# Cursor Agent Models (May 2026)

Full model list from `agent models` on Dell Precision 5810 (Debian 13), authenticated as tw24fr@gmail.com.

## Claude Models

| Model ID | Description |
|----------|-------------|
| `claude-opus-4-7-max` | Opus 4.7 1M Max |
| `claude-opus-4-7-max-fast` | Opus 4.7 1M Max Fast |
| `claude-opus-4-7-xhigh` | Opus 4.7 1M Extra High |
| `claude-opus-4-7-xhigh-fast` | Opus 4.7 1M Fast |
| `claude-opus-4-7-high` | Opus 4.7 1M High |
| `claude-opus-4-7-high-fast` | Opus 4.7 1M High Fast |
| `claude-opus-4-7-medium` | Opus 4.7 1M Medium |
| `claude-opus-4-7-medium-fast` | Opus 4.7 1M Medium Fast |
| `claude-opus-4-7-low` | Opus 4.7 1M Low |
| `claude-opus-4-7-low-fast` | Opus 4.7 1M Low Fast |
| `claude-opus-4-7-thinking-max` | Opus 4.7 1M Max Thinking |
| `claude-opus-4-7-thinking-max-fast` | Opus 4.7 1M Max Thinking Fast |
| `claude-opus-4-7-thinking-xhigh` | Opus 4.7 1M Extra High Thinking |
| `claude-opus-4-7-thinking-xhigh-fast` | Opus 4.7 1M Thinking Fast |
| `claude-opus-4-7-thinking-high` | Opus 4.7 1M High Thinking |
| `claude-opus-4-7-thinking-high-fast` | Opus 4.7 1M High Thinking Fast |
| `claude-opus-4-7-thinking-medium` | Opus 4.7 1M Medium Thinking |
| `claude-opus-4-7-thinking-medium-fast` | Opus 4.7 1M Medium Thinking Fast |
| `claude-opus-4-7-thinking-low` | Opus 4.7 1M Low Thinking |
| `claude-opus-4-7-thinking-low-fast` | Opus 4.7 1M Low Thinking Fast |
| `claude-4.6-opus-max` | Opus 4.6 1M Max |
| `claude-4.6-opus-max-thinking` | Opus 4.6 1M Max Thinking |
| `claude-4.6-opus-max-thinking-fast` | Opus 4.6 1M Max Thinking Fast |
| `claude-4.6-opus-high` | Opus 4.6 1M |
| `claude-4.6-opus-high-thinking` | Opus 4.6 1M Thinking |
| `claude-4.6-opus-high-thinking-fast` | Opus 4.6 1M Thinking Fast |
| `claude-4.5-opus-high` | Opus 4.5 |
| `claude-4.5-opus-high-thinking` | Opus 4.5 Thinking |
| `claude-4.6-sonnet-medium` | Sonnet 4.6 1M |
| `claude-4.6-sonnet-medium-thinking` | Sonnet 4.6 1M Thinking |
| `claude-4.5-sonnet` | Sonnet 4.5 |
| `claude-4.5-sonnet-thinking` | Sonnet 4.5 Thinking |
| `claude-4-sonnet` | Sonnet 4 |
| `claude-4-sonnet-thinking` | Sonnet 4 Thinking |

## GPT-5.x Models

| Model ID | Description |
|----------|-------------|
| `gpt-5.5-extra-high` | GPT-5.5 1M Extra High |
| `gpt-5.5-extra-high-fast` | GPT-5.5 Extra High Fast |
| `gpt-5.5-high` | GPT-5.5 1M High |
| `gpt-5.5-high-fast` | GPT-5.5 High Fast |
| `gpt-5.5-medium` | GPT-5.5 1M |
| `gpt-5.5-medium-fast` | GPT-5.5 Fast |
| `gpt-5.5-low` | GPT-5.5 1M Low |
| `gpt-5.5-low-fast` | GPT-5.5 Low Fast |
| `gpt-5.5-none` | GPT-5.5 1M None |
| `gpt-5.5-none-fast` | GPT-5.5 None Fast |
| `gpt-5.4-xhigh` | GPT-5.4 1M Extra High |
| `gpt-5.4-xhigh-fast` | GPT-5.4 Extra High Fast |
| `gpt-5.4-high` | GPT-5.4 1M High |
| `gpt-5.4-high-fast` | GPT-5.4 High Fast |
| `gpt-5.4-medium` | GPT-5.4 1M |
| `gpt-5.4-medium-fast` | GPT-5.4 Fast |
| `gpt-5.4-low` | GPT-5.4 1M Low |
| `gpt-5.2-xhigh` | GPT-5.2 Extra High |
| `gpt-5.2-xhigh-fast` | GPT-5.2 Extra High Fast |
| `gpt-5.2-high` | GPT-5.2 High |
| `gpt-5.2-high-fast` | GPT-5.2 High Fast |
| `gpt-5.2-medium` | GPT-5.2 |
| `gpt-5.2-fast` | GPT-5.2 Fast |
| `gpt-5.2-low` | GPT-5.2 Low |
| `gpt-5.2-low-fast` | GPT-5.2 Low Fast |
| `gpt-5.1-high` | GPT-5.1 High |
| `gpt-5.1` | GPT-5.1 |
| `gpt-5.1-low` | GPT-5.1 Low |

