AlibabaChecking

Wan 2.7 / Text to Video

wan-2-7-text-to-video

text to videoOutput: VideoInput: text + audio

Loading price…

Official list price · Not verified

Try in Playground Get API key

Parameters

Required

promptprompt: string

1–5000 chars

durationduration: string

resolutionresolution: string

aspectRatioaspectRatio: string

Aspect ratio

Common options

audioUrlaudioUrl: string

Drop an audio file here or click to uploadOne file

background music MP3 or WAV; maximum 15 MB. HTTPS audio URL or media:<uuid>

Advanced (3)

negativePromptnegativePrompt: string

0–500 chars

promptExtendpromptExtend: boolean

Whether to enable prompt intelligent rewriting. After activation, use the large model to intelligently rewrite the input prompt. For shorter prompt generation, the effect is significantly improved, but it will increase the time consumption.

seedseed: integer

Randomly select seeds with a value range of [0, 2147483647]. If not specified, the system will automatically generate random seeds. If you need to improve the reproducibility of the generated results, it is recommended to fix the seed value. Please note that due to the probabilistic nature of model generation, even with the same seed, it cannot be guaranteed that the results generated each time will be completely consistent 0–2147483647

Request preview

{
  "model": "wan-2-7-text-to-video",
  "input": {
    "duration": "5",
    "resolution": "720P",
    "aspectRatio": "16:9",
    "promptExtend": true
  }
}

The web playground sends this body with your signed-in session. From code, send the same body with an API key.

Estimated charge

Loading price…

Credits are reserved when a task is accepted and charged only on success. Failed tasks release the reservation; unconfirmed outcomes remain reserved until verified.

What it does

Generate video from text with optional audio.

2–15 seconds · 720p or 1080p

Input parameters

Only the fields this model accepts. Required fields must be provided.

Field	Type	Required	Default	Allowed values and constraints
`prompt`	`string`	required	—	1–5000 chars
`negativePrompt`	`string`	optional	—	0–500 chars
`audioUrl`	`string`	optional	—	background music MP3 or WAV; maximum 15 MB. HTTPS audio URL or media:<uuid>
`duration`	`string`	required	`"5"`	One of: `"2"`, `"3"`, `"4"`, `"5"`, `"6"`, `"7"`, `"8"`, `"9"`, `"10"`, `"11"`, `"12"`, `"13"`, `"14"`, `"15"`
`resolution`	`string`	required	`"720P"`	One of: `"720P"`, `"1080P"`
`aspectRatio`	`string`	required	`"16:9"`	Aspect ratio One of: `"16:9"`, `"9:16"`, `"1:1"`, `"4:3"`, `"3:4"`
`promptExtend`	`boolean`	optional	`true`	Whether to enable prompt intelligent rewriting. After activation, use the large model to intelligently rewrite the input prompt. For shorter prompt generation, the effect is significantly improved, but it will increase the time consumption.
`seed`	`integer`	optional	—	Randomly select seeds with a value range of [0, 2147483647]. If not specified, the system will automatically generate random seeds. If you need to improve the reproducibility of the generated results, it is recommended to fix the seed value. Please note that due to the probabilistic nature of model generation, even with the same seed, it cannot be guaranteed that the results generated each time will be completely consistent 0–2147483647

Limits and behaviour

Asynchronous only: submit a task, then poll for the result.
prompt: 1–5000 chars
negativePrompt: 0–500 chars
seed: 0–2147483647
Media inputs accept public HTTPS URLs or media:<uuid> references from POST /api/v1/media.

Endpoint

All models share one asynchronous job API. This model is selected by its slug.

Submit

POST https://api.hermes-ai.net/api/v1/jobs

{
  "model": "wan-2-7-text-to-video",
  "input": {
    "prompt": "A lighthouse on a rocky coast at sunrise, soft light",
    "duration": "5",
    "resolution": "720P",
    "aspectRatio": "16:9"
  }
}

Then poll GET /api/v1/jobs/{id} until the status is terminal.

Authentication

Send an API key with the jobs:create scope to submit and jobs:read to poll.

