QwenImage modelComprobando
Qwen Image 3.0 API
qwen-image-3-0-pro-image-editQwen Image 3.0 and Pro for image generation and edits with optional thinking controls.
- Text to image
- Image to image
- Up to 3 input images
- Up to 6 images per request
Ejecuta Qwen Image 3.0 en el 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.
Parámetros
modelQwen Image 3.0Pro image editqwen-image-3-0-pro-image-edit
Avanzado (4)
input.negativePromptNegative prompt describing unwanted content. ≤ 600 chars
input.promptExtendWhether to enable intelligent prompt rewriting. Enabled by default; improves results for short editing instructions.
input.enableThinkingEnable thinking mode for prompt rewriting. On by default: better quality, slower. Turn off to cut rewrite time to about 20s. Only takes effect when promptExtend=true. Supported for Direct I2I; not supported when promptExtendMode=agent.
input.seedRandom seed in [0, 2147483647]. Fixing the seed reproduces results; leave empty for random. 0–2147483647
Los créditos se reservan al aceptar una tarea y solo se cobran si tiene éxito. Las tareas fallidas liberan la reserva; los resultados sin confirmar siguen reservados hasta verificarse.
Vista previa de la solicitud
{"model": "qwen-image-3-0-pro-image-edit","input": {"imageNum": 1,"promptExtend": true,"promptExtendMode": "direct","enableThinking": true}}El playground web envía este cuerpo con tu sesión iniciada. Desde código, envía el mismo cuerpo con una clave de API.
Resultado
Run the request and the result appears here, with its status and cost.
Precios de Qwen Image 3.0
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 retriesLos reintentos idempotentes con la misma clave no generan un segundo cargo.
- Price changesEnvía expectedPriceMicros para rechazar la tarea con PRICE_CHANGED si el precio cambió después de mostrarlo.
Compara las variantes de Qwen Image 3.0
Each variant has its own model ID and input schema. Pick the task first, then the tier. Additional fields are shown when variants differ.
Pro text to imagePredeterminado
qwen-image-3-0-pro-text-to-imageText to image; Texto
qwen-image-3-0-pro-image-editImage to image; Texto, imagen
qwen-image-3-0-image-editImage to image; Texto, imagen
qwen-image-3-0-text-to-imageText to image; Texto
| Variant | Tarea | Entrada |
|---|---|---|
Pro text to imagePredeterminadoqwen-image-3-0-pro-text-to-image | Text to image | Texto |
Pro image editqwen-image-3-0-pro-image-edit | Image to image | Texto, imagen |
Image editqwen-image-3-0-image-edit | Image to image | Texto, imagen |
Text to imageqwen-image-3-0-text-to-image | Text to image | Texto |
Qué puede hacer Qwen Image 3.0
The Qwen team introduces Qwen Image 3.0 with a focus on rich layouts, realistic detail and multilingual text. These are manufacturer descriptions, not guarantees of exact text or visual accuracy; review outputs for your use case.
Hermes lists Standard and Pro text-to-image and image-editing variants. The edit schemas accept up to three reference images. The schemas also list an optional thinking control, prompt-extension settings and a seed. Check the current status, allowed inputs and price for the selected model before running.
Capacidades
Up to 3 input images
Send up to 3 images in one request as HTTPS URLs or uploaded media references.
imageUrlsVariantes: Pro image edit, Image edit
Up to 6 images per request
Ask for several results in one task.
imageNumEvery variant
Negative prompt
Describe what to keep out of the result.
negativePromptEvery variant
Seed
Accepts a seed value.
seedEvery variant
Casos de uso
Explore complex compositions
Describe a layout and its visual hierarchy in a text prompt.
Revise an existing design
Provide references and describe what should be preserved or changed.
Iterate on typography
Specify the desired text and verify spelling and legibility in the result.
Llama a Qwen Image 3.0 desde código
Every image, video and music model uses the same asynchronous job API: submit a task, then poll for the result.
