AiCostCompare

Claude Haiku 4.5 vs DeepSeek V4 Flash 0731

Side-by-side API pricing and Artificial Analysis performance for Claude Haiku 4.5 (Anthropic) and DeepSeek V4 Flash 0731 (DeepSeek). Green cells mark the better value in each row.

Prices updated Sep 17, 2026, 4:19 AM UTC · refreshed hourly

Claude Haiku 4.5

Anthropic

DeepSeek V4 Flash 0731

DeepSeek

Pricing
Input $/1M$1.00$0.06
Output $/1M$5.00$0.12
Blended $/1M (3:1)$2.00$0.075
RAG example (30K in / 2K out)$0.04$0.00204
Quality & speed
Intelligence Index17.634.5
Coding Index43.969.1
Agentic Index10.341.7
Output speed (tok/s)
Time to first token
Specs
Context window200K1.31M
Input modalitiestext, image, filetext

FAQ

Which is cheaper, Claude Haiku 4.5 or DeepSeek V4 Flash 0731?

DeepSeek V4 Flash 0731 has the lower blended API price at $0.075 per 1M tokens (3:1 input:output mix), versus $2.00 for the other model. Prices are live from OpenRouter and refresh about hourly.

Which is better for RAG workloads?

For a typical RAG request (30K input / 2K output tokens), DeepSeek V4 Flash 0731 costs about $0.00204 per request versus $0.04. Also compare context windows: Claude Haiku 4.5 offers 200K and DeepSeek V4 Flash 0731 offers 1.31M.

Which scores higher on Artificial Analysis benchmarks?

DeepSeek V4 Flash 0731 leads on the Artificial Analysis Intelligence Index (34.5 vs 17.6). Check coding and agentic indices on this page for workload-specific tradeoffs.