Fastest, most cost-efficient model for sub-second high-volume tasks
| Scenario | Input Tokens | Output Tokens | Uncached Cost | With Prompt Caching |
|---|---|---|---|---|
| Short Chat Query | 1,000 | 500 | $0.00350 | $0.00260 |
| Document Summarization | 10,000 | 2,000 | $0.0200 | $0.0110 |
| Codebase & Context Analysis | 100,000 | 20,000 | $0.2000 | $0.1100 |
| Batch Corpus Processing | 1,000,000 | 100,000 | $1.50 | $0.6000 |
Ideal for production workloads demanding budget capabilities, deep context depth (200k tokens), and reliability from Anthropic. Excellent when predictable tokenomics and prompt caching support are paramount.
If your use-case requires sub-second streaming latency or ultra-high frequency classification at micro-cent pricing, consider lighter budget options such as Gemini Flash-Lite or Claude Haiku. For deep formal logic, consider dedicated reasoning models like o3.
For Claude Haiku 4.5, 1 million input tokens costs $1.00, while 1 million output tokens costs $5.00. If using prompt caching, repetitive input prefixes are discounted to $0.10 per million.
Claude Haiku 4.5 features a maximum context window of 200,000 tokens (~150,000 words), with a maximum output limit of 8,192 tokens per completion.
Claude Haiku 4.5 utilizes the Anthropic Claude BPE (~65k vocabulary). Token counting on TokenMath runs client-side to ensure maximum privacy.
Yes. Claude Haiku 4.5 supports prompt caching with a cached input rate of $0.10/1M (saving up to 90% on repeated input context).