fishtoken Sign up
VideoImage

Wan 2.7 API

Wan 2.7 covers several video jobs and image generation. Pick the job with the model ID; the API key and balance are the same for all of them.

Create your accountQuickstart

At a glance

Type
Video generation, video editing, image generation
Video model IDs
  • wan2.7-t2v
  • wan2.7-i2v
  • wan2.7-r2v
  • wan2.7-videoedit
Image model IDs
  • wan2.7-image
  • wan2.7-image-pro
Endpoints
POST https://fishtoken.ai/v1/video/generations
POST https://fishtoken.ai/v1/images/generations
Billing
Pay as you go from your prepaid balance. Current price: fishtoken.ai/pricing

What it can do

  • wan2.7-t2v: text to video. Describe a scene, get a clip.
  • wan2.7-i2v: image to video. Animate a product photo or a still.
  • wan2.7-r2v: reference to video. Generate a clip guided by reference material.
  • wan2.7-videoedit: video editing. Change an existing clip with an instruction.
  • wan2.7-image and wan2.7-image-pro: image generation.

Where it fits in Southeast Asia

  • Turn existing product photos into short clips for listings and shop pages.
  • Adapt one clip for another market by editing it instead of shooting again.
  • Campaign images and banners for sales events.
  • Social posts that pair a generated image with a short clip.

Example request

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

curl: image-to-video (wan2.7-i2v)
# Image-to-video: animate a product photo
curl https://fishtoken.ai/v1/video/generations \
  -H "Authorization: Bearer $FISHTOKEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "wan2.7-i2v",
    "prompt": "Slow push-in on the sneaker, light moving across the fabric",
    "image": "https://example.com/your-product-photo.jpg"
  }'

# 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"

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.

Python: image generation (wan2.7-image)
from openai import OpenAI
import os

client = OpenAI(base_url="https://fishtoken.ai/v1", api_key=os.environ["FISHTOKEN_API_KEY"])

img = client.images.generate(
    model="wan2.7-image",
    prompt="Flat-lay of a batik scarf on a light wooden table, soft daylight",
)
print(img.data[0])  # image URL or data, depending on the model

Example fields. Image models use /v1/images/generations (and /v1/images/edits for edits). Check the FishToken docs for the parameters each model supports.

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 Wan 2.7

One account and one API key for every featured model.

Create your accountQuickstart

Other featured models

Same account, same API key, same balance.