> ## Documentation Index
> Fetch the complete documentation index at: https://gccai.heqingsong.uk/llms.txt
> Use this file to discover all available pages before exploring further.
# FLUX 3 Video Generation
> - Asynchronous processing mode, returns a task ID for subsequent queries
- Unified entry: text-to-video / image-to-video / video continuation / draft two-step
- Output H.264 + AAC with synced audio, duration 5~20 seconds
- Resolution hd / fhd, seven aspect ratios
```bash cURL theme={null}
curl --request POST \
--url https://gccai.heqingsong.uk/v1/videos/generations \
--header 'Authorization: Bearer ' \
--header 'Content-Type: application/json' \
--data '{
"model": "flux-3-video",
"prompt": "An orange cat jumps onto a sunlit wooden table, its tail brushes a glass that wobbles but does not fall. Cinematic, shallow depth of field.",
"duration": 5,
"resolution": "hd",
"aspect_ratio": "16:9"
}'
```
```python Python theme={null}
import requests
url = "https://gccai.heqingsong.uk/v1/videos/generations"
payload = {
"model": "flux-3-video",
"prompt": "An orange cat jumps onto a sunlit wooden table, its tail brushes a glass that wobbles but does not fall. Cinematic, shallow depth of field.",
"duration": 5,
"resolution": "hd",
"aspect_ratio": "16:9",
}
headers = {
"Authorization": "Bearer ",
"Content-Type": "application/json",
}
response = requests.post(url, json=payload, headers=headers)
print(response.json())
```
```javascript JavaScript theme={null}
const url = "https://gccai.heqingsong.uk/v1/videos/generations";
const payload = {
model: "flux-3-video",
prompt: "An orange cat jumps onto a sunlit wooden table, its tail brushes a glass that wobbles but does not fall. Cinematic, shallow depth of field.",
duration: 5,
resolution: "hd",
aspect_ratio: "16:9",
};
const headers = {
Authorization: "Bearer ",
"Content-Type": "application/json",
};
fetch(url, {
method: "POST",
headers: headers,
body: JSON.stringify(payload),
})
.then((response) => response.json())
.then((data) => console.log(data))
.catch((error) => console.error("Error:", error));
```
```go Go theme={null}
package main
import (
"bytes"
"encoding/json"
"fmt"
"io/ioutil"
"net/http"
)
func main() {
url := "https://gccai.heqingsong.uk/v1/videos/generations"
payload := map[string]interface{}{
"model": "flux-3-video",
"prompt": "An orange cat jumps onto a sunlit wooden table",
"duration": 5,
"resolution": "hd",
"aspect_ratio": "16:9",
}
jsonData, _ := json.Marshal(payload)
req, _ := http.NewRequest("POST", url, bytes.NewBuffer(jsonData))
req.Header.Set("Authorization", "Bearer ")
req.Header.Set("Content-Type", "application/json")
client := &http.Client{}
resp, err := client.Do(req)
if err != nil {
panic(err)
}
defer resp.Body.Close()
body, _ := ioutil.ReadAll(resp.Body)
fmt.Println(string(body))
}
```
```json 200 theme={null}
{
"code": 200,
"data": [
{
"status": "submitted",
"task_id": "task_01J9HA7JPQ9A0Z6JZ3V8M9W6PZ"
}
]
}
```
```json 400 theme={null}
{
"error": {
"code": 400,
"message": "Invalid request parameters",
"type": "invalid_request_error"
}
}
```
```json 401 theme={null}
{
"error": {
"code": 401,
"message": "Authentication failed, please check your API key",
"type": "authentication_error"
}
}
```
```json 402 theme={null}
{
"error": {
"code": 402,
"message": "Insufficient account balance, please top up and try again",
"type": "payment_required"
}
}
```
```json 422 theme={null}
{
"error": {
"code": 422,
"message": "Parameter conflict or invalid value",
"type": "invalid_request_error"
}
}
```
```json 429 theme={null}
{
"error": {
"code": 429,
"message": "Too many requests, please try again later",
"type": "rate_limit_error"
}
}
```
## Authorization
All endpoints require Bearer Token authentication
Get your API Key from the [API Key Management Page](https://gccai.heqingsong.uk/keys):
```
Authorization: Bearer YOUR_API_KEY
```
## Generation Modes
`flux-3-video` is a **unified entry**: mode is inferred from fields, or set explicitly with `mode`.
| Mode | Trigger | Notes |
| ---------------------------- | ------------------------------------ | --------------------------------------------------------------------- |
| **Text-to-video (t2v)** | `prompt` only | Pure text |
| **Image-to-video (i2v)** | `image_urls` | Keyframes; see below |
| **Video continuation (v2v)** | `video_url` / `video_urls` | Higher unit price; if both image and video are set, continuation wins |
| **Draft → final** | `draft:true` or `draft_from_task_id` | Cheap preview, then full-price final |
`mode` values: `t2v` / `i2v` / `v2v` / `draft_enhance`, or official spellings `text-to-video` / `image-continuation` / `video-continuation`. **Explicit `mode` has highest priority.**
### Image-to-video keyframe semantics
Order in `image_urls` is semantic — do not sort or dedupe:
| Count | Meaning |
| ----- | ---------------------------------------------------------------------------------- |
| 1 | **Start frame** |
| 2 | First start, second **end frame** |
| 3\~10 | First start, last end, middle frames **evenly spaced** (set `duration` explicitly) |
## Request Parameters
Fixed value: `flux-3-video`
Prompt. **Must not be sent** when using `draft_from_task_id` (rejected if present).