## GPT-5.x Mini & Nano

| Model ID | Description |
|----------|-------------|
| `gpt-5.4-mini-xhigh` | GPT-5.4 Mini Extra High |
| `gpt-5.4-mini-high` | GPT-5.4 Mini High |
| `gpt-5.4-mini-medium` | GPT-5.4 Mini |
| `gpt-5.4-mini-low` | GPT-5.4 Mini Low |
| `gpt-5.4-mini-none` | GPT-5.4 Mini None |
| `gpt-5.4-nano-xhigh` | GPT-5.4 Nano Extra High |
| `gpt-5.4-nano-high` | GPT-5.4 Nano High |
| `gpt-5.4-nano-medium` | GPT-5.4 Nano |
| `gpt-5.4-nano-low` | GPT-5.4 Nano Low |
| `gpt-5.4-nano-none` | GPT-5.4 Nano None |
| `gpt-5-mini` | GPT-5 Mini (current) |

## Codex Models

| Model ID | Description |
|----------|-------------|
| `gpt-5.3-codex-xhigh` | Codex 5.3 Extra High |
| `gpt-5.3-codex-xhigh-fast` | Codex 5.3 Extra High Fast |
| `gpt-5.3-codex-high` | Codex 5.3 High |
| `gpt-5.3-codex-high-fast` | Codex 5.3 High Fast |
| `gpt-5.3-codex` | Codex 5.3 |
| `gpt-5.3-codex-fast` | Codex 5.3 Fast |
| `gpt-5.3-codex-low` | Codex 5.3 Low |
| `gpt-5.3-codex-low-fast` | Codex 5.3 Low Fast |
| `gpt-5.2-codex-xhigh` | Codex 5.2 Extra High |
| `gpt-5.2-codex-xhigh-fast` | Codex 5.2 Extra High Fast |
| `gpt-5.2-codex-high` | Codex 5.2 High |
| `gpt-5.2-codex-high-fast` | Codex 5.2 High Fast |
| `gpt-5.2-codex` | Codex 5.2 |
| `gpt-5.2-codex-fast` | Codex 5.2 Fast |
| `gpt-5.2-codex-low` | Codex 5.2 Low |
| `gpt-5.2-codex-low-fast` | Codex 5.2 Low Fast |
| `gpt-5.1-codex-max-xhigh` | Codex 5.1 Max Extra High |
| `gpt-5.1-codex-max-xhigh-fast` | Codex 5.1 Max Extra High Fast |
| `gpt-5.1-codex-max-high` | Codex 5.1 Max High |
| `gpt-5.1-codex-max-high-fast` | Codex 5.1 Max High Fast |
| `gpt-5.1-codex-max-medium` | Codex 5.1 Max |
| `gpt-5.1-codex-max-medium-fast` | Codex 5.1 Max Medium Fast |
| `gpt-5.1-codex-max-low` | Codex 5.1 Max Low |
| `gpt-5.1-codex-max-low-fast` | Codex 5.1 Max Low Fast |
| `gpt-5.1-codex-mini-high` | Codex 5.1 Mini High |
| `gpt-5.1-codex-mini` | Codex 5.1 Mini |
| `gpt-5.1-codex-mini-low` | Codex 5.1 Mini Low |

## Other Models

| Model ID | Description |
|----------|-------------|
| `gemini-3.1-pro` | Gemini 3.1 Pro |
| `gemini-3-flash` | Gemini 3 Flash |
| `grok-4.3` | Grok 4.3 1M |
| `kimi-k2.5` | Kimi K2.5 |
| `composer-2` | Composer 2 |
| `composer-2-fast` | Composer 2 Fast (default) |
| `auto` | Auto (let Cursor choose) |

## Speed Levels Explained

Models follow a naming convention: `<family>-<variant>-<speed>-<thinking?>`

| Speed level | Quality | Speed | Use case |
|-------------|---------|-------|----------|
| `max` | Highest | Slowest | Complex architecture |
| `xhigh` / `extra-high` | Very high | Slow | Deep reasoning |
| `high` | High | Medium | General coding |
| `medium` | Balanced | Fast | Quick edits |
| `low` | OK | Fastest | Simple queries |
| `none` | Lowest | Fastest | Trivial completions |

The `-fast` suffix means the same quality but with a tighter reasoning budget (faster response).

## Key Recommendations

- **Best coding:** `claude-opus-4-7-thinking-xhigh` or `gpt-5.3-codex-xhigh`
- **Fast coding:** `gpt-5.3-codex-high-fast` or `composer-2-fast`
- **Cheapest quality:** `gpt-5-mini` (current default)
- **Planning/review:** `claude-opus-4-7-thinking-max`