---
title: "Image input"
canonical: "https://canmyagentuse.com/features/image-input"
contentKind: "feature"
locale: "en"
description: "Attach, paste, or select an image for use as model input."
llmSummary: "Image input means a product accepts attached, pasted, or selected images as model input. Supported methods, formats, limits, and surfaces are recorded as qualifiers."
publishedAt: "2026-08-28T00:00:00.000Z"
updatedAt: "2026-08-28T00:00:00.000Z"
verifiedAt: "2026-08-28"
tags: ["perception","image","uploads"]
---

# Image input

Image input means a product accepts attached, pasted, or selected images as model input. Supported methods, formats, limits, and surfaces are recorded as qualifiers.

- HTML: https://canmyagentuse.com/features/image-input
- JSON: https://canmyagentuse.com/api/v1/features/image-input.json
- Markdown: https://canmyagentuse.com/features/image-input.md

Terminology basis: **Common product term** — https://docs.x.ai/grok/faq.

## Current support at a glance

Image input: 15 supported, 0 partial, 0 unsupported, 16 unreviewed across 31 cataloged products.

- Reviewed current products: 15 of 31
- Supported: 15
- Partial: 0
- Unsupported: 0
- Unreviewed: 16
- Not applicable: 0

Unknown or unreviewed means insufficient published evidence; it does not mean unsupported.

This row asks whether an image selected, dragged, or pasted into the exact harness is interpreted as visual model context. Merely uploading the file to storage, extracting only its filename, or making it available to an unrelated tool does not establish image input.

Evidence should record accepted formats, per-file and per-message limits, animation handling, resolution or detail controls, whether metadata is stripped, and whether availability changes by model, plan, or client. Screenshot capture is a separate capability because it concerns acquiring the current interface rather than supplying an existing image.

Image input does not by itself establish screenshot capture, computer use, image generation, or reliable interpretation of every image format.

## Catalog context

- Category: [perception](/categories/perception.md)
- Terminology basis: Common product term
- Aliases: image input, image attachment, image upload, paste image, vision input
- Family: [File and media inputs](/features/file-inputs.md)
- Siblings: [Audio file input](/features/audio-file-input.md), [Document input](/features/office-document-input.md), [File upload limits](/features/upload-limits.md), [PDF input](/features/pdf-documents.md), [Video input](/features/video-input.md)

## Compatibility assertions

Unknown means insufficient published evidence; it does not mean unsupported.

### ChatGPT (web)

- Harness: [ChatGPT](/harnesses/chatgpt-web.md)
- current: **Supported**
  - Target: hosted-observation — 2026-08-28 ChatGPT Work web documentation observation; observed 2026-08-28
  - Environment: hosted-default
  - Constraint (runtime): images can be attached, pasted, or dragged into the web composer
  - Evidence: [OpenAI — Image inputs](https://learn.chatgpt.com/docs/image-inputs) — documented; observed 2026-08-28
  - Qualification note 3: Evidence checked 2026-08-28: OpenAI documents image attachment, paste, or drag-and-drop in ChatGPT Work on the web; Shift-drag image input in the ChatGPT desktop app; and pasted images or repeated -i/--image paths in Codex CLI.
- preview: **Unknown**

### Claude (web)

- Harness: [Claude](/harnesses/claude-web.md)
- current: **Supported**
  - Target: hosted-observation — 2026-08-28 Claude web documentation observation; observed 2026-08-28
  - Environment: hosted-default
  - Constraint (runtime): supports JPEG, PNG, GIF, and WebP through file selection, drag-and-drop, or clipboard paste
  - Evidence: [Anthropic — Upload files to Claude](https://support.claude.com/en/articles/8241126-upload-files-to-claude) — documented; observed 2026-08-28
  - Qualification note 4: Evidence checked 2026-08-28: Anthropic documents JPEG, PNG, GIF, and WebP uploads in Claude on the web and Claude Desktop, including drag-and-drop and clipboard paste.
- preview: **Unknown**

