From 73377e20bdac88448c359c6d1de6fb2bd3deeedc Mon Sep 17 00:00:00 2001
From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Date: Sun, 19 Jul 2026 17:02:46 +0000
Subject: [PATCH] docs(openrouter-video): sync with openrouter-web changes

prompt is now optional on POST /api/v1/videos for models that generate
from image input alone (openrouter-web #29276).

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---
 skills/openrouter-video/SKILL.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/skills/openrouter-video/SKILL.md b/skills/openrouter-video/SKILL.md
index a90558b..f31047a 100644
--- a/skills/openrouter-video/SKILL.md
+++ b/skills/openrouter-video/SKILL.md
@@ -72,7 +72,7 @@ echo "$resp" | jq --arg out "$(realpath "$OUTPUT")" \
 
 ## Parameters
 
-Required: `model`, `prompt`. Common optional fields:
+Required: `model`. `prompt` (string) is required by most models, but optional for models that can generate from image input alone (e.g. `x-ai/grok-imagine-video-1.5` driven by `frame_images`) — omitting it for a model that requires one returns a 400. Common optional fields:
 
 - `duration` (int) — must be one of the model's `supported_durations`.
 - `resolution` (string) / `aspect_ratio` (string) / `size` (string, `"WxH"`) — `size` is interchangeable with resolution + aspect_ratio.