Use the PixVerse API via RunAPI with a model skill, unified auth, and pay-as-you-go pricing.
curl -X POST https://runapi.ai/api/v1/pixverse/edit_video \
-H "Authorization: Bearer $RUNAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "pixverse-v6",
"video_url": "https://cdn.runapi.ai/public/samples/video.mp4",
"prompt": "Create a 10-second clip of a paper boat drifting down a rain-filled street gutter, camera following at water level."
}'import { PixverseClient } from "@runapi.ai/pixverse";
const client = new PixverseClient();
const result = await client.editVideo.run({
model: "pixverse-v6",
video_url: "https://cdn.runapi.ai/public/samples/video.mp4",
prompt: "Create a 10-second clip of a paper boat drifting down a rain-filled street gutter, camera following at water level.",
});require "runapi/pixverse"
client = RunApi::Pixverse::Client.new
result = client.edit_video.run(
model: "pixverse-v6",
video_url: "https://cdn.runapi.ai/public/samples/video.mp4",
prompt: "Create a 10-second clip of a paper boat drifting down a rain-filled street gutter, camera following at water level."
)npx skills add runapi-ai/pixverse -g# Claude Code
claude mcp add runapi -s user -- npx -y @runapi.ai/mcp
# Codex
codex plugin install runapi-mcp@agents
# Cursor / Windsurf / VS Code
npx @runapi.ai/mcp init cursorPixVerse V6 covers five video capabilities through one model version. Generate from a text prompt, animate a single image, guide a scene with up to seven reference images, interpolate between a first and last frame, or continue a finished result. Clips run 1 to 15 seconds at 360p to 1080p with optional synchronized audio.
| Model ID | pixverse-v6 |
| Provider | PixVerse |
| Modality | video |
| Task type | asynchronous |
| Billing unit | second |
| API endpoint | /api/v1/pixverse/edit_video |
| Commercial license | Yes — included via API |
| Catalog status | Operational |
Sign up and generate an API key from the dashboard.
Choose the version that best matches your quality and cost requirements.
Submit your prompt and parameters to the model's documented endpoint.
Poll the task or set a webhook, then download the completed output.
PixVerse V6 handles text-to-video, image-to-video, reference-guided edits, frame transitions, and extensions through RunAPI. One model version serves all five endpoints, so the same key and pricing model apply across every capability.
A single RunAPI API key unlocks the whole model catalog across all providers. No separate accounts to create, no API keys to rotate per integration, and no credential management overhead. Add a new model to your app by changing one parameter.
Per-call pricing in USD, billed monthly into a single invoice. No subscription tiers, no minimum spend, and failed generations are never charged. The pricing page and check_pricing API show exact costs before you commit to a model.
Typed schemas, parameter constraints, and setup notes are packaged in the model skill so your implementation starts from the right contract. The skill loads into Claude Code, Codex, Gemini CLI, Cursor, and VS Code — your agent knows the correct request shape before you write a line of code.
Five — text-to-video, image-to-video, reference-guided edit, frame transition, and extension of a finished result. All five use the same model version.
1 to 15 seconds per request, set with duration_seconds. Use the extend endpoint to continue a completed result beyond a single generation.
360p, 540p, 720p, and 1080p, across eight aspect ratios ranging from ultrawide to vertical.
Yes — set enable_audio to generate synchronized audio alongside the clip. It is off by default.
The reference-guided endpoint accepts 1 to 7 ordered public image URLs.
Pick the cheapest variant that meets your quality bar. Most teams start on the fast variant and graduate to pro for production.