### Gemini (web)

- Harness: [Gemini](/harnesses/gemini-web.md)
- current: **Supported**
  - Target: hosted-observation — 2026-08-28 Gemini Apps web documentation observation; observed 2026-08-28
  - Environment: hosted-default
  - Constraint (runtime): photos and images share Gemini Apps' documented file-count and size limits
  - Evidence: [Google — Upload and analyze files in Gemini Apps](https://support.google.com/gemini/answer/14903178?co=GENIE.Platform%3DDesktop&hl=en) — documented; observed 2026-08-28
  - Qualification note 5: Evidence checked 2026-08-28: Google documents photo and image uploads among Gemini Apps file inputs on the web, subject to the shared per-prompt and per-file upload limits.
- preview: **Unknown**

### Copilot (web)

- Harness: [Copilot](/harnesses/copilot-web.md)
- current: **Supported**
  - Target: hosted-observation — 2026-08-28 Microsoft Copilot web documentation observation; observed 2026-08-28
  - Environment: hosted-default
  - Constraint (runtime): supported image uploads are PNG, JPEG, PJP, and JFIF; the file-upload workflow documents asking Copilot to describe or analyze the image
  - Constraint (runtime): each file is limited to 50 MB and up to 20 files can be added to one conversation
  - Evidence: [Microsoft Support — File upload in Microsoft Copilot](https://support.microsoft.com/en-US/microsoft-copilot/file-upload-in-microsoft-copilot) — documented; observed 2026-08-28
  - Qualification note 8: Evidence checked 2026-08-28: Microsoft Copilot web accepts PNG, JPEG, PJP, and JFIF uploads and documents prompts that ask Copilot to describe and analyze the attached image.
- preview: **Unknown**

### Grok (web)

- Harness: [Grok](/harnesses/grok-web.md)
- current: **Supported**
  - Target: hosted-observation — 2026-08-28 Grok Web documentation observation; observed 2026-08-28
  - Environment: hosted-default
  - Constraint (runtime): file support and limits can vary by platform; this cell is scoped to the web surface
  - Evidence: [xAI — Grok files and data FAQ](https://docs.x.ai/grok/faq) — documented; observed 2026-08-28
  - Qualification note 1: Evidence checked 2026-08-28: xAI documents image uploads and image understanding in Grok Web chats.
- preview: **Unknown**

### Grok Bot (desktop)

- Harness: [Grok Bot](/harnesses/grok-bot-desktop.md)
- current: **Supported**
  - Target: hosted-observation — 2026-08-28 Grok Bot desktop documentation observation; observed 2026-08-28
  - Environment: hosted-default
  - Constraint (runtime): desktop composer accepts up to six attachments per message and documents a 25 MB limit per image
  - Constraint (policy): damaged or unusually formatted files may not be readable
  - Evidence: [xAI — Grok Bot files and results](https://docs.x.ai/grok-bot/files-and-results) — documented; observed 2026-08-28
  - Qualification note 2: Evidence checked 2026-08-28: Grok Bot messages accept pasted images and local file attachments; its files guide lists images as supported input and documents desktop attachment limits.

### Perplexity (web)

- Harness: [Perplexity](/harnesses/perplexity-web.md)
- current: **Supported**
  - Target: hosted-observation — 2026-08-28 Perplexity web documentation observation; observed 2026-08-28
  - Environment: hosted-default
  - Constraint (runtime): JPEG, HEF, and PNG can be attached or dragged into desktop web and are interpreted by multimodal models, including graphics and captions
  - Constraint (runtime): maximum image size is 40 MB; animation, metadata, and exact resolution handling are not established
  - Evidence: [Perplexity Help Center — Uploading images](https://www.perplexity.ai/help-center/en/articles/10354840-uploading-images-on-perplexity) — documented; observed 2026-08-28
  - Qualification note 7: Evidence checked 2026-08-28: Perplexity web accepts JPEG, HEF, and PNG images up to 40 MB and uses multimodal models to identify images and interpret graphics and captions.
- preview: **Unknown**

### Le Chat (web)

- Harness: [Le Chat](/harnesses/le-chat.md)
- current: **Supported**
  - Target: hosted-observation — 2026-08-28 Mistral Vibe web documentation observation; observed 2026-08-28
  - Environment: hosted-default
  - Constraint (runtime): PNG, JPEG, WebP, and GIF uploads can be interpreted as photos, diagrams, screenshots, or scanned pages
  - Constraint (policy): Le Chat is now Vibe at the same chat.mistral.ai entry point; this claim is scoped to the documented Work upload path
  - Evidence: [Mistral Docs — Work with Files and Canvas](https://docs.mistral.ai/vibe/work/files-and-canvas) — documented; observed 2026-08-28
  - Evidence: [Mistral Docs — Vibe overview](https://docs.mistral.ai/vibe) — documented; observed 2026-08-28
  - Qualification note 9: Evidence checked 2026-08-28: Mistral's current Vibe Work documentation, which supersedes Le Chat at chat.mistral.ai, accepts PNG, JPEG, WebP, and GIF uploads and interprets photos, diagrams, screenshots, and scanned pages.
- preview: **Unknown**

