Runway Gen-4.5 Text-to-Video

POST Base URL: https://api.hiapi.ai /v1/tasks

Image, video, and audio models are called through theUnified Async API POST /v1/tasks endpoint; only the input fields differ (see input parameters below).

Model summary

Model ID	runway-gen-4.5/text-to-video
Type	Video generation (text-to-video)
Endpoint	POST /v1/tasks
Pricing	See HiAPI Pricing

Cinematic 720p landscape or portrait video from a prompt. 16:9 supports 5/8/10s; 9:16 supports 5/10s.

Production guidance

For production, pass callback.url at the top level of the request body so HiAPI can notify your service when the task reaches a terminal state.
GET /v1/tasks/:id is better for local debugging, low-volume jobs, or fallback reconciliation if a callback is missed.
Use callback.when=final. Both success and fail are terminal states, so your service should deduplicate by taskId.

Best suited for

Cinematic shots

Describe the subject, lighting and camera move for concept previews and mood shots.

prompt

5/8/10 second clips

Pick the clip length you need.

duration

720p landscape or portrait

Choose 16:9 or 9:16; resolution remains 720p.

aspect_ratio

Request parameters

POST https://api.hiapi.ai/v1/tasks

# Create an async task — returns taskId immediately (generation runs async)
# Replace YOUR_API_KEY with your account API key
curl -X POST "https://api.hiapi.ai/v1/tasks" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "runway-gen-4.5/text-to-video",
  "input": {
    "prompt": "A rainy neon-lit city alley at night, a woman in a red trench coat holding a clear umbrella walks slowly away from the camera, reflections shimmering on wet asphalt, steam rising from vents, smooth tracking shot, cinematic",
    "duration": 5,
    "aspect_ratio": "16:9"
  }
}'

import requests, json

# Business params — fields vary by model (see the model page)
payload = json.loads(r'''
{
  "model": "runway-gen-4.5/text-to-video",
  "input": {
    "prompt": "A rainy neon-lit city alley at night, a woman in a red trench coat holding a clear umbrella walks slowly away from the camera, reflections shimmering on wet asphalt, steam rising from vents, smooth tracking shot, cinematic",
    "duration": 5,
    "aspect_ratio": "16:9"
  }
}
''')

# Create an async task — returns taskId immediately (generation runs async)
resp = requests.post(
    "https://api.hiapi.ai/v1/tasks",
    headers={"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
    json=payload,
)
print(resp.json())  # Returns { code, message, data: { taskId } }

// Create an async task — returns taskId immediately (generation runs async)
// Replace YOUR_API_KEY with your account API key
const resp = await fetch("https://api.hiapi.ai/v1/tasks", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
  "model": "runway-gen-4.5/text-to-video",
  "input": {
    "prompt": "A rainy neon-lit city alley at night, a woman in a red trench coat holding a clear umbrella walks slowly away from the camera, reflections shimmering on wet asphalt, steam rising from vents, smooth tracking shot, cinematic",
    "duration": 5,
    "aspect_ratio": "16:9"
  }
}),
});
console.log(await resp.json()); // Returns { code, message, data: { taskId } }

model string required

Fixed value runway-gen-4.5/text-to-video.

example runway-gen-4.5/text-to-video

input object required

Video generation settings.

prompt string required

Describe the video. Max 1000 characters.

duration enum optional

Video length in seconds; 9:16 supports only 5 or 10 seconds.

default 5 enum: 5810

aspect_ratio enum optional

Landscape or portrait video framing. Portrait supports 5 or 10 seconds, without an audio track.

default 16:9 enum: 16:99:16

callback object optional

Optional callback configuration. When set, HiAPI notifies your service when the task reaches a terminal state.

url string required

Required when callback is set; HTTPS URL that receives terminal task notifications.

example https://your-domain.com/hiapi/callback

when enum optional

Callback trigger timing. Use final.

default final enum: final

Example requests

Neon rain alley (5s)

Text-only generation with a cinematic tracking shot.

Request body

{
  "model": "runway-gen-4.5/text-to-video",
  "input": {
    "prompt": "A rainy neon-lit city alley at night, a woman in a red trench coat holding a clear umbrella walks slowly away from the camera, reflections shimmering on wet asphalt, steam rising from vents, smooth tracking shot, cinematic",
    "duration": 5,
    "aspect_ratio": "16:9"
  }
}

Getting the result

The response returns a taskId immediately without waiting for generation to finish.
In production, prefer waiting for callback.url to receive the terminal notification. For local debugging, poll GET /v1/tasks/:id.
When status=success, download the generated video from output[].url.
When status=fail, fix the request based on the returned error instead of retrying the same invalid payload.

FAQ

Can I change the resolution or aspect ratio?

Resolution is fixed at 720p. Choose 16:9 landscape or 9:16 portrait. For first-frame guidance, square, 4:3 or 3:4, use runway-gen-4.5/image-to-video.

Which durations are available?

16:9 supports 5, 8 or 10 seconds; 9:16 supports 5 or 10 seconds. The default is 5.

Next steps

Aspect ratios and durations

Aspect ratio	Durations
16:9 landscape	5 / 8 / 10s
9:16 portrait	5 / 10s

Portrait output is 720×1280 with no audio track and has a higher per-second rate than landscape. See live pricing.