OpenAIVerified Active: September 18, 2026
GPT-5.6 LunaAPI Pricing & Specifications
Ultra-fast low-latency frontier reasoning engine built for high-throughput operational pipelines.
đ Core Specifications & Pricing Rates
Standard Input
$0.20 / 1M tokens
Standard Output
$1.20 / 1M tokens
Cached Input
$0.0200 / 1M tokens
Cache Write
$0.25 / 1M tokens
Context Window
1.05M (1,050,000 tokens)
Max Output Tokens
64,000 tokens
Supported Capabilities:â Visionâ Function Calling / Toolsâ JSON Modeâ Deep Reasoning
⥠Tiered Context Threshold: For prompts > 272K tokens, input rate steps up to $0.40/1M, output steps up to $1.80/1M, cached read steps up to $0.04/1M, and cache write steps up to $0.50/1M.
đĻ Asynchronous Batch API Supported: Official provider documentation offers a 50% discount on non-streaming 24h batch requests.
Live Workload Cost Estimator: GPT-5.6 Luna
Adjust token volumes to simulate your exact monthly API bill.
âšī¸ Context Tier Threshold: Standard rate is $0.20 in / $1.20 out (â¤272K). Requests exceeding 272K tokens reprice to $0.40 in / $1.80 out / $0.04 cached / $0.50 write per 1M.
Estimated 60% repeated context
Estimated Total Monthly Cost
Compare All Models in Calculatorâ$15.45/ month
$0.00062 per API request(Saves $4.05/mo with caching)
đĄ Estimated Monthly Workload Scenarios
High-Volume Chat Moderation
$32.00/mo100,000 streaming content analyses (1,000 input, 100 output)
100,000 requests âĸ 1000 in / 100 out
âī¸ Head-to-Head Competitor Comparisons
GPT-5.6 Luna vs. GPT-5.1 Mini
Luna is 20% cheaper on input ($0.20 vs $0.25) and 40% cheaper on output ($1.20 vs $2.00) with 1.05M context.
1.25x cheaper input than 5.1 MiniView GPT-5.1 Mini â
đ Historical Price Changes & Updates
2026-07-09
GPT-5.6 Luna released as high-speed operational tier at $0.20 input / $1.20 output per 1M tokens.
đ Verified Primary Sources
All pricing, token limits, and capabilities are cross-checked against official provider documentation and live API endpoints.