### Devin (web)

- Harness: [Devin](/harnesses/devin-web.md)
- current: **Unknown**
- preview: **Unknown**

### Replit Agent (web)

- Harness: [Replit Agent](/harnesses/replit-agent.md)
- current: **Unknown**
- preview: **Unknown**

### ChatGPT (desktop)

- Harness: [ChatGPT](/harnesses/chatgpt-desktop.md)
- current: **Supported**
  - Target: dated-documentation — current ChatGPT desktop documentation; observed 2026-08-28
  - Environment: local-default
  - Constraint (runtime): Shift-drag supplies an image for inspection in the desktop app
  - Evidence: [OpenAI — Image inputs](https://learn.chatgpt.com/docs/image-inputs) — documented; observed 2026-08-28
  - Qualification note 3: Evidence checked 2026-08-28: OpenAI documents image attachment, paste, or drag-and-drop in ChatGPT Work on the web; Shift-drag image input in the ChatGPT desktop app; and pasted images or repeated -i/--image paths in Codex CLI.
- preview: **Unknown**

### Claude (desktop)

- Harness: [Claude](/harnesses/claude-desktop.md)
- current: **Supported**
  - Target: dated-documentation — current Claude Desktop documentation; observed 2026-08-28
  - Environment: local-default
  - Constraint (runtime): supports JPEG, PNG, GIF, and WebP through the shared Claude chat attachment workflow
  - Evidence: [Anthropic — Upload files to Claude](https://support.claude.com/en/articles/8241126-upload-files-to-claude) — documented; observed 2026-08-28
  - Qualification note 4: Evidence checked 2026-08-28: Anthropic documents JPEG, PNG, GIF, and WebP uploads in Claude on the web and Claude Desktop, including drag-and-drop and clipboard paste.
- preview: **Unknown**

### Cursor (desktop)

- Harness: [Cursor](/harnesses/cursor.md)
- current: **Supported**
  - Target: dated-documentation — current Cursor Agent documentation; observed 2026-08-28
  - Environment: local-default
  - Constraint (runtime): PNG, JPEG, GIF, WebP, and SVG files enter conversation context when the selected model is vision-capable
  - Evidence: [Cursor — Agent overview](https://cursor.com/docs/agent/overview) — documented; observed 2026-08-28
  - Qualification note 6: Evidence checked 2026-08-28: Cursor Agent can read PNG, JPEG, GIF, WebP, and SVG files and place them in conversation context for a vision-capable model.
- preview: **Unknown**

### OpenWork Desktop (desktop)

- Harness: [OpenWork Desktop](/harnesses/openwork-desktop.md)
- current: **Unknown**

### Copilot Chat (desktop)

- Harness: [Copilot Chat](/harnesses/vscode-copilot.md)
- current: **Supported**
  - Target: dated-documentation — current GitHub Copilot Chat documentation for VS Code; observed 2026-08-28
  - Environment: local-default
  - Constraint (runtime): JPEG, PNG, GIF, WebP, HEIC, and HEIF images can be pasted, dragged, or added from the VS Code Explorer when the selected model supports image input
  - Constraint (plan): image attachments are documented as available on all Copilot plans and enabled by default
  - Evidence: [GitHub Docs — Asking GitHub Copilot questions in your IDE](https://docs.github.com/en/enterprise-cloud@latest/copilot/how-tos/chat-with-copilot/chat-in-ide?tool=vscode) — documented; observed 2026-08-28
  - Qualification note 10: Evidence checked 2026-08-28: VS Code Copilot Chat accepts image context for vision-capable models. Current GitHub documentation lists JPEG, PNG, GIF, WebP, HEIC, and HEIF and says image attachments are available on all Copilot plans.
- preview: **Unknown**

### Chrome WebMCP origin trial (desktop)

- Harness: [Chrome WebMCP origin trial](/harnesses/chrome-webmcp-preview.md)
- current: **Unknown**

