From fc9158f324a962c75a5a73db3c21e2b178a01322 Mon Sep 17 00:00:00 2001
From: Promise Emmanuel Oluwadare
 <95595405+PromiseGameFi@users.noreply.github.com>
Date: Sun, 23 Aug 2026 02:10:25 +0100
Subject: [PATCH] docs: correct OpenAI vision request count

---
 docs/how-to/call-openai-vision.md | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/docs/how-to/call-openai-vision.md b/docs/how-to/call-openai-vision.md
index 565cc1b8..9d3452ab 100644
--- a/docs/how-to/call-openai-vision.md
+++ b/docs/how-to/call-openai-vision.md
@@ -64,7 +64,7 @@ same file can point at a different endpoint without editing it. Inside the
 step, the endpoint remains an ordinary OpenAI SDK option:
 
 ```python
-@app.check(uses="vision")
+@app.check(uses="vision", version="responses-contact-sheet-v1")
 def describe_activity(episode: hflow.Episode) -> hflow.CheckResult:
     client = OpenAI(
         api_key=os.environ["OPENAI_API_KEY"],
@@ -92,10 +92,10 @@ uv run --extra openai python examples/openai_vision/pipeline.py
 ```
 
 Pass an MCAP path to use your own episode. The example samples frames at 0.5
-FPS, caps the request at 12 tiles, and makes one model request per episode. Those
-choices are part of the measurement definition: change them deliberately and
-version the step explicitly when external model configuration cannot be hashed
-from the function.
+FPS, caps each request at 12 tiles, and makes one model request per check: two
+requests per episode for the two checks it ships. Those choices are part of the
+measurement definition: change them deliberately and version the step explicitly
+when external model configuration cannot be hashed from the function.
 
 ## Keep model output as evidence