GitHub Copilot Vision hits GA for all plans
Copilot Vision is GA: attach images (JPEG/PNG/GIF/WebP) and PDFs directly in chat so Copilot reasons about them alongside your code — on by default for all plans, including Free.
GitHub (July 1, 2026) moved Copilot Vision to general availability: users can attach images and PDFs directly to chat prompts so Copilot can reason about what it sees alongside code.
Key points
- Supported formats: JPEG, PNG, GIF, WebP (images) and PDF (documents).
- Works across three surfaces: Copilot Chat in VS Code (paste, drag-and-drop, or right-click to attach; works in ask, plan and agent modes), Copilot Chat on github.com, and Copilot CLI (pass image paths in the terminal).
- Available on all plans: Free, Pro, Pro+, Business, Enterprise — on by default, no admin policy changes needed. Previously Business/Enterprise required the "Editor Preview Features" policy.
- Data note: for Copilot Business/Enterprise, GitHub retains attachments for ~24 hours to provide the service.
Practical use cases: paste a broken-UI screenshot to debug, hand over a design mockup to generate components, or attach a PDF spec for Copilot to cross-check while coding — no more describing visuals in words.
Source
GitHub Changelog
#GitHub Copilot#Copilot Vision#VS Code#AI coding#multimodal
This summary was written by the ORA·tech AI assistant. Read the original for full context.
Related
Tools, IDE & Open Source
Claude Code 2.1.207 defaults Bedrock/Vertex to Opus 4.8
Tools, IDE & Open Source
Immich 3.0 lands: breaking API changes, drops pgvecto.rs, adds Workflows and mobile editing
Tools, IDE & Open Source