### Windsurf (desktop)

- Harness: [Windsurf](/harnesses/windsurf.md)
- current: **Unknown**
- preview: **Unknown**

### Zed Agent (desktop)

- Harness: [Zed Agent](/harnesses/zed-agent.md)
- current: **Unknown**
- preview: **Unknown**

### Continue (desktop)

- Harness: [Continue](/harnesses/continue.md)
- current: **Unknown**
- preview: **Unknown**

### Cline (desktop)

- Harness: [Cline](/harnesses/cline.md)
- current: **Unknown**
- preview: **Unknown**

### JetBrains AI (desktop)

- Harness: [JetBrains AI](/harnesses/jetbrains-ai.md)
- current: **Unknown**
- preview: **Unknown**

### Warp (desktop)

- Harness: [Warp](/harnesses/warp.md)
- current: **Unknown**
- preview: **Unknown**

### Claude CLI (cli)

- Harness: [Claude CLI](/harnesses/claude-cli.md)
- current: **Supported**
  - Target: dated-documentation — current Claude Code workflow documentation; observed 2026-08-28
  - Environment: local-default
  - Constraint (runtime): images can be dragged into the Claude Code window, pasted with the documented terminal shortcut, or referenced by path and are analyzed as visual context
  - Constraint (runtime): multiple images, diagrams, screenshots, and mockups are documented; accepted formats and complete model-specific limits are not listed on the workflow page
  - Evidence: [Claude Code Docs — Common workflows](https://code.claude.com/docs/en/common-workflows) — documented; observed 2026-08-28
  - Qualification note 11: Evidence checked 2026-08-28: Claude Code accepts image drag-and-drop, clipboard paste, and image paths and documents analysis of screenshots, diagrams, mockups, and multiple images.
- preview: **Unknown**

### ChatGPT CLI (cli)

- Harness: [ChatGPT CLI](/harnesses/chatgpt-cli.md)
- current: **Unknown**
- preview: **Unknown**

### Codex CLI (cli)

- Harness: [Codex CLI](/harnesses/codex-cli.md)
- current: **Supported**
  - Target: dated-documentation — current Codex CLI documentation; observed 2026-08-28
  - Environment: local-default
  - Constraint (runtime): accepts pasted images and one or more paths through -i/--image; OpenAI names common formats including PNG and JPEG
  - Evidence: [OpenAI — Image inputs](https://learn.chatgpt.com/docs/image-inputs) — documented; observed 2026-08-28
  - Qualification note 3: Evidence checked 2026-08-28: OpenAI documents image attachment, paste, or drag-and-drop in ChatGPT Work on the web; Shift-drag image input in the ChatGPT desktop app; and pasted images or repeated -i/--image paths in Codex CLI.
- preview: **Unknown**

### OpenCode (cli)

- Harness: [OpenCode](/harnesses/opencode.md)
- current: **Unknown**
- preview: **Unknown**

### Gemini CLI (cli)

- Harness: [Gemini CLI](/harnesses/gemini-cli.md)
- current: **Supported**
  - Target: dated-documentation — current Gemini CLI custom-command documentation; observed 2026-08-28
  - Environment: local-default
  - Constraint (runtime): supported image files, with PNG and JPEG given as examples, are encoded and injected as multimodal input when referenced with @{...} in a custom command
  - Constraint (runtime): this evidence establishes custom-command file injection, not every ordinary-prompt attachment or clipboard path
  - Evidence: [Gemini CLI — Custom commands](https://geminicli.com/docs/cli/custom-commands/) — documented; observed 2026-08-28
  - Qualification note 12: Evidence checked 2026-08-28: Gemini CLI custom commands encode supported image paths, including PNG and JPEG examples, and inject them as multimodal input through @{...}.
- preview: **Unknown**

### Aider (cli)

- Harness: [Aider](/harnesses/aider.md)
- current: **Unknown**
- preview: **Unknown**

### Goose (cli)

- Harness: [Goose](/harnesses/goose.md)
- current: **Unknown**
- preview: **Unknown**

### Copilot CLI (cli)

- Harness: [Copilot CLI](/harnesses/copilot-cli.md)
- current: **Unknown**
- preview: **Unknown**

### Amp (cli)

- Harness: [Amp](/harnesses/amp-cli.md)
- current: **Unknown**
- preview: **Unknown**