image to image | Texte, image | 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 | — |
Ce que Nano Banana 2.1 sait faire
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.
Capacités
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.
imageUrlsVariantes: Image to image, Image to image
Cas d’usage
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.
Appelez Nano Banana 2.1 depuis votre code
Every image, video and music model uses the same asynchronous job API: submit a task, then poll for the result.
- 1
Créez une clé d’API
In the dashboard, with the jobs:create and jobs:read scopes. Clés d’API - 2
Soumettre une tâche
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.
Requête minimale
Required fields only, generated from the schema of Image to image. Set HERMES_API_KEY in your environment.
- Model ID
nano-banana-2-1-image-to-image-stable- Point de terminaison
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-image-to-image-stable",
"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 (nano-banana-2-1-image-to-image-stable). Les champs inconnus sont rejetés avec INVALID_MODEL_INPUT.
| Champ | Type | Obligatoire | Par défaut | Valeurs autorisées et contraintes |
|---|---|---|---|---|
imageUrls | string[] | obligatoire | — | ≤ 14 items, HTTPS image URL or media:<uuid> |
prompt | string | obligatoire | — | 1–20000 chars |
aspectRatio | string | facultatif | "1:1" | Parmi: |
resolution | string | obligatoire | "1k" | Parmi: |
thinkingLevel | string | facultatif | "medium" | Parmi: |
Importez d’abord un fichier local
Remplacez l’URL d’exemple par la référence média renvoyée.
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-tête | Valeur | Remarques |
|---|---|---|
Authorization | Bearer <API key> | Ou envoyez la clé dans x-api-key. |
Content-Type | application/json | |
Idempotency-Key | <unique string ≤128> | Obligatoire. Ne le réutilisez que pour retenter la même requête. |
| Champ | Type | Remarques |
|---|---|---|
id | string | ID de tâche Hermes AI. Utilisez-le pour interroger. |
model | string | Slug du modèle. |
status | string | Voir les statuts de tâche. |
errorCode | string | null | Défini lorsqu’une tâche échoue ou doit être examinée. |
priceMicros | integer | Devis fixé à l’admission, en micro-unités USD. |
currency | "USD" | |
createdAt / updatedAt | string | Horodatages ISO 8601. |
assets[] | array | { id, type, url?, text? }. url est un lien /api/v1/results/<uuid> de même origine. |
replayed | boolean | Soumission uniquement. true lorsqu’une nouvelle tentative idempotente correspond. |
| Statut | Final | Signification |
|---|---|---|
queued | non | Acceptée, en attente d’un worker. |
submitting | non | En cours d’envoi au fournisseur du modèle. |
running | non | Le modèle est en cours de génération. |
succeeded | oui | Terminée. Les résultats sont dans assets. |
failed | oui | Terminée sans résultat. La réservation est libérée. |
reconciliation_required | oui | The result is being verified. Keep the task ID and do not resubmit automatically. |
| HTTP | Code | Signification et action |
|---|---|---|
401 | AUTH_REQUIRED | Clé d’API ou session manquante ou invalide. |
403 | INSUFFICIENT_SCOPE | La clé d’API n’a pas la portée requise par ce point de terminaison. |
403 | PERMISSION_DENIED | Cet identifiant ne peut pas effectuer cette opération. |
429 | API_KEY_RATE_LIMITED | La limite de débit de la clé d’API est atteinte. Respectez Retry-After. |
429 | API_KEY_USAGE_EXCEEDED | La clé d’API a atteint sa limite d’utilisation. Créez une nouvelle clé. |
400 | INVALID_REQUEST | Le corps n’est pas un objet JSON ou une valeur obligatoire manque. |
400 | INVALID_IDEMPOTENCY_KEY | Idempotency-Key doit comporter de 1 à 128 caractères ASCII imprimables. |
400 | INVALID_MODEL_INPUT | input ne correspond pas au schéma du modèle (champ inconnu, champ obligatoire manquant ou valeur invalide). |
400 / 413 | INPUT_TOO_LARGE | Le corps de la requête dépasse 256 Ko. Importez d’abord les médias et envoyez une référence média. |
404 | REQUEST_NOT_FOUND | No chat request with this ID belongs to your account. |
404 | MODEL_NOT_FOUND | Aucun modèle n’a ce slug. |
404 | JOB_NOT_FOUND | Aucune tâche avec cet ID n’appartient à votre compte. |
409 | IDEMPOTENCY_CONFLICT | Cette Idempotency-Key a été utilisée avec une autre entrée. Utilisez une nouvelle clé pour une nouvelle requête. |
409 | PRICE_CHANGED | Le prix diffère de expectedPriceMicros. Récupérez le prix et confirmez à nouveau. |
409 | MODEL_PRICE_UNAVAILABLE | Aucun prix n’est encore configuré pour ce modèle ; il ne peut donc pas s’exécuter. |
409 | PAYMENT_REVIEW_REQUIRED | A refund left an uncovered balance. Contact support or cover the balance before submitting tasks. |
409 | INSUFFICIENT_CREDITS | Les crédits disponibles ne couvrent pas le prix de la tâche. |
429 | RATE_LIMITED | Trop de soumissions de tâches par minute. Réessayez plus tard. |
429 | EXPORT_RATE_LIMITED | Too many CSV exports this minute. Honor Retry-After. |
429 | CONCURRENCY_LIMITED | Trop de tâches inachevées. Attendez qu’une tâche se termine. |
503 | EXECUTION_UNAVAILABLE | L’exécution n’est pas configurée pour ce modèle actuellement. |
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 | This model is temporarily unavailable. Try again later. |
503 | EXECUTION_TEMPORARILY_UNAVAILABLE | L’exécution est temporairement indisponible. Réessayez avec la même Idempotency-Key. |
503 | AUTH_UNAVAILABLE | L’authentification est temporairement indisponible. Réessayez plus tard. |
503 | API_UNAVAILABLE | L’API est temporairement indisponible. Réessayez plus tard. |
FAQ de l’API Nano Banana 2.1
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?
Nano Banana 2.1 by Google 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 Nano Banana 2.1 support?
Across its variants, Nano Banana 2.1 supports 1K, 2K et la 4K resolution et la 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 et la 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 image 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. Les champs inconnus sont rejetés avec 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 text to image, Text to image et la Text to image differ in fields: Text to image adds thinkingLevel; for image to image, Image to image et la Image to image differ in fields: Image to image 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.