Claude Haiku 4.5
by Anthropic · anthropic/claude-haiku-4.5 · #228 cheapest of 325 paid models
Prices updated Jul 22, 2026, 2:41 AM UTC · refreshed hourly
Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...
Compare vs:GPT-5.6 SolGPT-5.6 TerraGPT-4.1GPT-4.1 Mini
Pricing
Input
$1.00
per 1M tokens
Output
$5.00
per 1M tokens
Blended (3:1)
$2.00
3 input : 1 output
Cache read
$0.10
per 1M cached tokens
Cache write
$1.25
per 1M tokens
Cache & batch economics
Effective prices for Claude Haiku 4.5 with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $2.00 | $0.107 | — |
| 50% | $1.66 | $0.062 | −42% |
| 90% | $1.39 | $0.026 | −76% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates for this provider’s batch API. Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.002 | $2.00 |
| Document summary | 8,000 | 1,000 | $0.013 | $13.00 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.04 | $40.00 |
| Long-context analysis | 150,000 | 5,000 | $0.175 | $175.00 |
Performance
Intelligence Index
29.6
AA composite quality
Coding Index
43.9
Math Index
—
Agentic Index
16.4
Output speed
—
median
Time to first token
—
median
Time to first answer
—
after reasoning tokens
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 1,149 |
| UI components | 1,142 |
| Data viz | 1,160 |
| SVG | 1,072 |
| 3D | 1,131 |
| Game dev | 1,155 |
| Code categories | 1,148 |
| ASCII art | 1,182 |
Specs
Context window
200K
tokens
Max output
64K
tokens
Input modalities
text, image, file
Tokenizer
Claude