happyhorse-1.0-official

Happy Horse 1.0 Official Channel — direct first-party Aliyun Model Studio routing with ReAPI's URL-only media contract.

Happy Horse 1.0 Official Channel — direct first-party routing, distinct from the standard happyhorse-1.0 channel. It uses the official Aliyun Model Studio SKUs behind one ReAPI model id and keeps ReAPI's URL-only media contract.

Official channel, ReAPI boundary. The upstream provider is Aliyun Model Studio first-party. Media inputs must still be public http(s) URLs; base64/data URI media is not accepted by ReAPI even where upstream docs show base64 examples.

Watermark policy is also a ReAPI override: Aliyun's official default is true, but ReAPI defaults watermark to false. Send "watermark": true if you want the upstream watermark.

Quick example

curl https://reapi.ai/api/v1/videos/generations \
  -H "Authorization: Bearer rk_live_xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "happyhorse-1.0-official",
    "prompt": "A coastal road at sunset, slow-motion camera push-in, cinematic feel",
    "resolution": "1080P",
    "size": "4:5",
    "duration": 5,
    "seed": 42
  }'

import requests

resp = requests.post(
    "https://reapi.ai/api/v1/videos/generations",
    headers={
        "Authorization": "Bearer rk_live_xxx",
        "Content-Type": "application/json",
    },
    json={
        "model": "happyhorse-1.0-official",
        "prompt": "A coastal road at sunset, slow-motion camera push-in",
        "resolution": "1080P",
        "size": "4:5",
        "duration": 5,
        "seed": 42,
    },
    timeout=30,
)
print(resp.json())

const r = await fetch("https://reapi.ai/api/v1/videos/generations", {
  method: "POST",
  headers: {
    Authorization: "Bearer rk_live_xxx",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "happyhorse-1.0-official",
    prompt: "A coastal road at sunset, slow-motion camera push-in",
    resolution: "1080P",
    size: "4:5",
    duration: 5,
    seed: 42,
  }),
});
console.log(await r.json());

package main

import (
    "bytes"
    "encoding/json"
    "fmt"
    "io"
    "net/http"
)

func main() {
    body, _ := json.Marshal(map[string]any{
        "model":      "happyhorse-1.0-official",
        "prompt":     "A coastal road at sunset, slow-motion camera push-in",
        "resolution": "1080P",
        "size":       "4:5",
        "duration":   5,
        "seed":       42,
    })
    req, _ := http.NewRequest("POST",
        "https://reapi.ai/api/v1/videos/generations", bytes.NewReader(body))
    req.Header.Set("Authorization", "Bearer rk_live_xxx")
    req.Header.Set("Content-Type", "application/json")

    resp, _ := http.DefaultClient.Do(req)
    defer resp.Body.Close()
    out, _ := io.ReadAll(resp.Body)
    fmt.Println(string(out))
}

Request surface

The public endpoint and async response envelope are the same as the standard channel:

POST /api/v1/videos/generations

One model id auto-routes by request shape:

Shape	Official upstream SKU
`prompt` only	`happyhorse-1.0-t2v`
`first_frame_image` (+ optional `prompt`)	`happyhorse-1.0-i2v`
`image_urls` 1-9 + `prompt`	`happyhorse-1.0-r2v`
`video_url` (+ optional `image_urls` 0-5) + `prompt`	`happyhorse-1.0-video-edit`

first_frame_image, image_urls, and video_url are mutually exclusive except for the legal EDIT combination: video_url + image_urls.

Official-channel constraints

Field	Official channel behavior
`model`	Must be `"happyhorse-1.0-official"`
`prompt`	Required for T2V / R2V / EDIT, optional for I2V. Aliyun truncates over-length prompt text upstream; ReAPI does not reject official-channel prompts at the standard-channel 2500-character cap.
`first_frame_image`	Public `http(s)` URL only. Base64/data URI is rejected by ReAPI.
`image_urls`	Public `http(s)` URLs only. R2V accepts 1-9 images; EDIT accepts 0-5 reference images.
`video_url`	Public `http(s)` URL only. EDIT source video must be 3-60 seconds, long side ≤2160 px, short side ≥320 px, and aspect ratio between 1:2.5 and 2.5:1. Aliyun also enforces file size ≤100 MB and fps >8.
`resolution`	`"720P"` or `"1080P"`; omitted lets upstream apply its default.
`size`	T2V/R2V ratio: `"16:9"`, `"9:16"`, `"1:1"`, `"4:3"`, `"3:4"`, `"4:5"`, `"5:4"`. Ignored for I2V and EDIT because output shape follows the source media.
`duration`	3-15 seconds for T2V/I2V/R2V. Ignored for EDIT because output length follows the source video.
`watermark`	ReAPI default is `false` even though Aliyun's official default is `true`. Explicit `true` / `false` is honored.
`seed`	Integer from 0 to 2147483647.
`audio_setting`	EDIT only: `"auto"` or `"origin"`.

