GPT-5.6 Luna pricing & benchmarks
GPT-5.6 Luna is available from OpenAI at $0.100 per million input tokens and $0.600 per million output tokens ($0.225 blended at 3:1). It accepts up to 1,050,000 tokens of context. GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...
Pricing
Per million tokens · OpenRouter
Input$0.100
Output$0.600
Blended (3:1)$0.225
Specification
openai/gpt-5.6-luna
Context window1.1M
Max output128K
ReleasedJul 2026
LicenceProprietary
Modalitiesin:text, in:image, in:file, out:text
Benchmarks
Independently run — not vendor self-reports. Every score links its source.
| Benchmark | Score | Config | Run | Source |
|---|---|---|---|---|
| GPQA Diamond | 91.6% ±1.7 | max effort | 2026-07-09 | Independently run · Epoch AI |
| FrontierMath T1–3 | 82.1% ±2.3 | max effort | 2026-07-09 | Independently run · Epoch AI |
| FrontierMath T4 | 61.0% ±7.7 | max effort | 2026-07-09 | Independently run · Epoch AI |
| SimpleQA Verified | 41.7% ±1.6 | max effort | 2026-07-09 | Independently run · Epoch AI |
| OTIS Mock AIME | 98.3% ±1.2 | max effort | 2026-07-09 | Independently run · Epoch AI |
Scores published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0.
Where to run GPT-5.6 Luna
6 options across 3 providers · 22× between cheapest and dearest. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
| Host | Blended $/1M | In / Out | Context | Uptime 24h |
|---|---|---|---|---|
| OpenAI (flex) ⚠ re-prices above 272K prompt tokens ($0.100/$0.450) |
$0.112 | $0.050 / $0.300 | 1.1M | 88.1% |
| OpenAI ⚠ re-prices above 272K prompt tokens ($0.200/$0.900) |
$0.225 | $0.100 / $0.600 | 1.1M | 88.1% |
| OpenAI (priority) | $0.450 | $0.200 / $1.20 | 1.1M | 88.1% |
| Amazon Bedrock (us-east-1) ⚠ re-prices above 272K prompt tokens ($0.440/$1.98) |
$0.495 | $0.220 / $1.32 | 1.1M | 100.0% |
| Azure ⚠ re-prices above 272K prompt tokens ($2.00/$9.00) |
$2.25 | $1.00 / $6.00 | 1.1M | 99.7% |
| Azure (eu) ⚠ re-prices above 272K prompt tokens ($2.20/$9.90) |
$2.48 | $1.10 / $6.60 | 1.1M | 100.0% |
Host prices and uptime from OpenRouter, synced 2026-08-08.
Compare GPT-5.6 Luna
FAQ
How much does GPT-5.6 Luna cost?
GPT-5.6 Luna costs $0.100 per million input tokens and $0.600 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.225 per million tokens.
What is GPT-5.6 Luna's context window?
GPT-5.6 Luna accepts up to 1,050,000 tokens of context, and can generate up to 128,000 output tokens.
How good is GPT-5.6 Luna on benchmarks?
GPT-5.6 Luna scores 91.6% on GPQA Diamond, independently run and published by Epoch AI. 5 benchmark results are listed on this page, each with its run date and source.