AiCostCompare

Claude Sonnet 5 vs GPT-6 Luna (batch)

Side-by-side API pricing and Artificial Analysis performance for Claude Sonnet 5 (Anthropic) and GPT-6 Luna (batch) (OpenAI). Green cells mark the better value in each row.

Prices updated Nov 18, 2026, 12:28 AM UTC · refreshed nightly

Claude Sonnet 5

Anthropic

GPT-6 Luna (batch)

OpenAI

Pricing
Input $/1M$2.00$0.05
Output $/1M$10.00$0.25
Blended $/1M (3:1)$4.00$0.10
RAG example (30K in / 2K out)$0.08$0.002
Quality & speed
Intelligence Index—27.9
Coding Index71.5—
Agentic Index43.6—
Output speed (tok/s)——
Time to first token——
Specs
Context window1M1.05M
Input modalitiestext, image, filefile, image, text

FAQ

Which is cheaper, Claude Sonnet 5 or GPT-6 Luna (batch)?

GPT-6 Luna (batch) has the lower blended API price at $0.10 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), GPT-6 Luna (batch) costs about $0.002 per request versus $0.08. Also compare context windows: Claude Sonnet 5 offers 1M and GPT-6 Luna (batch) offers 1.05M.

Which scores higher on Artificial Analysis benchmarks?

GPT-6 Luna (batch) leads on the Artificial Analysis Intelligence Index (27.9 vs —). Check coding and agentic indices on this page for workload-specific tradeoffs.