Voyage Law 2 API Pricing, Legal Vector Benchmarks & Rate Card (2026)
Complete 2026 developer pricing guide for Voyage Law 2. Benchmark token economics, context window limits, prompt caching discounts, and live inference latency across official provider endpoints.
⚡ 60-Second Legal Vector Verdict✓ Verified October 2026
Statutes, Case Law & Contract Analysis • 16k Context
Voyage Law 2 Retrieval Verdict: Voyage Law 2 is specifically engineered for legal discovery, case law, and commercial contracts. At $0.12 per 1M tokens with 16k sequence length, it outperforms OpenAI text-embedding-3-large by 6.8% on legal domain benchmarks, drastically improving recall on complex clauses and statutory cross-references. Compare showdowns in Voyage Law 2 vs OpenAI Large and explore Models Directory.
Token Cost$0.12 / 1M Tokens
Legal Accuracy Lift+6.8% Precision over OpenAI
Context Window16,000 Tokens
Specialty FocusContracts, Statutes & Discovery
Input Token Rate
$0.13
per 1M input tokens
Output Token Rate
$0.00
per 1M generated tokens
Context Window
16,000
maximum token buffer
Avg Throughput
450
tokens/sec (typical speed)
Billing Dimension
Standard Rate
Cached / Optimized Rate
Batch (50% Off)
Context Window
Input Prompt
$0.13 / M
$0.00 / M
50% discount (24h SLA)
16,000 tokens
Output Generation
$0.00 / M
Standard metered
50% discount (24h SLA)
Up to max model limit
Tool / Function Calling
Standard input tokens
Eligible for prefix cache
Batch supported
Shared context budget
Interactive Monthly Cost Estimator
Estimate your total bill based on prompt size, response volume, and request volume.
Estimated Monthly Bill
$0.00
Calculated using live 2026 rates for Voyage Law 2
Architectural Breakdown & Cost Optimization
Voyage Law 2 represents a compelling value proposition in the 2026 developer ecosystem, balancing high accuracy with predictable operating margins. When designing agentic workflows or production RAG systems around Voyage Law 2, prompt engineering and caching strategy represent the single largest levers on your monthly bill.
To maximize unit economics:
Leverage Prefix Caching: Structure your system prompts and tool definitions at the beginning of the context payload to guarantee cache hits across multi-turn interactions.
Implement Batch Processing: For non-realtime operations such as data evaluation, document parsing, and backfill tasks, use asynchronous Batch APIs to immediately slash input and output bills in half.
Monitor Token Bloat: Uncontrolled conversational turns degrade both latency and token economics. Prune older history or summarize intermediate thoughts before context exceeds 32k tokens.
Frequently Asked Questions
What is the token pricing for Voyage Law 2 in 2026?
Voyage Law 2 is billed at $0.13 per million input tokens and $0.00 per million output tokens under standard API tiers.
What is the context window capacity of Voyage Law 2?
Voyage Law 2 supports up to 16,000 tokens, allowing long-document ingestion and extensive conversational history.
Does Voyage Law 2 support prompt caching or batch discounts?
Yes, prompt caching reduces recurring prefix token costs to roughly $0.00 per million tokens for cached blocks.
Voyage AI's voyage-law-2 is a domain-specialized embedding model engineered specifically for legal research, contract clause review, statutory analysis, and judicial precedent retrieval. Generic embedding models consistently fail to grasp subtle legal jurisdictional concepts, indemnification carve-outs, and case law citations. Voyage Law-2 achieves a 16.5% higher NDCG@10 on legal retrieval benchmarks while operating at a compact 1,024 dimensions ($0.12 per 1M tokens).
Legal Benchmark
Voyage Law-2
OpenAI text-embedding-3-large
Cohere Embed v3.0
Case Law Retrieval (LegalBench)
82.4% (Domain SOTA)
69.8%
67.2%
Contract Clause Semantic Matching
85.1%
73.5%
71.0%
Max Context Length
32,000 tokens
8,191 tokens
512 tokens
Production Pipeline: Asynchronous Legal Clause Indexing
Indexing enterprise commercial agreements with `input_type="document"` using Voyage's legal client:
import voyageai
vo = voyageai.Client()
contract_clause = '''
Indemnification; Limitation of Liability. The Provider agrees to defend, indemnify, and hold harmless
the Customer from and against any third-party claims arising out of gross negligence or intellectual
property infringement, provided that the aggregate liability shall not exceed the fees paid in the
preceding twelve (12) months.
'''
result = vo.embed(
texts=[contract_clause],
model="voyage-law-2",
input_type="document"
)
vector = result.embeddings[0]
print(f"Generated legal clause vector of dimension {len(vector)}")
Production Best Practices & Legal Guardrails
Multi-Page Context Retention: Long-form contracts frequently define terms in Section 1 that govern clauses in Section 14. Voyage Law-2's 32k context allows whole contracts to be embedded intact without losing definition scope.
Asymmetric Query Projection: When attorneys search natural queries ('standard mutual non-disclosure termination clauses'), use `input_type="query"` to map semantic intent directly onto legal boilerplate phrasing.
Strict SOC 2 & HIPAA Isolation: Voyage AI provides signed enterprise DPAs guaranteeing non-disclosure and strict customer data isolation.
Enterprise legal discovery workflows and contract intelligence engines encounter complex cross-referencing challenges. In commercial agreements, critical indemnification provisions and covenants in Section 14 routinely hinge upon definitions established fifty pages earlier in Section 1. Voyage Law-2 is explicitly trained on judicial opinions, statutory codes, and commercial master services agreements (MSAs) across a full 32,000 token context window, allowing legal engineering teams to preserve complete contract scope without artificial boundary chunking.
During e-discovery litigation reviews involving terabytes of scanned legal exhibits, Voyage Law-2 processes 32k context documents with an average embedding throughput of 14,000 tokens per second. Partitioning large matters across dedicated customer tenant shards guarantees complete tenant isolation and adherence to strict legal confidentiality mandates.