跳转到主要内容
2026/11/16 20:13 (UTC+8) · Model Status · OpenAI ⚠️ gpt-image-2.6-all SVG output falls short — SVG is better served by the “write code” route A user reported that SVG from -all is not usable; our retest confirms it. output_format=svg does return real vectors, but no writer model is involved. The cause is the route. gpt-image-2.6-all is the reverse-engineered ChatGPT web pipeline: SVG comes straight from the image model, and the svg.model field is accepted but ignored (documented on the model page), so you cannot point it at a stronger writing model. Official-relay gpt-image-2.6-sunburst / gpt-image-2.6-flare take a different path: svg.model (for example gpt-5.6-terra) writes the SVG code first and returns it as a vector — code is the image, with much better control over structure and text. Options, by use case:
  • Official relay gpt-image-2.6-sunburst / gpt-image-2.6-flare: choose the writing model with svg.model, tune svg.reasoning.effort, billed by tokens
  • A text model writes the SVG: gpt-5.6-terra / gpt-6-luna emit <svg> code, fully controllable
  • gpt-image-2.6-all: still returns SVG, but the svg object has no effect and quality falls short; good for a quick preview
APIYI is also evaluating conversational SVG generation and image-to-SVG for AI Image Master; we will post updates here. 📖 Docs: GPT-Image-2.6-All overview · GPT Image 2.6 official relay · SVG reasoning effort FAQ
← Back to Live Updates · 📚 Monthly archive