AiCostCompare

Claude Sonnet 4 vs GPT-4.1 Mini

Side-by-side API pricing and Artificial Analysis performance for Claude Sonnet 4 (Anthropic) and GPT-4.1 Mini (OpenAI). Green cells mark the better value in each row.

Prices updated Jul 22, 2026, 1:38 AM UTC · refreshed hourly

Claude Sonnet 4

Anthropic

GPT-4.1 Mini

OpenAI

Pricing
Input $/1M$3.00$0.40
Output $/1M$15.00$1.60
Blended $/1M (3:1)$6.00$0.70
RAG example (30K in / 2K out)$0.12$0.0152
Quality & speed
Intelligence Index28.914.8
Coding Index37.620.2
Agentic Index16.61.7
Output speed (tok/s)84
Time to first token0.55s
Specs
Context window1M1.05M
Input modalitiesimage, text, fileimage, text, file

FAQ

Which is cheaper, Claude Sonnet 4 or GPT-4.1 Mini?

GPT-4.1 Mini has the lower blended API price at $0.70 per 1M tokens (3:1 input:output mix), versus $6.00 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), GPT-4.1 Mini costs about $0.0152 per request versus $0.12. Also compare context windows: Claude Sonnet 4 offers 1M and GPT-4.1 Mini offers 1.05M.

Which scores higher on Artificial Analysis benchmarks?

Claude Sonnet 4 leads on the Artificial Analysis Intelligence Index (28.9 vs 14.8). Check coding and agentic indices on this page for workload-specific tradeoffs.