AiCostCompare

Claude Haiku 4.5 vs DeepSeek V3 0324

Side-by-side API pricing and Artificial Analysis performance for Claude Haiku 4.5 (Anthropic) and DeepSeek V3 0324 (DeepSeek). Green cells mark the better value in each row.

Prices updated Nov 16, 2026, 12:45 AM UTC · refreshed nightly

Claude Haiku 4.5

Anthropic

DeepSeek V3 0324

DeepSeek

Pricing
Input $/1M$1.00$0.29
Output $/1M$5.00$1.14
Blended $/1M (3:1)$2.00$0.502
RAG example (30K in / 2K out)$0.04$0.011
Quality & speed
Intelligence Index7.4—
Coding Index43.921.2
Agentic Index80.8
Output speed (tok/s)——
Time to first token——
Specs
Context window200K164K
Input modalitiestext, image, filetext

FAQ

Which is cheaper, Claude Haiku 4.5 or DeepSeek V3 0324?

DeepSeek V3 0324 has the lower blended API price at $0.502 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), DeepSeek V3 0324 costs about $0.011 per request versus $0.04. Also compare context windows: Claude Haiku 4.5 offers 200K and DeepSeek V3 0324 offers 164K.

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.