Differences from `happyhorse-1.0`

Aspect	`happyhorse-1.0`	`happyhorse-1.0-official`
Upstream channel	Standard	Aliyun Model Studio official
Wire `model` value	`"happyhorse-1.0"`	`"happyhorse-1.0-official"`
T2V/R2V ratios	`16:9`, `9:16`, `1:1`, `4:3`, `3:4`	Adds `4:5` and `5:4`
Prompt cap	ReAPI rejects above 2500 chars	Aliyun truncation semantics; no local 2500-char reject
EDIT video dimensions	Standard channel validation rules	Official Aliyun validation rules
Default watermark	ReAPI default `false`	ReAPI default `false` (intentional override from Aliyun default `true`)
Per-second rate	Baseline	10% off the baseline
Validation error prefix	`happyhorse:`	`happyhorse-official:`

Pricing

Per-second × resolution. 10% off the standard channel at every supported resolution. See current 720P / 1080P / 4K rates on the Happy Horse model page.

Bill formula (1 credit = $0.001):

Mode	Billable seconds
T2V / I2V / R2V	`duration` you sent (default 5)
EDIT	`ceil(probed_source_seconds) + min(ceil(probed_source_seconds), 15)` — vendor processes the source AND produces a capped output; both sides are billable. Failed probe → `400 PRICING_UNAVAILABLE`, no charge.

Final bill: ceil(per_second_usd_after_discount × billable_seconds × 1000) credits. Failed jobs refund automatically.

Examples

Source video	Mode	Billable seconds
—	T2V, `duration=5`	5
—	T2V, `duration=10`	10
5s clip	EDIT	5 + min(5, 15) = 10
8.3s clip	EDIT	9 + min(9, 15) = 18
60s clip	EDIT	60 + min(60, 15) = 75
20s clip	EDIT	20 + min(20, 15) = 35

Apply ceil(per_second_usd_after_discount × billable_seconds × 1000) for the credit charge.

Validation errors

The response envelope and numeric error-code system match the standard channel, but official-channel validation follows the official Aliyun rules listed above. Error messages from this channel use the happyhorse-official: prefix.

Pattern-match on the numeric code, not the message string.

When to pick which channel

Need	Channel
Lowest unit price	`happyhorse-1.0-official`
Official Aliyun Model Studio route	`happyhorse-1.0-official`
`size` values `4:5` or `5:4`	`happyhorse-1.0-official`
Existing integration with no migration	`happyhorse-1.0`
Standard channel route / existing constraints	`happyhorse-1.0`

Switching channels = changing the model string in your request body. The response envelope and polling flow are shared; provider-specific validation and pricing differ as documented above.

Watermark policy is also a ReAPI override: Aliyun's official default is true, but ReAPI defaults watermark to false. Send "watermark": true if you want the upstream watermark.

Quick example

curl https://reapi.ai/api/v1/videos/generations \
  -H "Authorization: Bearer rk_live_xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "happyhorse-1.0-official",
    "prompt": "A coastal road at sunset, slow-motion camera push-in, cinematic feel",
    "resolution": "1080P",
    "size": "4:5",
    "duration": 5,
    "seed": 42
  }'

import requests

resp = requests.post(
    "https://reapi.ai/api/v1/videos/generations",
    headers={
        "Authorization": "Bearer rk_live_xxx",
        "Content-Type": "application/json",
    },
    json={
        "model": "happyhorse-1.0-official",
        "prompt": "A coastal road at sunset, slow-motion camera push-in",
        "resolution": "1080P",
        "size": "4:5",
        "duration": 5,
        "seed": 42,
    },
    timeout=30,
)
print(resp.json())

const r = await fetch("https://reapi.ai/api/v1/videos/generations", {
  method: "POST",
  headers: {
    Authorization: "Bearer rk_live_xxx",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "happyhorse-1.0-official",
    prompt: "A coastal road at sunset, slow-motion camera push-in",
    resolution: "1080P",
    size: "4:5",
    duration: 5,
    seed: 42,
  }),
});
console.log(await r.json());

package main

import (
    "bytes"
    "encoding/json"
    "fmt"
    "io"
    "net/http"
)

func main() {
    body, _ := json.Marshal(map[string]any{
        "model":      "happyhorse-1.0-official",
        "prompt":     "A coastal road at sunset, slow-motion camera push-in",
        "resolution": "1080P",
        "size":       "4:5",
        "duration":   5,
        "seed":       42,
    })
    req, _ := http.NewRequest("POST",
        "https://reapi.ai/api/v1/videos/generations", bytes.NewReader(body))
    req.Header.Set("Authorization", "Bearer rk_live_xxx")
    req.Header.Set("Content-Type", "application/json")

    resp, _ := http.DefaultClient.Do(req)
    defer resp.Body.Close()
    out, _ := io.ReadAll(resp.Body)
    fmt.Println(string(out))
}

Request surface

The public endpoint and async response envelope are the same as the standard channel:

POST /api/v1/videos/generations

One model id auto-routes by request shape:

Shape	Official upstream SKU
`prompt` only	`happyhorse-1.0-t2v`
`first_frame_image` (+ optional `prompt`)	`happyhorse-1.0-i2v`
`image_urls` 1-9 + `prompt`	`happyhorse-1.0-r2v`
`video_url` (+ optional `image_urls` 0-5) + `prompt`	`happyhorse-1.0-video-edit`

first_frame_image, image_urls, and video_url are mutually exclusive except for the legal EDIT combination: video_url + image_urls.

