// AI Platform Drift

GitHub Copilot adds inline image generation with separate token billing

GitHub Copilot changelog · published 2026-10-28 18:22 UTC
WORTH KNOWING BUDGET MODELPRICINGLIMITS
WHAT CHANGEDGitHub Copilot now generates and edits images directly in chat sessions using GPT Image 2.5 Flare. Image generation is in public preview for Copilot Pro, Pro+, Business, and Enterprise tiers as of 28 October 2026. Images are billed separately from chat models based on image tokens that count toward plan AI credits. Organization and enterprise owners can disable image generation via Copilot model policies.
WHY IT MATTERSImage generation consumes AI credits under a separate token budget from chat interactions, which affects cost forecasting for teams on metered plans. The feature is enabled by default, so usage begins immediately unless admins apply a policy block.
WHAT TO DOCheck current AI credit consumption in your GitHub billing dashboard to establish a baseline, then monitor for image token usage over the next billing cycle. If your team does not need image generation, disable it now via Copilot model policies to prevent unplanned credit consumption.
Model-reported confidence 85% (not measured accuracy) Primary source ↗ written by anthropic/claude-sonnet-4.5
Show the reasoning — raw diff, triage verdict, confidence
RAW DIFF
+## Generate and edit images directly in Copilot
+https://github.blog/changelog/2026-10-28-generate-and-edit-images-directly-in-copilot
+Wed, 28 Oct 2026 15:30:55 +0000
+
+You can now generate and edit images using natural language in GitHub Copilot. When you ask for an image, your selected reasoning model calls a dedicated image-generation tool powered by GPT Image 2.5 Flare, previews the result inline, and saves it to your project.
+Previously, getting a visual asset while working in Copilot meant stepping away to a separate tool, describing what you needed again, generating it there, and manually bringing it back into your project. This update removes that context switch, so you can go from an idea to a usable image without breaking your flow.
+
+Describe an image conversationally in any Copilot chat session, whether you’re starting a new request or in the middle of a coding task.
+Copilot previews the generated image inline and saves it directly to your workspace.
+Organization and enterprise owners can turn off image generation by disabling the image generation model using Copilot model policies.
+You can opt in to a visible “Made with AI” watermark on images Copilot generates and edits. Watermarking is off by default.
+
+To try it, open a Copilot chat in VS Code, the GitHub Copilot app, or Copilot CLI and describe the image you want.
+Image generation is in public preview for Copilot Pro, Copilot Pro+, Copilot Business, and Copilot Enterprise. It’s billed separately from your chat model, based on image tokens that count toward your plan’s AI credits.
+Join the discussion within GitHub Community.
+
+The post Generate and edit images directly in Copilot appeared first on The GitHub Blog.
HOW IT WAS JUDGED
Triage signals below are model-reported assertions, preserved verbatim; they are not independent arithmetic verification.
triage verdictMATERIAL at 0.92, needed 0.5
triage reasoningNew image generation feature with separate billing and admin controls affects platform capabilities and cost modeling.
signalsnew capability added to platform · new model introduced: GPT Image 2.5 Flare · new billing model: image tokens counted separately against AI credits · new admin control: image generation can be disabled via model policies · public preview availability across multiple Copilot tiers
suppression—
triage modelanthropic/claude-haiku-4.5 ($0.00000)
writer modelanthropic/claude-sonnet-4.5 ($0.00000)