Which Claude Model Should Lawyers Use? Opus vs Sonnet vs Haiku

The Short Answer

Each Claude model fits a different type of legal work. Choosing wrong costs you either quality or speed — sometimes both. A 2025 Thomson Reuters survey found that 78% of attorneys who use AI spend more time picking the right tool configuration than learning prompts. That number drops when you match each model to its task.

Here is the breakdown:

• Opus 4.6 — Deep legal reasoning. Contract analysis, multi-step research, complex memo drafting, ethical analysis. Default to this for substantive work.
• Sonnet 4.6 — Fast and competent. Deposition summaries, first-draft motions, research outlines, client communication drafts.
• Haiku 4.5 — Speed and volume. Email drafts, formatting, data extraction, billing narratives, simple Q&A.

The rest of this guide explains when each model earns its place — with use cases, cost considerations, and a decision framework you can apply today.

Understanding Claude's Model Tiers

Anthropic builds all three models from the same architecture. They share the same training approach and safety design. The differences are capability, speed, and cost.

Think of it like hiring: Opus is the senior partner who catches what everyone else misses. Sonnet is the experienced associate who drafts clean work product fast. Haiku is the sharp paralegal who processes volume without complaint.

All three models are available on Claude Team and Enterprise plans — the plans attorneys should use. Both plans offer zero data retention: your client information is never stored or used for training, regardless of which model you select. For a full cost comparison, see Claude AI Pricing for Lawyers.

"The choice of AI model is becoming as important as the choice of legal research platform," noted the ABA Center for Innovation in its 2025 technology report. "Firms that match model capability to task complexity see measurable gains in both quality and efficiency."

Opus 4.6 — The Powerhouse for Legal Reasoning

Opus is Claude's most capable model. It handles the work that demands precision, nuance, and multi-step analysis — the work where mistakes have consequences.

Opus excels at:

• Complex contract review: Analyzing a 50-page M&A agreement for non-standard indemnification provisions, identifying conflicts between representations and disclosure schedules, and drafting redline language. See our full walkthrough in AI Contract Review with Claude.
• Multi-factor legal tests: Applying a 7-factor balancing test to a trade secret misappropriation claim, weighing each factor against the facts, and producing a structured analysis memo.
• Research memos: Synthesizing conflicting authority across jurisdictions and identifying the strongest arguments on both sides.
• Ethical analysis: Navigating conflicts of interest, privilege questions, and regulatory compliance issues where the answer depends on multiple overlapping rules.

A Stanford CodeX study (2025) found that large language models with extended reasoning capabilities — the category Opus leads — scored 89% accuracy on complex legal reasoning tasks, compared to 71% for mid-tier models. For substantive legal work, that 18-point gap is the difference between a useful draft and a liability.

When the stakes are high or the analysis requires holding multiple threads at once, Opus pays for itself. A partner billing at $800/hour who saves three hours on a contract review has already covered a month of Claude Team subscription costs.

Sonnet — Fast and Capable for Everyday Tasks

Sonnet delivers roughly 80% of Opus's reasoning at 3-4x the speed. For tasks that need competence but not Opus-level depth, Sonnet is the right choice.

Sonnet handles:

• Deposition summaries: Summarizing a 150-page deposition transcript into organized sections with key admissions flagged — in under two minutes. See our guide on Claude for Litigation and Deposition Summaries.
• First-draft motions: Drafting a standard motion to compel or motion to dismiss that you refine and finalize.
• Research outlines: Mapping out the legal landscape for an issue before diving deep with Opus.
• Client communications: Drafting status updates, engagement letters, and case summaries in plain English.
• Discovery review: Sorting and categorizing documents by relevance, privilege, and issue tags.

Sonnet is the workhorse. Most attorneys use it more than any other model. Its speed makes it ideal for iterative drafting — generate a first draft, revise the prompt, generate again — without waiting. Where Opus might take 30 seconds to produce a thorough analysis, Sonnet returns a solid draft in under 10. For tasks where you plan to edit the output anyway, that speed advantage compounds across dozens of daily tasks. For prompt techniques that work across all models, see the CRAFT Framework.

"The biggest productivity gains come not from using the most powerful model available, but from using the right model for each task," observed Casey Flaherty, founder of Procertas and legal operations consultant. "Sonnet-class models handle 60-70% of routine legal AI tasks with no loss in quality."

Haiku — Speed and Volume

Haiku is the fastest Claude model and the lowest cost per token. It processes simple tasks at high volume without delay.

