Claude Haiku 4.5 (batch)
by Anthropic · anthropic/claude-haiku-4.5:batch · #234 cheapest of 422 paid models
Prices updated Sep 19, 2026, 5:27 PM 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
$0.50
per 1M tokens
Output
$2.50
per 1M tokens
Blended (3:1)
$1.00
3 input : 1 output
Cache read
$0.05
per 1M cached tokens
Cache write
$0.625
per 1M tokens
Cache & batch economics
Effective prices for Claude Haiku 4.5 (batch) with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $1.00 | $0.0535 | — |
| 50% | $0.831 | $0.031 | −42% |
| 90% | $0.696 | $0.013 | −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 | $0.001 | $1.00 |
| Document summary | 8,000 | 1,000 | $0.0065 | $6.50 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.02 | $20.00 |
| Long-context analysis | 150,000 | 5,000 | $0.0875 | $87.50 |
Performance
Intelligence Index
17.6
AA composite quality
Coding Index
43.9
Math Index
—
Agentic Index
10.3
Output speed
—
median
Time to first token
—
median
Time to first answer
—
after reasoning tokens
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 1,135 |
| UI components | 1,115 |
| Data viz | 1,139 |
| SVG | 1,049 |
| 3D | 1,101 |
| Game dev | 1,120 |
| Code categories | 1,130 |
| ASCII art | 1,159 |
Specs
Context window
200K
tokens
Max output
64K
tokens
Input modalities
text, image, file
Tokenizer
Claude