OpenAI · Ultra Fast · Updated 2026-11-22

GPT-6 Luna API Pricing & Cost Breakdown

High-volume routing, classification, RAG extraction, and low-latency chatbots.

Input / 1M Tokens
$0.10
Cached Input / 1M
$0.010
Output / 1M Tokens
$0.50
Context Window
1.05M

Workload Cost Scenarios (30-Day Billing)

Budget flagship at $0.10/1M input and $0.01/1M cached input.

Scenario In / Out per Req Uncached Monthly 50% Cache Hit Monthly
Hobby / Prototype (100 req/day) 1500 / 400 $1.05 $0.85
Growing Startup (2,500 req/day) 2500 / 700 $45.00 $36.56
Production Scale (50,000 req/day) 3000 / 800 $1,050.00 $847.50

Compare GPT-6 Luna Against Alternatives

Frequently Asked Questions

What is GPT-6 Luna API pricing per 1M tokens?

Standard input is $0.10/1M, cached input is $0.010/1M, and output is $0.50/1M.

What is the context window of GPT-6 Luna?

GPT-6 Luna supports a 1.05M token context window with up to 128,000 max output tokens.

How much does prompt caching save on GPT-6 Luna?

Prompt caching reduces cached input token rates by 90% compared with uncached input.

What workloads is GPT-6 Luna best suited for?

High-volume routing, classification, RAG extraction, and low-latency chatbots.