QwenImage modelChecking
Qwen Image 3.0 API
qwen-image-3-0-text-to-imageQwen 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
Run Qwen Image 3.0 in the 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.
Parameters
modelQwen Image 3.0Text to imageqwen-image-3-0-text-to-image
Advanced (4)
input.negativePromptNegative prompt describing unwanted content. ≤ 600 chars
input.promptExtendWhether to enable intelligent prompt rewriting. Enabled by default; improves results for short prompts.
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 T2I and Agent T2I.
input.seedRandom seed in [0, 2147483647]. Fixing the seed reproduces results; leave empty for random. 0–2147483647
Credits are reserved when a task is accepted and charged only on success. Failed tasks release the reservation; unconfirmed outcomes remain reserved until verified.
Request preview
{"model": "qwen-image-3-0-text-to-image","input": {"imageNum": 1,"promptExtend": true,"promptExtendMode": "direct","enableThinking": true}}The web playground sends this body with your signed-in session. From code, send the same body with an API key.
Result
Run the request and the result appears here, with its status and cost.
Qwen Image 3.0 pricing
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 retriesIdempotent retries with the same key do not create a second charge.
- Price changesSend expectedPriceMicros to reject the task with PRICE_CHANGED if the price changed after you displayed it.
Compare Qwen Image 3.0 variants
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 imageDefault
qwen-image-3-0-pro-text-to-imageText to image; Text
qwen-image-3-0-pro-image-editImage to image; Text, image
qwen-image-3-0-image-editImage to image; Text, image
qwen-image-3-0-text-to-imageText to image; Text
| Variant | Task | Input |
|---|---|---|
Pro text to imageDefaultqwen-image-3-0-pro-text-to-image | Text to image | Text |
Pro image editqwen-image-3-0-pro-image-edit | Image to image | Text, image |
Image editqwen-image-3-0-image-edit | Image to image | Text, image |
Text to imageqwen-image-3-0-text-to-image | Text to image | Text |
What Qwen Image 3.0 can do
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.
Capabilities
Up to 3 input images
Send up to 3 images in one request as HTTPS URLs or uploaded media references.
imageUrlsVariants: 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
Use cases
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.
Call Qwen Image 3.0 from code
Every image, video and music model uses the same asynchronous job API: submit a task, then poll for the result.
- 1
Create an API key
In the dashboard, with the jobs:create and jobs:read scopes. API keys - 2
Submit a task
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.
Minimal request
Required fields only, generated from the schema of Text to image. Set HERMES_API_KEY in your environment.
- Model ID
qwen-image-3-0-text-to-image- 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-text-to-image",
"input": {
"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"Input parameters
Fields of Text to image (qwen-image-3-0-text-to-image). Unknown fields are rejected with INVALID_MODEL_INPUT.
