Sora 2

Sora 2 generates video from text or animates an input image.

Last updated View as MarkdownAgent setup

Sora 2

Node type: video:sora_2_text_to_video
Category: video

Unavailable: Sora 2 was retired by OpenAI on 24 Sep 2026 and no longer runs. Swap this node for Veo 3.1 (video:veo3_1), which does text or image to video with native audio.

Description

Sora 2 no longer runs: OpenAI retired it on 24 Sep 2026. To make the same kind of clip in Wireflow, swap this node for Veo 3.1 (video:veo3_1), which does text or image to video with native audio, and run it from code with POST /api/v1/workflows/{id}/run or from an agent over the Wireflow MCP server. This node's type was video:sora_2_text_to_video. It took a prompt and an optional image and made 4 to 20 second clips at 720p.

Pricing

  • Cost: ~10 credits per second
  • Per-second rate: The figure is the rate for a 5-second clip. Shorter clips can cost a bit more per second. You're always charged for the real length.

Variant family

  • Family: sora-2
  • Is primary: yes
  • All variants: video:sora_2_image_to_video, video:sora_2_image_to_video_pro, video:sora_2_text_to_video, video:sora_2_text_to_video_pro

Canvas ports

These appear as port handles on the left side of the node.

ID Label Details
prompt Prompt TEXT (required)
image_url Image URL IMAGE

These render as form fields in the right-side config panel when the node is selected.

ID Label Details
quality Quality TEXT · options: standard, pro
aspect_ratio Aspect Ratio TEXT · options: 9:16, 16:9
delete_video Delete Video BOOLEAN
duration Duration NUMBER · options: 4, 8, 12, 16, 20
resolution Resolution TEXT · options: 720p

Outputs

ID Label Type
video Generated Video VIDEO

Auto-generated from the Wireflow node registry.

For AI agents: the full documentation index is at /llms.txt, and most docs pages are available as Markdown by adding .md to the URL.

© 2026 Wireflow. All rights reserved.