---
title: "vision.image.ask · OpenVibe.Services"
canonical: "https://openvibe.services/docs/capabilities/vision.image.ask"
updated: null
---

# vision.image.ask · OpenVibe.Services

HTML: [vision.image.ask · OpenVibe.Services](https://openvibe.services/docs/capabilities/vision.image.ask)

# `vision.image.ask`

Generated at 2026-11-13 06:25:48 UTC from [`openvibe-contracts v0.419.0`](https://github.com/OpenVibers/OpenVibe.Contracts/tree/v0.419.0) and [`openvibe-sdk v0.161.0`](https://github.com/OpenVibers/OpenVibe.SDK/tree/v0.161.0).

Not grantable to apps (active, first-party).

Ask or describe an image on OpenVibe.Vision: POST /api/v1/ask and /api/v1/describe take an image (multipart, data URL or public URL), a question, a task (ask, describe, identify, count, translate, ocr) and a mode (auto, local, ai). A read question is answered by the local OCR reader first; everything else goes through OpenVibe.AI, whose provenance the answer reports. In auto mode a read question also works anonymously; any other task needs a signed-in person or this capability.

- Owner: vision (token audience `openvibe.vision`)
- Version: 1.0
- Status: active
- Visibility: first-party
- Resource constraints: none
- Quota class: vision-ask
- Permissions: vision:ask
- Input: [vision.ask-request@1](/docs/contracts/vision.ask-request)
- Output: vision.answer-result@1
- Events: vision.result.ready
- Implemented by: - `POST /api/v1/ask`
- `POST /api/v1/describe`

[These routes in the API explorer](/docs/api/vision#cap-vision.image.ask)