AiCostCompare

Claude Haiku 4.5 vs LFM2.5-24B-A2B

Side-by-side API pricing and Artificial Analysis performance for Claude Haiku 4.5 (Anthropic) and LFM2.5-24B-A2B (Liquid AI). Green cells mark the better value in each row.

Prices updated Nov 18, 2026, 12:29 AM UTC · refreshed nightly

Claude Haiku 4.5

Anthropic

LFM2.5-24B-A2B

Liquid AI

Pricing
Input $/1M$1.00$0.05
Output $/1M$5.00$0.70
Blended $/1M (3:1)$2.00$0.212
RAG example (30K in / 2K out)$0.04$0.0029
Quality & speed
Intelligence Index7.4—
Coding Index43.9—
Agentic Index8—
Output speed (tok/s)——
Time to first token——
Specs
Context window200K128K
Input modalitiestext, image, filetext

FAQ

Which is cheaper, Claude Haiku 4.5 or LFM2.5-24B-A2B?

LFM2.5-24B-A2B has the lower blended API price at $0.212 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), LFM2.5-24B-A2B costs about $0.0029 per request versus $0.04. Also compare context windows: Claude Haiku 4.5 offers 200K and LFM2.5-24B-A2B offers 128K.

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.