Can Claude Opus 5.5 Generate Images? We Asked It for Pixel Art

What Opus 5.5 can and cannot make

Anthropic released Claude Opus 5.5 on September 22, 2026. Its announcement is about coding, knowledge work, computer use and cost: $4 per million input tokens and $20 per million output tokens. It does not describe an image generator.

What Opus 5.5 can do is write code that draws: an SVG file, an HTML canvas, a small script. For logos, icons and pixel art, that is useful, because code places every shape exactly where it says. For a photo, a painting or a soft illustration, use an image model.

The test: a 32 × 32 mascot

We asked for one sprite with hard limits we could check afterwards: a 32 × 32 grid, one square per pixel, at most eight colours, a transparent background and no text. We used Opus 5.5 at the Medium effort level in claude.ai.

Draw a 32 x 32 pixel-art sprite of the mascot for Rook & Rabbit, a board-game cafe: a white rabbit hugging a black chess rook, facing right, on a transparent background. Draw it as one SVG with viewBox="0 0 32 32" and shape-rendering="crispEdges", where every pixel is one 1x1 <rect> on the integer grid. Use at most 8 colours, including a dark outline colour. No text. Reply with the SVG code only, in one code block.

It looked at its own drawing four times

Before it answered, Opus 5.5 turned its SVG into a picture and looked at the result. The step list shows four rounds: a first draft, a revised sprite, a patch for gaps and paws, and a hand-composed version, each followed by reading the rendered file. The whole answer took a little over a minute.

That loop is the main reason the result holds together. A model that writes code for a picture without seeing it tends to leave gaps and stray pixels.

What we measured

We copied the SVG, 26,444 bytes, and counted it with a script. It holds 629 squares, every one exactly 1 × 1 on the integer grid, with no duplicates and nothing outside the 32 × 32 frame. It uses 6 colours, under the limit of 8, and the unused pixels are transparent.

Compare that with “pixel art” from an image model. In our photo-to-pixel-art test the same day, a generated image that looked like pixel art held 173,508 distinct colours and blocks of uneven size. Code gives you the grid by construction.

Where it falls short

Look at the arms. At this size the rabbit's hug reads as two white bars across the rook, and most of the rook hides behind the body. A pixel artist would cheat the pose to keep both characters readable; the model kept to the literal brief.

The file is also heavy for what it is: 26,444 bytes of SVG for a picture that saves as a PNG of a few hundred bytes. Export it to PNG at 1× and at a whole-number scale before you use it in a game or on a website.

When to use a code model and when to use an image model

Use Opus 5.5 or another code model when the grid has to be exact: sprites, icons, simple logos, patterns you will edit by hand. Use an image model when you need texture, light, a photo or a full scene. In Ciyo, GPT Image 2.5 Flare and Sunburst make the pictures; Ciyo does not run Claude Opus 5.5.

The two also work together. You can draw the sprite as code and then use an image model for the poster or the shop sign around it.

• Turn a photo into real pixel art
• Can Claude Opus 5.5 draw an SVG logo?
• Claude Opus 5.5 pricing, worked out on a real job
• Anthropic: Introducing Claude Opus 5.5