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.

Request body

Field	Type	Required	Notes
`model`	`string`	required	Model slug from the catalog.
`input`	`object`	required	Fields from the model's input schema.
`expectedPriceMicros`	`integer`	optional	Price you showed the user. A mismatch returns 409 PRICE_CHANGED before any charge.

input fields

Unknown fields are rejected with INVALID_MODEL_INPUT.

Field	Type	Required	Default	Allowed values and constraints
`prompt`	`string`	required	—	1–5000 chars
`negativePrompt`	`string`	optional	—	0–500 chars
`audioUrl`	`string`	optional	—	background music MP3 or WAV; maximum 15 MB. HTTPS audio URL or media:<uuid>
`duration`	`string`	required	`"5"`	One of: `"2"`, `"3"`, `"4"`, `"5"`, `"6"`, `"7"`, `"8"`, `"9"`, `"10"`, `"11"`, `"12"`, `"13"`, `"14"`, `"15"`
`resolution`	`string`	required	`"720P"`	One of: `"720P"`, `"1080P"`
`aspectRatio`	`string`	required	`"16:9"`	Aspect ratio One of: `"16:9"`, `"9:16"`, `"1:1"`, `"4:3"`, `"3:4"`
`promptExtend`	`boolean`	optional	`true`	Whether to enable prompt intelligent rewriting. After activation, use the large model to intelligently rewrite the input prompt. For shorter prompt generation, the effect is significantly improved, but it will increase the time consumption.
`seed`	`integer`	optional	—	Randomly select seeds with a value range of [0, 2147483647]. If not specified, the system will automatically generate random seeds. If you need to improve the reproducibility of the generated results, it is recommended to fix the seed value. Please note that due to the probabilistic nature of model generation, even with the same seed, it cannot be guaranteed that the results generated each time will be completely consistent 0–2147483647

Response

202 for a new task, 200 when an Idempotency-Key replay matches. GET /api/v1/jobs/{id} returns the same shape without replayed.

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.

Task statuses

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.

Errors

Every error body is { code, error }. Handle by code.

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`	`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.

Full API guide · OpenAPI 3.1

Hermes AI price

Loading price…

Official list price

Manufacturer standard API rates in USD, before channel discounts. Units and specifications follow the official source.

Official price not verified for this model.

What affects cost

Resolution, duration and output quantity can affect the quote. Review the rate card and the Playground quote before submitting.

· Only successful tasks are charged. Failed tasks release reserved credits; tasks with an unconfirmed outcome keep their reservation until the result is verified.
· Idempotent retries with the same key do not create a second charge.
· Send expectedPriceMicros to reject the task with PRICE_CHANGED if the price changed after you displayed it.

Estimate

Select the specifications in Playground to see the task quote.

// Billing

How billing works

Tasks use prepaid credits. Add credits on the Billing page; your balance updates after payment confirmation.

When	Effect
Task accepted	The quoted amount is reserved from your balance.
Task succeeded	The final amount is charged once and any unused reservation is returned.
Task failed	The reserved amount is returned to your available balance.

Tasks with an unconfirmed outcome keep their reserved credits until the result is verified. Keep the task ID and contact support if you need help.

Payment refunds are reflected in your balance and transaction history on the Billing page.

Minimal request

Required fields only, generated from this model's schema. Set HERMES_API_KEY in your environment.

# 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": "wan-2-7-text-to-video",
  "input": {
    "prompt": "A lighthouse on a rocky coast at sunrise, soft light",
    "duration": "5",
    "resolution": "720P",
    "aspectRatio": "16:9"
  }
}'

# 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"

With documented defaults

The same request with each optional default written out, so you can see what to change.

# 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": "wan-2-7-text-to-video",
  "input": {
    "prompt": "A lighthouse on a rocky coast at sunrise, soft light",
    "duration": "5",
    "resolution": "720P",
    "aspectRatio": "16:9",
    "promptExtend": true
  }
}'

# 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"

Upload a local file first

Replace the example URL with the returned media reference.

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.