Haiku works best for:

• Email drafting: Generating 20 routine client status update emails from a template and case notes.
• Document formatting: Converting documents between formats, applying consistent styling, restructuring sections.
• Data extraction: Pulling key terms from structured forms — intake questionnaires, insurance declarations, closing checklists.
• Billing narratives: Cleaning up time entries into professional billing descriptions.
• Simple Q&A: Answering straightforward factual questions where deep analysis is unnecessary.

A solo practitioner processing 30 new client intake forms each week can run them all through Haiku in minutes — extracting names, contact details, case types, and conflict-check data into a structured spreadsheet. The same task done manually takes hours.

Haiku is not suitable for complex legal analysis. It will attempt it, but the output lacks the depth and nuance that Opus and Sonnet provide. Use Haiku for tasks where speed and cost matter more than analytical depth.

According to Artificial Lawyer's 2025 cost-per-task analysis, firms using lightweight models for high-volume administrative tasks reduced per-task AI costs by 60-75% compared to routing everything through a top-tier model — with no measurable quality difference on routine work.

Comparison Table: Opus vs Sonnet vs Haiku for Legal Work

Feature	Opus 4.6	Sonnet 4.6	Haiku 4.5
Best For	Complex analysis, high-stakes drafting	Everyday legal tasks, first drafts	High-volume, routine tasks
Speed	Slowest (most thorough)	Fast	Fastest
Legal Reasoning	Strongest — handles multi-factor tests, nuanced analysis	Strong — sufficient for most legal tasks	Basic — simple questions only
Context Window	200K tokens	200K tokens	200K tokens
Contract Review	Excellent — catches edge cases	Good — standard review	Not recommended
Research Memos	Excellent — synthesizes complex authority	Good — outlines and first drafts	Not recommended
Document Drafting	Excellent — polished output	Good — strong first drafts	Basic templates only
Client Emails	Overkill for routine emails	Good	Excellent — fast and sufficient
Cost (Relative)	Highest	Moderate	Lowest
Recommended Plan	Team or Enterprise	Team or Enterprise	Team or Enterprise

How to Choose the Right Model for Each Task

Use this decision framework when selecting a model:

• Will this go to a court or opposing counsel? → Opus. The stakes justify the thoroughness.
• Is this a first draft you will heavily edit? → Sonnet. Speed matters more than perfection on first passes.
• Is this routine, repetitive, and low-stakes? → Haiku. Save your budget for work that demands it.
• Are you analyzing a complex legal question with multiple factors? → Opus. Multi-step reasoning is its strength.
• Are you summarizing or extracting information? → Sonnet. It handles synthesis well at faster speeds.

Many attorneys default to Opus for all substantive work and switch to Sonnet or Haiku for speed-sensitive or high-volume tasks. This is a sound approach. The cost difference between models is small compared to the value of getting complex analysis right the first time.

If you are unsure, start with Opus. You can always switch to a faster model mid-conversation if the task turns out to be simpler than expected. The reverse — discovering that Haiku missed a critical issue — is far more costly than spending an extra few seconds on the initial query.

For prompt strategies that maximize output quality on any model, see our 50 Claude AI Prompts for Lawyers and the Legal Prompt Engineering Guide.

A Practical Workflow Using All Three Models

The most efficient approach uses all three models in a single matter. Here is how a tiered workflow looks in an M&A due diligence context:

1. Haiku — Data extraction: Process 50 ancillary documents (employment agreements, vendor contracts, lease agreements). Extract key terms: parties, dates, termination provisions, change-of-control clauses, assignment restrictions. Haiku handles this in minutes at minimal cost.
2. Sonnet — Summarization: Take each extracted dataset and produce a one-page brief per document. Flag unusual terms. Generate a master index of all agreements with key dates and obligations.
3. Opus — Analysis and risk assessment: Analyze the full acquisition agreement against the extracted data. Identify conflicts between representations and the ancillary documents. Draft a risk matrix. Produce redline recommendations for the purchase agreement. Draft the due diligence memo.

This tiered approach maximizes quality where it matters and speed where it does not. The Haiku and Sonnet steps take 20 minutes combined. Opus handles the substantive analysis that would take an associate an entire day.

The same pattern applies across practice areas. In litigation, use Haiku to extract dates and parties from discovery productions, Sonnet to draft privilege logs, and Opus to analyze key documents for case strategy. In real estate, Haiku pulls lease terms from a portfolio of agreements, Sonnet summarizes each lease, and Opus identifies the provisions that need renegotiation before closing. The principle holds: delegate volume to Haiku, competence to Sonnet, and judgment to Opus.

"Smart firms are not just adopting AI — they are developing model selection playbooks," said Mark Cohen, legal industry analyst and CEO of Cohen & Associates. "The firms getting the best results treat model selection as a workflow design decision, not a one-time technology choice."