Model Selection Strategy

You are mid-feature, the agent just produced a solid implementation plan, and now you need it to write the actual code. Do you stick with the default model or switch? You have heard Opus 4.6 is “the best” but it is also the most expensive. Sonnet 4.5 is cheaper but you are not sure if it can handle the complexity. Gemini 3 Pro has a massive context window but you have never tried it. Meanwhile, the model picker in Cursor shows eight options and zero guidance. This article gives you the decision framework so model selection becomes a two-second choice, not a five-minute debate.

What You’ll Walk Away With

• A clear default model recommendation (and why it is the default)
• A decision tree for when to switch models based on task type, not guesswork
• Cost-per-task estimates so you can budget your monthly usage
• Practical prompting adjustments for each model’s strengths
• The keyboard shortcut to switch models instantly without leaving your flow

The Quick Reference

Model	Input / Output Cost	Default Context	Max Context	Best For
Claude Opus 4.6	$5 / $25 per 1M tokens	200k	1M	Default for everything — best agentic performance
Claude Sonnet 4.5	$3 / $15 per 1M tokens	200k	1M	Budget-conscious daily work, large context needs
Gemini 3 Pro	$2 / $12 per 1M tokens	200k	1M	Extreme context, multimodal (image/diagram analysis)
GPT-5.2	$1.75 / $14 per 1M tokens	272k	—	Strong alternative, good for UI work
Composer 1	$1.25 / $10 per 1M tokens	200k	—	Speed-critical iteration in Cursor
Grok Code	$0.20 / $1.50 per 1M tokens	256k	—	Very budget-friendly simple tasks

Note

Cursor’s pricing is usage-based at API rates. Your Pro plan ($20/month) includes a budget of usage that gets consumed based on which models you use. Opus 4.6 burns through it faster than Sonnet 4.5 or Composer 1, but the quality difference on complex tasks is substantial.

Claude Opus 4.6: Your Default

Claude Opus 4.6 is the recommended default model for all coding work in Cursor. It has the highest SWE-Bench scores, the best agentic performance (it handles multi-step tool use reliably), and it produces the most architecturally sound code.

When to Use Opus 4.6

• Every task until you have a specific reason to switch
• Complex multi-file refactoring
• Architecture design and system planning
• Security audits and code review
• Test generation for nuanced business logic
• Any task where getting it right the first time saves more money than the model costs

Prompting Tips for Opus 4.6

Opus 4.6 benefits from high-level goals with constraints, rather than step-by-step micromanagement. Let it reason.

Copy-paste prompt for Opus 4.6 architecture work

Analyze the authentication system across all files in src/auth/ and src/middleware/.
Identify security vulnerabilities and architectural issues.
Propose a refactoring plan that addresses each issue.
Before implementing, explain your reasoning and ask if I want to adjust the approach.

Claude Sonnet 4.5: The Budget Workhorse

Sonnet 4.5 costs 40% less than Opus 4.6 on input tokens and 40% less on output tokens. For straightforward tasks — writing a utility function, adding a field to a form, generating standard CRUD endpoints — the quality difference is minimal.

When to Switch to Sonnet 4.5

• Routine coding where the pattern is well-established
• Tasks where you will review and iterate regardless
• When your monthly usage budget is running low
• Long conversations where you need Max mode (1M context) but want to manage cost

The Practical Test

If you can describe the task in one sentence and the expected output is predictable, Sonnet 4.5 will handle it. If the task requires weighing tradeoffs or understanding subtle architectural implications, stick with Opus 4.6.

Copy-paste prompt for Sonnet 4.5 utility work

Create a TypeScript utility function that debounces async functions.
It should support cancellation and return the result of the last invocation.
Include comprehensive tests using Vitest.

Gemini 3 Pro: The Context Specialist

Gemini 3 Pro’s headline feature is its 1M token context window (accessible via Max mode). When you need the AI to understand your entire codebase at once — not just the files you manually reference — Gemini 3 Pro is the model to reach for.

