tokevenClaude Haiku 4.5
Claude Haiku 4.5 is Claude's fastest and most affordable model, priced at $1.00/MTok input and $5.00/MTok output with a 200K context window.
Input $/MTok
$1.00
Output $/MTok
$5.00
Context window
200K
Cache read discount
90% off
Claude Haiku 4.5 pricing breakdown
| Rate | Input $/MTok | Output $/MTok |
|---|---|---|
| Standard | $1.00 | $5.00 |
| Cached read (90% off input) | $0.10 | - |
| Cached write (25% surcharge) | $1.25 | - |
| Batch (50% off) | $0.50 | $2.50 |
All rates in USD per million tokens. Prices verified against provider documentation.
Claude Haiku 4.5 task benchmarks
Confidence scores (0-100) and cross-provider rank for each task type. Rank 1 is best across all 20 models.
| Task | Confidence | Rank |
|---|---|---|
| Code Generation | 72/100 | #6 |
| Code Review | 70/100 | #7 |
| Summarization | 82/100 | #5 |
| Q&A | 86/100 | #4 |
| Extraction | 88/100 | #2 |
| Reasoning | 65/100 | #7 |
| Classification | 90/100 | #2 |
| Creative Writing | 60/100 | #7 |
Claude Haiku 4.5 cost by use case
Estimated cost per API call using default token counts for each workload.
| Use case | Input tokens | Output tokens | Cost / call |
|---|---|---|---|
| Code Generation | 2,000 | 4,000 | $0.0220 |
| Unit Test Generation | 3,000 | 5,000 | $0.0280 |
| SQL Generation | 1,500 | 1,000 | $0.006500 |
| API Generation | 3,000 | 6,000 | $0.0330 |
| Code Refactoring | 4,000 | 4,000 | $0.0240 |
| Code Review | 5,000 | 2,000 | $0.0150 |
| PR Review | 8,000 | 3,000 | $0.0230 |
| Security Review | 6,000 | 2,500 | $0.0185 |
| Bug Detection | 5,000 | 2,000 | $0.0150 |
| Document Summarization | 10,000 | 1,000 | $0.0150 |
| PDF Summarization | 15,000 | 1,500 | $0.0225 |
| Meeting Notes | 8,000 | 2,000 | $0.0180 |
Monthly cost projections
Projected monthly spend at different call volumes, using code generation as a representative workload (2,000 input / 4,000 output tokens per call).
| Calls / month | Without caching | With caching (90% read discount) |
|---|---|---|
| 1K | $22 | $20.74 |
| 10K | $220 | $207.4 |
| 100K | $2,200 | $2,074 |
| 500K | $11,000 | $10,370 |
| 1M | $22,000 | $20,740 |
Caching estimate assumes 70% of input tokens are cache reads. Your actual cache hit rate will depend on prompt structure and reuse.
Fast / Budget alternatives to Claude Haiku 4.5
Same-tier models from other providers, sorted by input price.
| Model | Provider | Input $/MTok | Output $/MTok | Input savings |
|---|---|---|---|---|
| GPT 5.6 Luna | GPT | $0.20 | $1.20 | 80% cheaper |
| Gemini 3.5 Flash-Lite | Gemini | $0.30 | $2.50 | 70% cheaper |
| Gemini 3 Flash | Gemini | $0.50 | $3.00 | 50% cheaper |
| Grok Build 0.1 | Grok | $1.00 | $2.00 | Same price |
| Gemini 3.5 Flash | Gemini | $1.50 | $9.00 | 50% more |
Other Claude models
Track your Claude Haiku 4.5 spend
See exactly how much you spend on Claude Haiku 4.5 and where you can save. Two-line wrapper install, no API keys shared.