- 1
Crea una clave de API
In the dashboard, with the jobs:create and jobs:read scopes. Claves de API - 2
Enviar una tarea
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.
Solicitud mínima
Required fields only, generated from the schema of Pro image edit. Set HERMES_API_KEY in your environment.
- Model ID
qwen-image-3-0-pro-image-edit- Endpoint
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": "qwen-image-3-0-pro-image-edit",
"input": {
"imageUrls": [
"https://example.com/input.png"
],
"prompt": "A lighthouse on a rocky coast at sunrise, soft light"
}
}'
# 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"Parámetros de entrada
Fields of Pro image edit (qwen-image-3-0-pro-image-edit). Los campos desconocidos se rechazan con INVALID_MODEL_INPUT.
| Campo | Tipo | Obligatorio | Predeterminado | Valores permitidos y restricciones |
|---|---|---|---|---|
imageUrls | string[] | obligatorio | — | Input images (1-3), ordered by array position. Public URLs, OSS temporary URLs, and Base64 are supported. Recommended size: 384-2048px, max 10MB per image. ≤ 3 items, HTTPS image URL or media:<uuid> |
prompt | string | obligatorio | — | Image editing instruction describing what to preserve, replace, redraw, or enhance. Chinese and English are supported. ≤ 3000 chars |
negativePrompt | string | opcional | — | Negative prompt describing unwanted content. ≤ 600 chars |
size | string | opcional | — | Output resolution as width*height. Total pixels must be within 512*512 to 2048*2048. Labels 1k/2k denote resolution tier. Leave empty to let the model choose from the prompt. Uno de: 262144–4194304 pixels; width*height, Aspect ratio 1:8–8:1 |
imageNum | integer | opcional | 1 | Number of images generated per request. Defaults to 1. Uno de: |
promptExtend | boolean | opcional | true | Whether to enable intelligent prompt rewriting. Enabled by default; improves results for short editing instructions. |
promptExtendMode | string | opcional | "direct" | Prompt rewriting mode, effective only when promptExtend is enabled. Use direct for direct rewriting or agent for agent-based rewriting. Uno de: |
enableThinking | boolean | opcional | true | Enable thinking mode for prompt rewriting. On by default: better quality, slower. Turn off to cut rewrite time to about 20s. Only takes effect when promptExtend=true. Supported for Direct I2I; not supported when promptExtendMode=agent. |
seed | integer | opcional | — | Random seed in [0, 2147483647]. Fixing the seed reproduces results; leave empty for random. 0–2147483647 |
Sube primero un archivo local
Sustituye la URL de ejemplo por la referencia multimedia devuelta.
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
| Encabezado | Valor | Notas |
|---|---|---|
Authorization | Bearer <API key> | O envía la clave en x-api-key. |
Content-Type | application/json | |
Idempotency-Key | <unique string ≤128> | Obligatorio. Reutilízalo solo para reintentar la misma solicitud. |
| Campo | Tipo | Notas |
|---|---|---|
id | string | ID de tarea de Hermes AI. Úsalo para consultar. |
model | string | Slug del modelo. |
status | string | Consulta los estados de la tarea. |
errorCode | string | null | Se establece cuando una tarea falla o requiere revisión. |
priceMicros | integer | Cotización fijada al aceptarla, en micro-unidades de USD. |
currency | "USD" | |
createdAt / updatedAt | string | Marcas de tiempo ISO 8601. |
assets[] | array | { id, type, url?, text? }. url es un enlace /api/v1/results/<uuid> del mismo origen. |
replayed | boolean | Solo al enviar. true cuando coincide un reintento idempotente. |
| Estado | Final | Significado |
|---|---|---|
queued | no | Aceptada y a la espera de un trabajador. |
submitting | no | Enviándose al proveedor del modelo. |
running | no | El modelo está generando. |
succeeded | sí | Terminada. Los resultados están en assets. |
failed | sí | Terminada sin resultado. La reserva se libera. |