Duration in seconds, integer **5\~20**, default `5`
**`duration: "auto"` is not supported** (billing needs a fixed second count). Omit, `"auto"`, or non-integers → treated as **5 seconds** without error and without adaptive length.
For **video continuation**, the delivered duration may be shorter than requested (e.g. request 5s, get 4s). The request is pre-charged for the requested seconds and the difference is refunded after completion; final amount is query `cost`. Text/image-to-video do not show this gap.
Resolution
* `hd` (default; also accepts `720p`)
* `fhd` (also accepts `1080p`)
Measured: `hd` \~1280×704 at 16:9; `fhd` \~1920×1088.
Draft mode (`draft:true`) **only** allows `hd`.
Aspect ratio
Options: `21:9`, `2:1`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`, or `auto` (default; chosen automatically from the prompt and assets)
Image-to-video keyframes, **1\~10**, public http(s) URL or base64
Input video for continuation (mp4, public URL or base64)
Same as `video_url`; uses the **first** item (compat)
Generate synced audio, default `true`. `false` yields silent video (**no discount**)
Draft mode: \~**1/3 price** low-quality preview; only with `resolution: hd`
Draft → final: ID of **your** successful draft task
* Only `resolution` may change; prompt, duration, images, video cannot
* Charged at full final price; draft fee is not credited
* Mutually exclusive with `draft:true`
Moderation tolerance **0\~4**, default `2` (higher = more permissive)
Do not confuse with FLUX.2 images (0~~5) or Kontext (0~~6).
Explicit mode (optional); see Generation Modes
## Draft Mode
Two-step workflow when iterating is expensive:
```
Step 1 draft:true → ~1/3 price low-quality preview
Step 2 draft_from_task_id → full-price final matching the draft look
```
### Create draft
```json theme={null}
{
"model": "flux-3-video",
"prompt": "An orange cat jumps onto a sunlit wooden table",
"duration": 5,
"draft": true
}
```
### Draft to final
```json theme={null}
{
"model": "flux-3-video",
"draft_from_task_id": "task_01K_DRAFT...",
"resolution": "fhd"
}
```
Draft-to-final re-renders at full quality using the draft’s saved params (mode / prompt / seed / assets). Continuation drafts finalize at continuation final rates.
## Request Examples
### Text-to-video (portrait)
```json theme={null}
{
"model": "flux-3-video",
"prompt": "Rainy Tokyo street at night, neon in puddles, a person walks with an umbrella.",
"duration": 8,
"resolution": "fhd",
"aspect_ratio": "9:16"
}
```
### Image-to-video (start + end frame)
```json theme={null}
{
"model": "flux-3-video",
"prompt": "Slow push-in as a flower opens from bud to bloom",
"image_urls": [
"https://example.com/bud.jpg",
"https://example.com/bloom.jpg"
],
"duration": 5
}
```
### Video continuation
```json theme={null}
{
"model": "flux-3-video",
"prompt": "Camera keeps following as the lead turns toward a distant lighthouse",
"video_url": "https://example.com/clip.mp4",
"duration": 5
}
```
### Silent video
```json theme={null}
{
"model": "flux-3-video",
"prompt": "...",
"audio": false
}
```
## Constraints
| Limit | Value |
| ------------------ | ---------------------------------------------------- |
| Duration | Integer 5\~20 (`auto` unsupported; `21` is rejected) |
| Keyframes | 1\~10 |
| Resolution | `hd` / `fhd` only; draft only `hd` |
| Aspect ratio | Seven options or `auto` |
| `safety_tolerance` | 0\~4 |
### Common submit errors (usually not charged)
| Case | Notes |
| ----------------------------------------------------- | ----------------------------- |
| Missing `prompt` | Required except draft enhance |
| Invalid `resolution` / `aspect_ratio` / `duration` | Out of range |
| Keyframes > 10 | Cap exceeded |
| Explicit `i2v` without images / `v2v` without video | Mode/asset mismatch |
| `draft:true` + `fhd` | Draft is hd only |
| Invalid / non-draft / unfinished `draft_from_task_id` | Finalization preconditions |
| Changing prompt / duration on finalize | Only `resolution` allowed |
| Both `draft` and `draft_from_task_id` | Mutually exclusive |
Moderation failures end as `failed` with **full refund**.
## Capability Coverage
| Capability | Status |
| ---------------------------------- | ------------------------------------------------ |
| t2v / i2v / v2v | ✅ Auto or explicit `mode` |
| Draft / draft enhance | ✅ `draft` / `draft_from_task_id` |
| Synced audio | ✅ On by default; `audio:false` off (no discount) |
| Timed keyframes `[seconds, image]` | ❌ Evenly spaced keyframe array only |
| `duration: "auto"` | ❌ Not supported |
## Response
Status code; 200 on success
Response data array
Task status; `submitted` on create
Task ID for polling
**Query results**
Video generation is async. Poll [Get Task Status](/en/api-reference/tasks/status).
Recommended interval **5\~10 seconds**; client timeout **15 minutes** (20s fhd is slower). Measured \~60s for `t2v` + `hd` + 5s.
On success use `result.videos[0].url`; assets are mirrored to the platform CDN. `cost` is the final charge. Failures are fully refunded.