AiCostCompare

Claude Haiku 4.5 vs Extract

Side-by-side API pricing and Artificial Analysis performance for Claude Haiku 4.5 (Anthropic) and Extract (Scaledown). Green cells mark the better value in each row.

Prices updated Nov 17, 2026, 12:02 PM UTC · refreshed nightly

Claude Haiku 4.5

Anthropic

Extract

Scaledown

Pricing
Input $/1M$1.00$0.04
Output $/1M$5.00Free
Blended $/1M (3:1)$2.00$0.03
RAG example (30K in / 2K out)$0.04$0.0012
Quality & speed
Intelligence Index7.4—
Coding Index43.9—
Agentic Index8—
Output speed (tok/s)——
Time to first token——
Specs
Context window200K1M
Input modalitiestext, image, filetext, image, file

FAQ

Which is cheaper, Claude Haiku 4.5 or Extract?

Extract has the lower blended API price at $0.03 per 1M tokens (3:1 input:output mix), versus $2.00 for the other model. Prices are live from OpenRouter and refresh nightly.

Which is better for RAG workloads?

For a typical RAG request (30K input / 2K output tokens), Extract costs about $0.0012 per request versus $0.04. Also compare context windows: Claude Haiku 4.5 offers 200K and Extract offers 1M.

Which scores higher on Artificial Analysis benchmarks?

Claude Haiku 4.5 leads on the Artificial Analysis Intelligence Index (7.4 vs —). Check coding and agentic indices on this page for workload-specific tradeoffs.