Claude 3.5 Haiku
AnthropicFast, cost-effective model for high-volume tasks. Great for code review and simple queries.
Claude 3.5 Haiku Pricing
| Token Type | Price per Million |
|---|---|
| Input tokens | $0.800 |
| Output tokens | $4.00 |
| Cache read tokens | $0.080 |
| Cache creation tokens | $1.00 |
Estimated Cost by Project Size
Realistic cost estimates for common coding scenarios. Assumes 30% cache hit rate where caching is available.
| Scenario | Token Usage | Estimated Cost |
|---|---|---|
| Small Script (1K lines) | 50K input / 30K output | $0.16 |
| Medium Feature (10K lines) | 500K input / 200K output | $1.24 |
| Large Project (50K lines) | 2,500K input / 1,000K output | $6.21 |
| Code Review (5K lines) | 250K input / 25K output | $0.32 |
Benchmark Performance — Claude 3.5 Haiku
Third-party benchmark scores normalized to 0-100 scale. Higher is better. Aggregated scores from published third-party benchmarks. SWE-bench measures real GitHub issue resolution. LiveCodeBench measures competitive programming ability. HumanEval measures basic code generation. BigCodeBench measures practical, multi-step coding tasks. All scores normalized to 0-100 scale.
Sources: SWE-bench Verified, LiveCodeBench, HumanEval, BigCodeBench
Get Access to Claude 3.5 Haiku
Ready to start using Claude 3.5 Haiku? Get API access directly from Anthropic.
How Does Claude 3.5 Haiku Compare?
| Model | Input ($/M) | Medium Feature Cost | |
|---|---|---|---|
| Claude 3.5 Haiku | $0.800 | $1.24 | selected |
| Qwen Coder Plus | $0.800 | $1.08 | Compare |
| Claude 4 Haiku | $0.800 | $1.24 | Compare |
| Claude Sonnet 4 Lite | $1.00 | $1.55 | Compare |
| DeepSeek Reasoner (R1) | $0.550 | $0.63 | Compare |
| GPT-3.5 Turbo | $0.500 | $0.48 | Compare |
Related Models
Claude Sonnet 4
AnthropicAnthropic's balanced model for coding and general tasks. Best price-performance ratio in the Claude family.
Claude Opus 4
AnthropicAnthropic's most powerful model. Best for complex reasoning and challenging coding tasks.
Claude 3.5 Sonnet
AnthropicPrevious generation Sonnet. Still excellent for coding tasks at the same price point.
Claude 3 Opus
AnthropicFirst generation Opus. Highest reasoning capability in the Claude 3 family.