Claude 3.5 Haiku is 73% cheaper than Claude 3.5 Sonnet (v2) on blended 3:1 token pricing. Claude 3.5 Sonnet (v2) costs $3.00/1M in and $15.00/1M out, while Claude 3.5 Haiku costs $0.80/1M in and $4.00/1M out.
Claude 3.5 Sonnet (v2) vs Claude 3.5 Haiku
Compare verified input/output token rates, prompt caching discounts, latency tiers, and context limits between Anthropic and Anthropic.
| Metric / Feature | Claude 3.5 Sonnet (v2) (Anthropic) | Claude 3.5 Haiku (Anthropic) |
|---|---|---|
| Input Price ($ / 1M Tokens) | $3.00 | $0.80 |
| Output Price ($ / 1M Tokens) | $15.00 | $4.00 |
| Prompt Caching Input Rate | $0.300/1M | $0.080/1M |
| Blended 3:1 Rate (Production) | $6.000 / 1M | $1.600 / 1M |
| Max Context Window | 200k | 128k |
| Multimodal Vision | ✅ Supported | ❌ Text Only |
| MMLU Benchmark | 88.3% | 75.2% |
| Throughput & Latency | Fast (~50 t/s) | Ultra-Fast (~95 t/s) |
| Best For | Autonomous coding, complex tool use, multi-step agent reasoning | Real-time agents, code completion, fast document scanning |
When to Choose Claude 3.5 Sonnet (v2)
Choose Claude 3.5 Sonnet (v2) if your workload requires autonomous coding, complex tool use, multi-step agent reasoning. Ideal for teams needing Anthropic's infrastructure and ecosystem tooling.
When to Choose Claude 3.5 Haiku
Choose Claude 3.5 Haiku if your primary objective is real-time agents, code completion, fast document scanning. Ideal for scaling high-throughput pipelines with Anthropic.
Want to compare Claude 3.5 Sonnet (v2) against another model?
Select another target model to view immediate pricing & latency trade-offs.