GPT-5.6 Luna
Pricing & Specs

OpenAI · $0.2 input / $1.2 output per 1M tokens · 1.05M context window

$0.2
per 1M input tokens
$1.2
per 1M output tokens
1.05M
context window (tokens)

The per-token price never tells the full story. A typical task (1K input + 500 output tokens) on GPT-5.6 Luna costs about $0.0008 — roughly $0.80 per 1,000 runs. But if it needs 3x the tokens of a cheaper model to match quality on YOUR task, the economics flip. The only way to know is to benchmark it on your actual workload.

GPT-5.6 Luna API Pricing

TokensPrice
Input$0.2 / 1M tokens
Output$1.2 / 1M tokens
Cached input$0.02 / 1M tokens

Prompts >272K tokens priced at 2x input, 1.5x output. Cache writes at 1.25x uncached input rate.

What that means in practice

1x One typical task (1K input + 500 output tokens): $0.0008
1K 1,000 runs of that task: $0.80
💡 Real cost depends on how verbose the model is on YOUR prompts — benchmark to measure actual tokens, not estimates.

GPT-5.6 Luna Specs

SpecValue
Context window1.05M tokens
Max output tokens128K tokens
Input modalitiestext, image
Output modalitiestext
Knowledge cutoffFebruary 16, 2026
Reasoning modelYes
Tool / function callingYes
JSON modeYes
StreamingYes
Prompt cachingYes
Batch APIYes

Notes

Cost-optimized for high-volume workloads. Corresponds to nano tier from earlier GPT-5 families.

FAQ

How much does GPT-5.6 Luna cost?

GPT-5.6 Luna costs $0.2 per 1M input tokens and $1.2 per 1M output tokens ($0.02 per 1M cached input tokens).

What is GPT-5.6 Luna's context window?

GPT-5.6 Luna has a 1.05M-token context window. Maximum output is 128K tokens.

Can I test GPT-5.6 Luna on my own task?

Yes. OpenMark lets you benchmark GPT-5.6 Luna against 100+ models on your own task with real API calls — no API keys needed, free tier available.

Is GPT-5.6 Luna the right model for YOUR task?

Pricing tables can't answer that. Benchmark it against 100+ models
on your actual workload — real API calls, real costs. Free tier available.

Benchmark GPT-5.6 Luna — Free →