AiCostCompare

Claude Haiku 4.5 vs GPT-5.6 Luna (batch)

Side-by-side API pricing and Artificial Analysis performance for Claude Haiku 4.5 (Anthropic) and GPT-5.6 Luna (batch) (OpenAI). Green cells mark the better value in each row.

Prices updated Nov 19, 2026, 12:11 AM UTC · refreshed nightly

Claude Haiku 4.5

Anthropic

GPT-5.6 Luna (batch)

OpenAI

Pricing
Input $/1M$1.00$0.10
Output $/1M$5.00$0.60
Blended $/1M (3:1)$2.00$0.225
RAG example (30K in / 2K out)$0.04$0.0042
Quality & speed
Intelligence Index7.423.8
Coding Index——
Agentic Index——
Output speed (tok/s)——
Time to first token——
Specs
Context window200K1.05M
Input modalitiestext, image, filefile, image, text

FAQ

Which is cheaper, Claude Haiku 4.5 or GPT-5.6 Luna (batch)?

GPT-5.6 Luna (batch) has the lower blended API price at $0.225 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), GPT-5.6 Luna (batch) costs about $0.0042 per request versus $0.04. Also compare context windows: Claude Haiku 4.5 offers 200K and GPT-5.6 Luna (batch) offers 1.05M.

Which scores higher on Artificial Analysis benchmarks?

GPT-5.6 Luna (batch) leads on the Artificial Analysis Intelligence Index (23.8 vs 7.4). Check coding and agentic indices on this page for workload-specific tradeoffs.