| Field | Type | Required | Default | Allowed values and constraints |
|---|---|---|---|---|
prompt | string | required | — | Positive prompt describing the desired image content, style, composition, and text rendering. Chinese and English are supported. ≤ 3000 chars |
negativePrompt | string | optional | — | Negative prompt describing unwanted content. ≤ 600 chars |
size | string | optional | — | Output resolution as width*height, from 262144 to 4194304 pixels, with aspect ratio between 1:8 and 8:1. Leave empty to let the model choose. One of: 262144–4194304 pixels; width*height, Aspect ratio 1:8–8:1 |
imageNum | integer | optional | 1 | Number of images generated per request. Defaults to 1. One of: |
promptExtend | boolean | optional | true | Whether to enable intelligent prompt rewriting. Enabled by default; improves results for short prompts. |
promptExtendMode | string | optional | "direct" | Prompt rewriting mode, effective only when promptExtend is enabled. Use direct for direct rewriting or agent for agent-based rewriting. One of: |
enableThinking | boolean | optional | 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 T2I and Agent T2I. |
seed | integer | optional | — | Random seed in [0, 2147483647]. Fixing the seed reproduces results; leave empty for random. 0–2147483647 |
Headers, response, task statuses and errors
| Header | Value | Notes |
|---|---|---|
Authorization | Bearer <API key> | Or send the key in x-api-key. |
Content-Type | application/json | |
Idempotency-Key | <unique string ≤128> | Required. Reuse it only to retry the identical request. |
| Field | Type | Notes |
|---|---|---|
id | string | Hermes AI task ID. Use it to poll. |
model | string | Model slug. |
status | string | See task statuses. |
errorCode | string | null | Set when a task fails or needs review. |
priceMicros | integer | Quote fixed at admission, USD micro-units. |
currency | "USD" | |
createdAt / updatedAt | string | ISO 8601 timestamps. |
assets[] | array | { id, type, url?, text? }. url is a same-origin /api/v1/results/<uuid> link. |
replayed | boolean | Submit only. true when an idempotent retry matched. |
| Status | Terminal | Meaning |
|---|---|---|
queued | no | Accepted and waiting for a worker. |
submitting | no | Being sent to the model provider. |
running | no | The model is generating. |
succeeded | yes | Finished. Results are in assets. |
failed | yes | Finished without a result. The hold is released. |
reconciliation_required | yes | The result is being verified. Keep the task ID and do not resubmit automatically. |
| HTTP | Code | Meaning and action |
|---|---|---|
401 | AUTH_REQUIRED | Missing or invalid API key or session. |
403 | INSUFFICIENT_SCOPE | The API key lacks the scope this endpoint needs. |
403 | PERMISSION_DENIED | This credential cannot perform the operation. |
429 | API_KEY_RATE_LIMITED | The API key's rate limit was reached. Honor Retry-After. |
429 | API_KEY_USAGE_EXCEEDED | The API key reached its usage limit. Create a new key. |
400 | INVALID_REQUEST | The body is not a JSON object or a required value is missing. |
400 | INVALID_IDEMPOTENCY_KEY | Idempotency-Key must be 1–128 printable ASCII characters. |
400 | INVALID_MODEL_INPUT | input does not match the model schema (unknown field, missing required field, or invalid value). |
400 / 413 | INPUT_TOO_LARGE | The request body is larger than 256 KB. Upload media first and send a media reference. |
404 | REQUEST_NOT_FOUND | No chat request with this ID belongs to your account. |
404 | MODEL_NOT_FOUND | No model has this slug. |
404 | JOB_NOT_FOUND | No task with this ID belongs to your account. |
409 | IDEMPOTENCY_CONFLICT | This Idempotency-Key was used with different input. Use a new key for a new request. |
409 | PRICE_CHANGED | The price differs from expectedPriceMicros. Fetch the price and confirm again. |
409 | MODEL_PRICE_UNAVAILABLE | No price is configured for this model yet, so it cannot run. |
409 | PAYMENT_REVIEW_REQUIRED | A refund left an uncovered balance. Contact support or cover the balance before submitting tasks. |
409 | INSUFFICIENT_CREDITS | Available credits do not cover the task price. |
429 | RATE_LIMITED | Too many task submissions per minute. Retry later. |
429 | EXPORT_RATE_LIMITED | Too many CSV exports this minute. Honor Retry-After. |
429 | CONCURRENCY_LIMITED | Too many unfinished tasks. Wait for one to finish. |
503 | EXECUTION_UNAVAILABLE | Execution is not configured for this model right now. |
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 | Execution is temporarily unavailable. Retry with the same Idempotency-Key. |
503 | AUTH_UNAVAILABLE | Authentication is temporarily unavailable. Retry later. |
503 | API_UNAVAILABLE | The API is temporarily unavailable. Retry later. |
Qwen Image 3.0 API FAQ
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 text to image and image to image. 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 image 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. Unknown fields are rejected with 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 and Text to image take the same input fields and differ in tier and price; for image to image, Pro image edit and 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.