> ## Documentation Index
> Fetch the complete documentation index at: https://docs.apiyi.com/llms.txt
> Use this file to discover all available pages before exploring further.

# New FAQ: which reasoning effort values work for SVG generation

> A new FAQ explains that svg.reasoning.effort support depends on svg.model: mainstream author models accept six tiers while minimal returns 400, plus the flat-field trap and why reasoning_tokens cannot prove a tier took effect.

**2026/11/10 22:32 (UTC+8)** · Docs Update · OpenAI

📖 **New FAQ: which reasoning effort values work for SVG generation**

Which `svg.reasoning.effort` values you can send depends on `svg.model`: mainstream author models such as `gpt-5.6-terra` and `gpt-6-luna` accept `none` / `low` / `medium` / `high` / `xhigh` / `max`, and `minimal` returns 400 — it belongs to the original GPT-5 generation (`gpt-5` / `gpt-5-mini` / `gpt-5-nano`) and was replaced by `none` from `gpt-5.1` on.

The page also covers two traps: the field must be nested as `svg.reasoning.effort` (a flat top-level field neither errors nor takes effect), and `reasoning_tokens` varies widely on the same simple prompt, so it cannot prove a tier took effect.

📖 [Read the SVG reasoning FAQ](https://docs.apiyi.com/en/faq/gpt-image-svg-reasoning-effort.md)

***

← [Back to live updates](https://docs.apiyi.com/en/live.md) · 📚 [Monthly archive](https://docs.apiyi.com/en/live/archive.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.