AiCostCompare

Claude Haiku 4.5 vs Mi:dm K 3.0 Pro

Side-by-side API pricing and Artificial Analysis performance for Claude Haiku 4.5 (Anthropic) and Mi:dm K 3.0 Pro (Kt). Green cells mark the better value in each row.

Prices updated Nov 17, 2026, 1:27 PM UTC · refreshed nightly

Claude Haiku 4.5

Anthropic

Mi:dm K 3.0 Pro

Kt

Pricing
Input $/1M$1.00$0.20
Output $/1M$5.00$0.80
Blended $/1M (3:1)$2.00$0.35
RAG example (30K in / 2K out)$0.04$0.0076
Quality & speed
Intelligence Index7.4—
Coding Index43.9—
Agentic Index8—
Output speed (tok/s)——
Time to first token——
Specs
Context window200K262K
Input modalitiestext, image, filetext

FAQ

Which is cheaper, Claude Haiku 4.5 or Mi:dm K 3.0 Pro?

Mi:dm K 3.0 Pro has the lower blended API price at $0.35 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), Mi:dm K 3.0 Pro costs about $0.0076 per request versus $0.04. Also compare context windows: Claude Haiku 4.5 offers 200K and Mi:dm K 3.0 Pro offers 262K.

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.