AiCostCompare

Claude Haiku 4.5 vs DeepSeek V4 Pro 0813

Side-by-side API pricing and Artificial Analysis performance for Claude Haiku 4.5 (Anthropic) and DeepSeek V4 Pro 0813 (DeepSeek). Green cells mark the better value in each row.

Prices updated Nov 16, 2026, 6:59 PM UTC · refreshed nightly

Claude Haiku 4.5

Anthropic

DeepSeek V4 Pro 0813

DeepSeek

Pricing
Input $/1M$1.00$0.111
Output $/1M$5.00$4.44
Blended $/1M (3:1)$2.00$1.19
RAG example (30K in / 2K out)$0.04$0.0122
Quality & speed
Intelligence Index7.423.1
Coding Index43.968.8
Agentic Index841.3
Output speed (tok/s)——
Time to first token——
Specs
Context window200K1.05M
Input modalitiestext, image, filetext

FAQ

Which is cheaper, Claude Haiku 4.5 or DeepSeek V4 Pro 0813?

DeepSeek V4 Pro 0813 has the lower blended API price at $1.19 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 V4 Pro 0813 costs about $0.0122 per request versus $0.04. Also compare context windows: Claude Haiku 4.5 offers 200K and DeepSeek V4 Pro 0813 offers 1.05M.

Which scores higher on Artificial Analysis benchmarks?

DeepSeek V4 Pro 0813 leads on the Artificial Analysis Intelligence Index (23.1 vs 7.4). Check coding and agentic indices on this page for workload-specific tradeoffs.