AiCostCompare

Claude Sonnet 5 vs Command A+

Side-by-side API pricing and Artificial Analysis performance for Claude Sonnet 5 (Anthropic) and Command A+ (Cohere). Green cells mark the better value in each row.

Prices updated Nov 14, 2026, 4:48 PM UTC · refreshed nightly

Claude Sonnet 5

Anthropic

Command A+

Cohere

Pricing
Input $/1M$2.00$0.30
Output $/1M$10.00$1.50
Blended $/1M (3:1)$4.00$0.60
RAG example (30K in / 2K out)$0.08$0.012
Quality & speed
Intelligence Index—6.2
Coding Index71.527.8
Agentic Index43.61
Output speed (tok/s)——
Time to first token——
Specs
Context window1M192K
Input modalitiestext, image, filetext, image

FAQ

Which is cheaper, Claude Sonnet 5 or Command A+?

Command A+ has the lower blended API price at $0.60 per 1M tokens (3:1 input:output mix), versus $4.00 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), Command A+ costs about $0.012 per request versus $0.08. Also compare context windows: Claude Sonnet 5 offers 1M and Command A+ offers 192K.

Which scores higher on Artificial Analysis benchmarks?

Command A+ leads on the Artificial Analysis Intelligence Index (6.2 vs —). Check coding and agentic indices on this page for workload-specific tradeoffs.