GPT-5.6 Luna API Pricing: $0.20 / $1.20 per 1M Tokens
The numbers: GPT-5.6 Luna (OpenAI) bills $0.20 per 1M input tokens, $1.20 per 1M output tokens, and $0.020 per 1M cached input tokens, inside a 1.05M context window. On our reference 200-step agent workload that works out to about $0.29 per task.
Lowest-cost GPT-5.6 tier; cheapest current-generation frontier rate published by OpenAI. Every figure on this page was read directly from OpenAI’s own documentation on September 18, 2026 — not copied from a third-party comparison table. Rates change; the source link and check date below are part of the data.
Verified rates
| Item | Rate | Unit |
|---|---|---|
| Input | $0.20 | per 1M tokens |
| Output | $1.20 | per 1M tokens |
| Cached input (cache read) | $0.020 | per 1M tokens |
| Context window | 1.05M | tokens |
Billing notes: Prompts over 272K input tokens bill at 2x input and 1.5x output for the whole request. Cache writes bill at 1.25x the uncached input rate.
Source: OpenAI official pricing ↗, checked September 18, 2026.
What a real workload costs on GPT-5.6 Luna
List rates are not bills. These two reference workloads translate the table above into money. The assumptions are visible so you can swap in your own trace — the cost calculator does exactly that.
Scenario A — one 200-step agent task
A coding agent runs 200 steps against a stable 40,000-token prefix (system prompt, tools, repository map). The prefix is written to cache on the first step, re-read on the remaining 199, and each step produces 500 output tokens. For OpenAI, cache writes bill at 1.25x the uncached input rate.
| Component | Calculation | Cost |
|---|---|---|
| Cache write (once) | 40,000 tokens × $0.25 / 1M | $0.01 |
| Cache reads | 199 × 40,000 × $0.020 / 1M | $0.16 |
| Output | 200 × 500 × $1.20 / 1M | $0.12 |
| Total per task | $0.29 |
Scenario B — one heavy month
A production service pushes 50M fresh input tokens, 150M cached input tokens, and 10M output tokens through GPT-5.6 Luna in a month:
| Component | Volume | Cost |
|---|---|---|
| Fresh input | 50M × $0.20 | $10.00 |
| Cached input | 150M × $0.020 | $3.00 |
| Output | 10M × $1.20 | $12.00 |
| Monthly total | $25.00 |
Head-to-head cost comparisons
- GPT-5.6 Luna vs Gemini 3.8 Flash — same workload, $0.29 vs $0.97 (3.4x apart).
- GPT-5.6 Luna vs DeepSeek V4.1 Flash — same workload, $0.29 vs $0.09 (3.2x apart).
Frequently asked questions
How much does GPT-5.6 Luna cost per million tokens?
GPT-5.6 Luna costs $0.20 per 1M input tokens and $1.20 per 1M output tokens, with cached input at $0.020 per 1M. Verified September 18, 2026 against OpenAI's official pricing.
What is the context window of GPT-5.6 Luna?
GPT-5.6 Luna supports a 1.05M token context window, per OpenAI's documentation checked September 18, 2026.
Does GPT-5.6 Luna support prompt caching?
Yes. Cached input tokens bill at $0.020 per 1M instead of the full input rate; cache writes bill at 1.25x the uncached input rate.
When was this GPT-5.6 Luna price last checked?
On September 18, 2026, against OpenAI's own pricing page: https://developers.openai.com/api/docs/models/gpt-5.6-luna