fishtoken Sign up
Video

Kling V3 API

Call Kling V3 video models through FishToken with one API key and a single prepaid balance.

At a glance

Type
Video generation
Model IDs
  • kling-v3
  • kling-v3-omni
Endpoint
POST https://fishtoken.ai/v1/video/generations
Billing
Pay as you go from your prepaid balance. Current price: fishtoken.ai/pricing

What it can do

  • Generate a video clip from a prompt through the video generations endpoint.
  • Two model IDs: the standard kling-v3 and the kling-v3-omni variant. Switch between them by changing the model field.
  • The inputs each variant accepts are listed in the FishToken docs.

Where it fits in Southeast Asia

  • Product showcase clips for online shops.
  • Short clips for social channels, with scenes and settings that match your local audience.
  • Ad creative variations to test against each other.
  • Promotional clips for launches, sales and events.

Example request

Set your key as an environment variable first: export FISHTOKEN_API_KEY=...

curl
# 1) Submit a generation task
curl https://fishtoken.ai/v1/video/generations \
  -H "Authorization: Bearer $FISHTOKEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kling-v3",
    "prompt": "Vertical shot: iced coffee with palm sugar being poured into a glass at a street stall, morning light",
    "duration": 5
  }'

# 2) The response includes a task ID. Check the task until the video is ready:
curl https://fishtoken.ai/v1/video/generations/TASK_ID \
  -H "Authorization: Bearer $FISHTOKEN_API_KEY"
Python (requests)
import os
import requests

API = "https://fishtoken.ai/v1"
HEADERS = {"Authorization": f"Bearer {os.environ['FISHTOKEN_API_KEY']}"}

task = requests.post(f"{API}/video/generations", headers=HEADERS, json={
    "model": "kling-v3",
    "prompt": "Vertical shot: iced coffee with palm sugar being poured into a glass at a street stall, morning light",
    "duration": 5,
}, timeout=60)
print(task.json())  # keep the task ID, then poll the task (see FishToken docs)

Example fields. The exact parameters each model accepts (duration, size, reference images and so on) and the response format are defined in the FishToken docs. Check them before you build on these examples.

Before you publish

Content filtering depends on the upstream model service. You are responsible for what you generate and publish: no sexual content, no graphic violence, and no real person's likeness or voice without their consent. Label AI-generated content where the platform you publish on or local law requires it.

Read the full content rules

Try Kling V3

One account and one API key for every featured model.

Other featured models

Same account, same API key, same balance.