reconciliation_required | sí | The result is being verified. Keep the task ID and do not resubmit automatically. |
| HTTP | Código | Significado y acción |
|---|---|---|
401 | AUTH_REQUIRED | Falta la clave de API o la sesión, o no es válida. |
403 | INSUFFICIENT_SCOPE | La clave de API no tiene el permiso que necesita este endpoint. |
403 | PERMISSION_DENIED | Esta credencial no puede realizar la operación. |
429 | API_KEY_RATE_LIMITED | Se alcanzó el límite de frecuencia de la clave de API. Respeta Retry-After. |
429 | API_KEY_USAGE_EXCEEDED | La clave de API alcanzó su límite de uso. Crea una clave nueva. |
400 | INVALID_REQUEST | El cuerpo no es un objeto JSON o falta un valor obligatorio. |
400 | INVALID_IDEMPOTENCY_KEY | Idempotency-Key debe tener entre 1 y 128 caracteres ASCII imprimibles. |
400 | INVALID_MODEL_INPUT | input no coincide con el esquema del modelo (campo desconocido, campo obligatorio ausente o valor no válido). |
400 / 413 | INPUT_TOO_LARGE | El cuerpo de la solicitud supera los 256 KB. Sube primero los archivos multimedia y envía una referencia. |
404 | REQUEST_NOT_FOUND | No chat request with this ID belongs to your account. |
404 | MODEL_NOT_FOUND | Ningún modelo tiene este slug. |
404 | JOB_NOT_FOUND | Ninguna tarea con este ID pertenece a tu cuenta. |
409 | IDEMPOTENCY_CONFLICT | Esta Idempotency-Key se usó con otra entrada. Usa una clave nueva para una solicitud nueva. |
409 | PRICE_CHANGED | El precio difiere de expectedPriceMicros. Obtén el precio y vuelve a confirmarlo. |
409 | MODEL_PRICE_UNAVAILABLE | Este modelo aún no tiene precio configurado, por lo que no puede ejecutarse. |
409 | PAYMENT_REVIEW_REQUIRED | A refund left an uncovered balance. Contact support or cover the balance before submitting tasks. |
409 | INSUFFICIENT_CREDITS | Los créditos disponibles no cubren el precio de la tarea. |
429 | RATE_LIMITED | Demasiados envíos de tareas por minuto. Vuelve a intentarlo más tarde. |
429 | EXPORT_RATE_LIMITED | Too many CSV exports this minute. Honor Retry-After. |
429 | CONCURRENCY_LIMITED | Demasiadas tareas sin terminar. Espera a que termine alguna. |
503 | EXECUTION_UNAVAILABLE | La ejecución no está configurada para este modelo en este momento. |
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 | La ejecución no está disponible temporalmente. Reintenta con la misma Idempotency-Key. |
503 | AUTH_UNAVAILABLE | La autenticación no está disponible temporalmente. Vuelve a intentarlo más tarde. |
503 | API_UNAVAILABLE | La API no está disponible temporalmente. Vuelve a intentarlo más tarde. |
Preguntas frecuentes sobre la API de Qwen Image 3.0
Answers built from the model's schema and the Hermes AI API contract.
Can I control thinking in the request?
The Hermes schemas list enableThinking. Check the selected variant's allowed values and price before using it; the exact effect depends on the upstream model.
What can the Qwen Image 3.0 API do?
Qwen Image 3.0 by Qwen handles texto a imagen y imagen a imagen. The catalog lists 4 variants, each with its own model ID and input schema. Check the current availability before sending a request.
What input does Qwen Image 3.0 accept?
A text prompt of up to 3,000 characters, plus imagen input (up to 3 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. Los campos desconocidos se rechazan con INVALID_MODEL_INPUT.
How is Qwen Image 3.0 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 Qwen Image 3.0 variant should I choose?
For text to image, Pro text to image y Text to image take the same input fields and differ in tier and price; for image to image, Pro image edit y Image edit take the same input fields and differ in tier and price. Pick the task first, then compare the tiers in the variants table.
How do I call the Qwen Image 3.0 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 Qwen Image 3.0 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.