AiCostCompare

Claude Haiku 4.5 (batch)

by Anthropic · anthropic/claude-haiku-4.5:batch · #236 cheapest of 452 paid models

Prices updated Nov 17, 2026, 5:29 PM UTC · refreshed nightly

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 rateEffective blended $/1MExample 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

WorkloadInput tokensOutput tokensCost / requestCost / 1K requests
Short chat message500300$0.001$1.00
Document summary8,0001,000$0.0065$6.50
Codebase question (RAG)30,0002,000$0.02$20.00
Long-context analysis150,0005,000$0.0875$87.50

Performance

Intelligence Index

7.4

AA composite quality

Coding Index

43.9

Math Index

—

Agentic Index

8

Output speed

—

median

Time to first token

—

median

Time to first answer

—

after reasoning tokens

Design Arena Elo

CategoryElo
Website1,114
UI components1,088
Data viz1,121
SVG1,014
3D1,052
Game dev1,087
Code categories1,104
ASCII art1,123

Specs

Context window

200K

tokens

Max output

64K

tokens

Input modalities

text, image, file

Tokenizer

Claude