When to Switch to Gemini 3 Pro

• Analyzing large codebases (50k+ lines) where cross-module understanding matters
• Working with images — paste a screenshot of a UI bug or a Figma design directly into chat
• Reviewing architectural diagrams or documentation that includes visual elements
• Tasks where context volume matters more than reasoning depth

Multimodal Advantage

Gemini 3 Pro handles images natively. Drag a screenshot into the Cursor chat and ask it to reproduce the layout, identify the visual bug, or implement a design from a mockup.

Copy-paste prompt for Gemini 3 Pro visual work

I've attached a screenshot of our current dashboard. The spacing between the
metric cards is inconsistent and the chart legend overlaps on mobile.
Fix the responsive layout in src/components/Dashboard.tsx to match the
spacing from our design system (8px base grid).

GPT-5.2 and Composer 1: Specialized Roles

GPT-5.2 is a strong general-purpose model available natively in Cursor. It has a 272k default context window and performs well on frontend work, UI generation, and bug fixing. Use it when you want a different “perspective” — sometimes switching models unsticks a problem that one model keeps getting wrong.

Composer 1 is Cursor’s own model, optimized for speed within the editor. It completes most turns in under 30 seconds and costs significantly less than the frontier models. Use it for rapid iteration: quick style changes, small refactors, and tasks where you are going to iterate five times anyway.

The Decision Tree

When a new task comes in, run through this:

1. Is this a complex, multi-file task or architectural decision?

   Yes: Use Claude Opus 4.6. The reasoning quality pays for itself.

2. Is this a simple, well-defined task with predictable output?

   Yes: Use Claude Sonnet 4.5 or Composer 1 (if speed matters).

3. Do I need to analyze more than 200k tokens of context?

   Yes: Use Gemini 3 Pro with Max mode, or Claude models in Max mode.

4. Am I working with images, screenshots, or diagrams?

   Yes: Use Gemini 3 Pro for its native multimodal support.

5. Am I stuck and the current model keeps making the same mistake?

   Yes: Switch to a different model. GPT-5.2 or a different Claude model often approaches the problem differently.

Switching Models in Cursor

The model picker is in the agent panel, right next to the mode selector. You can switch models mid-conversation — the new model picks up the existing context.

Keyboard shortcut: Press Cmd+. (macOS) or Ctrl+. (Windows/Linux) to quickly cycle through modes. For model selection, click the model name in the agent panel.

Auto Mode

Cursor offers an Auto setting that automatically selects the best model for each request based on the task complexity and current API availability. Auto uses blended pricing ($1.25 input, $6.00 output per 1M tokens) and handles model degradation automatically — if one model’s API is slow, it routes to another.

For beginners, Auto is a reasonable starting point. Once you develop a feel for which model suits which task, manual selection gives you more control and often better results.

Cost Optimization in Practice

Typical Monthly Usage Patterns

Developer Style	Primary Model	Monthly Cost Estimate
All Opus 4.6	Claude Opus 4.6	$100-200
Mixed (recommended)	Opus for complex, Sonnet/Composer for routine	$60-120
Budget-conscious	Sonnet 4.5 + Composer 1	$30-60

Cost-Saving Strategies

1. Start conversations fresh — long conversations accumulate context that costs money on every message
2. Use @ references instead of pasting large blocks of code — Cursor handles file references more efficiently
3. Switch to Composer 1 for iteration — if you are going to send 10 messages tweaking CSS, the cheap model is fine
4. Enable Max mode only when needed — do not leave it on permanently

When This Breaks

Model seems to have gotten worse: Models do not regress, but API performance varies. If a model is producing lower-quality output than usual, try the same prompt 10 minutes later or switch to a different model temporarily.

Switching models mid-conversation loses context: This is rare but can happen with very long conversations. If you notice degraded quality after a switch, start a new chat with the new model and reference specific files.

Auto mode keeps selecting a model you dislike: Disable Auto and select manually. The two seconds it takes to choose a model are worth the consistency.

Usage runs out before month end: Check your usage in Settings. If you are burning through Opus 4.6 tokens on tasks that Sonnet 4.5 could handle, shift your default for routine work.

What’s Next

Project Rules Set up .cursor/rules/ so the AI generates code that matches your team's conventions from the very first prompt.