# Aider v0.73.0: full o3-mini support and `--reasoning-effort`

> Aider gains full o3-mini support plus a `--reasoning-effort` argument (low/medium/high). Adds a `remove_reasoning` model setting to strip model-specific reasoning tags from responses, and hardens turn ordering to avoid R1 errors.

| | |
|---|---|
| **Tool** | Aider |
| **Version** | v0.73.0 |
| **Kind** | release |
| **Published** | 2025-01-31 |
| **Observed** | 2026-08-11 |
| **Significance** | 3/5 |
| **Breaking** | no |
| **Categories** | model-support, feature, fix |

## What changed


- Full o3-mini support: `aider --model o3-mini`
- New `--reasoning-effort` argument: low, medium, high
- New `remove_reasoning: tagname` model setting strips model-specific reasoning tags from responses
- R1 free on OpenRouter: `--model openrouter/deepseek/deepseek-r1:free`
- User/assistant turn order enforced to avoid R1 errors
- Better messaging around context window size limits, with Ollama-specific guidance
- Parent directories auto-created when creating new files
- Case-insensitive model name matching, original case preserved
- Fixed model metadata for `openrouter/deepseek/deepseek-r1`


## Sources

- [github_release](https://github.com/Aider-AI/aider/releases/tag/v0.73.0) — retrieved 2026-08-11

## Community

_No curated reactions recorded. Facts and community takes are kept in separate layers
and never blended._

---
Canonical: https://changelogs.info/aider/v0-73-0
Entity: https://changelogs.info/aider
Event ID: `evt_2025-01-31_aider_v0-73-0`
Licence: event synthesis © changelogs.info, CC BY 4.0. Linked sources belong to their vendors.