Official-channel constraints

Field	Official channel behavior
`model`	Must be `"happyhorse-1.0-official"`
`prompt`	Required for T2V / R2V / EDIT, optional for I2V. Aliyun truncates over-length prompt text upstream; ReAPI does not reject official-channel prompts at the standard-channel 2500-character cap.
`first_frame_image`	Public `http(s)` URL only. Base64/data URI is rejected by ReAPI.
`image_urls`	Public `http(s)` URLs only. R2V accepts 1-9 images; EDIT accepts 0-5 reference images.
`video_url`	Public `http(s)` URL only. EDIT source video must be 3-60 seconds, long side ≤2160 px, short side ≥320 px, and aspect ratio between 1:2.5 and 2.5:1. Aliyun also enforces file size ≤100 MB and fps >8.
`resolution`	`"720P"` or `"1080P"`; omitted lets upstream apply its default.
`size`	T2V/R2V ratio: `"16:9"`, `"9:16"`, `"1:1"`, `"4:3"`, `"3:4"`, `"4:5"`, `"5:4"`. Ignored for I2V and EDIT because output shape follows the source media.
`duration`	3-15 seconds for T2V/I2V/R2V. Ignored for EDIT because output length follows the source video.
`watermark`	ReAPI default is `false` even though Aliyun's official default is `true`. Explicit `true` / `false` is honored.
`seed`	Integer from 0 to 2147483647.
`audio_setting`	EDIT only: `"auto"` or `"origin"`.

Differences from `happyhorse-1.0`

Aspect	`happyhorse-1.0`	`happyhorse-1.0-official`
Upstream channel	Standard	Aliyun Model Studio official
Wire `model` value	`"happyhorse-1.0"`	`"happyhorse-1.0-official"`
T2V/R2V ratios	`16:9`, `9:16`, `1:1`, `4:3`, `3:4`	Adds `4:5` and `5:4`
Prompt cap	ReAPI rejects above 2500 chars	Aliyun truncation semantics; no local 2500-char reject
EDIT video dimensions	Standard channel validation rules	Official Aliyun validation rules
Default watermark	ReAPI default `false`	ReAPI default `false` (intentional override from Aliyun default `true`)
Per-second rate	Baseline	10% off the baseline
Validation error prefix	`happyhorse:`	`happyhorse-official:`

Pricing

Per-second × resolution. 10% off the standard channel at every supported resolution. See current 720P / 1080P / 4K rates on the Happy Horse model page.

Bill formula (1 credit = $0.001):

Mode	Billable seconds
T2V / I2V / R2V	`duration` you sent (default 5)
EDIT	`ceil(probed_source_seconds) + min(ceil(probed_source_seconds), 15)` — vendor processes the source AND produces a capped output; both sides are billable. Failed probe → `400 PRICING_UNAVAILABLE`, no charge.

Final bill: ceil(per_second_usd_after_discount × billable_seconds × 1000) credits. Failed jobs refund automatically.

Examples

Source video	Mode	Billable seconds
—	T2V, `duration=5`	5
—	T2V, `duration=10`	10
5s clip	EDIT	5 + min(5, 15) = 10
8.3s clip	EDIT	9 + min(9, 15) = 18
60s clip	EDIT	60 + min(60, 15) = 75
20s clip	EDIT	20 + min(20, 15) = 35

Apply ceil(per_second_usd_after_discount × billable_seconds × 1000) for the credit charge.

Validation errors

Pattern-match on the numeric code, not the message string.

When to pick which channel

Need	Channel
Lowest unit price	`happyhorse-1.0-official`
Official Aliyun Model Studio route	`happyhorse-1.0-official`
`size` values `4:5` or `5:4`	`happyhorse-1.0-official`
Existing integration with no migration	`happyhorse-1.0`
Standard channel route / existing constraints	`happyhorse-1.0`

Switching channels = changing the model string in your request body. The response envelope and polling flow are shared; provider-specific validation and pricing differ as documented above.

happyhorse-1.0-official

Quick example

Request surface

Official-channel constraints

Differences from `happyhorse-1.0`

Pricing

Examples

Validation errors

When to pick which channel

Table of Contents

happyhorse-1.0-official

Quick example

Request surface

Official-channel constraints

Differences from `happyhorse-1.0`

Pricing

Examples

Validation errors

When to pick which channel

Table of Contents