Claude Haiku 3.5 vs Voyage Large 2
Compare Claude Haiku 3.5 and Voyage Large 2: pricing, performance, context window, latency, and best use cases. Side-by-side comparison on XALEN.
Updated 2026-05-21 · By Abhishek Raj · Our methodology
| Feature | Claude Haiku 3.5 | Voyage Large 2 |
|---|---|---|
| Category | Compact | Embedding |
| Parameters | ~20B | ~500M |
| Context Window | 200K | 16K |
| Input Price | $0.008/1M tokens | $0.002/1M tokens |
| Output Price | $0.04/1M tokens | N/A/1M tokens |
| Latency | ~150ms | ~25ms |
Choose Claude Haiku 3.5 when:
- ✓ High-volume APIs
- ✓ Fast chatbots
- ✓ Content moderation
Very fast, Low cost, 200K context
Choose Voyage Large 2 when:
- ✓ Code search
- ✓ Long document RAG
- ✓ Semantic matching
16K context, High quality, Good for code
Verdict: Claude Haiku 3.5 vs Voyage Large 2
For cost efficiency, Voyage Large 2 wins at $0.002/1M input tokens. For speed, Claude Haiku 3.5 is faster at ~150ms. Claude Haiku 3.5 excels at High-volume APIs while Voyage Large 2 is better for Code search. Both are available on XALEN through a single API — try them in the Playground to see which fits your workload.
Detailed Analysis
Pricing Comparison
Claude Haiku 3.5 costs $0.008/1M input tokens and $0.04/1M output tokens. Voyage Large 2 costs $0.002 input and N/A output. Voyage Large 2 is 4.0x cheaper on input tokens. XALEN offers batch processing at 50% discount on both models.
Performance & Context
Claude Haiku 3.5 has a 200K context window with ~150ms latency. Voyage Large 2 offers 16K context at ~25ms. Claude Haiku 3.5 has the larger context window.
Best For
Claude Haiku 3.5 (Compact) is optimized for: High-volume APIs, Fast chatbots, Content moderation. Voyage Large 2 (Embedding) works best for: Code search, Long document RAG, Semantic matching.
Try Both on XALEN
Both models are available through XALEN's OpenAI-compatible API. Switch between them by changing the model parameter:
from xalen import XALEN
client = XALEN(api_key="xln_test_YOUR_KEY")
# Use Claude Haiku 3.5
response_a = client.chat.completions.create(
model="claude-haiku-3-5",
messages=[{"role": "user", "content": "Your question here"}]
)
# Use Voyage Large 2
response_b = client.chat.completions.create(
model="voyage-large-2",
messages=[{"role": "user", "content": "Your question here"}]
)Frequently Asked Questions
Which is better, Claude Haiku 3.5 or Voyage Large 2?
Claude Haiku 3.5 (Compact, ~20B) offers Very fast. Voyage Large 2 (Embedding, ~500M) offers 16K context. Choose Claude Haiku 3.5 for High-volume APIs or Voyage Large 2 for Code search.
How much does Claude Haiku 3.5 cost vs Voyage Large 2?
Claude Haiku 3.5: $0.008/1M input, $0.04/1M output. Voyage Large 2: $0.002/1M input, N/A/1M output. Both available on XALEN with batch processing at 50% discount.
Can I use both models on XALEN?
Yes. XALEN provides 200+ models through a single OpenAI-compatible API. Switch between Claude Haiku 3.5 and Voyage Large 2 by changing the model parameter. No code changes needed.
Related Comparisons
Last updated: 2026-05-21. Pricing and specifications may change. Check pricing page for latest rates.