Skip to content
TokenGauge
Menu

OpenAI · Frontier

GPT-5.6 Luna API pricing

Smallest GPT-5.6 model. Cheap enough to run at scale, and the discount still lands at 29 percent against OpenRouter.

Snapshot October 2026 · USD per million tokens · Best for: chat products, summarisation, cheap tool calls
SayGM, in / out
$0.15 / $0.89
No top-up fee
OpenRouter, in / out
$0.21 / $1.27
Includes the 5.5% top-up fee
Provider list price
$0.20 / $1.20
OpenAI direct
Per 100M tokens, 80/20
$30
$42 on OpenRouter

§ 01

What a month costs

The same three workloads used across the index. At every level the SayGM bill is about 29% lower.

Fig. 1Monthly bill at three usage levels, GPT-5.6 Luna
  • OpenRouter, fee included
  • SayGM
Side project5M in · 1M out
$2.32
$1.64
Production app50M in · 15M out
$30
$21
High volume500M in · 100M out
$232
$164
Show data as a table
OpenRouter, fee includedSayGM
Side project (5M in · 1M out)$2.32$1.64
Production app (50M in · 15M out)$30$21
High volume (500M in · 100M out)$232$164
Usage is millions of input and output tokens per month. No caching discount applied. Source: published rate cards, October 2026 snapshot. Current prices on saygm.com (opens in a new tab).

§ 02

Where the money goes

Output tokens cost 5.9 times more than input on GPT-5.6 Luna. At an 80/20 mix they make up 60% of the bill.

Fig. 2Share of the bill from output tokens at an 80/20 token mix
  • Input tokens (80% of volume)
  • Output tokens (20% of volume)
GPT-6.1 Sol
GPT-6 Luna
GPT-5.5
GPT-5.6 Terra
GPT-5.6 Luna
Show data as a table
ModelShare of bill from inputShare of bill from output
GPT-6.1 Sol44%56%
GPT-6 Luna43%57%
GPT-5.540%60%
GPT-5.6 Terra40%60%
GPT-5.6 Luna40%60%
Output tokens are a fifth of the volume but most of the cost on every frontier model. Trimming output length saves more than trimming prompts. Source: published rate cards, October 2026 snapshot. Current prices on saygm.com (opens in a new tab).

§ 03

Estimate a GPT-5.6 Luna bill

50M
10M

Monthly bill by provider

  • OpenRouter, fee included$23
  • Requesty, 5% included$23
  • Vercel AI Gateway$22
  • OpenAI direct, list price$22
  • SayGM$16
A year, vs the cheapest alternative
$67
25% lower than Vercel AI Gateway
A year, vs OpenRouter
$82
Fee included

Uncached prices from the October 2026 snapshot. Prompt caching lowers every provider's bill; batch jobs bought direct cost half of list. Current SayGM rates are on saygm.com (opens in a new tab).

§ 04

Other OpenAI models

USD per million tokens, input and output. OpenRouter includes its 5.5% top-up fee. Snapshot from October 2026.
ModelSayGMin / outOpenRouterin / out, fee incl.SayGM vs OpenRouter80/20 blend
GPT-6.1 SolOpenAI$1.49 / $7.45$2.11 / $10.55
29% lower
GPT-6 LunaOpenAI$0.07 / $0.37$0.11 / $0.53
33% lower
GPT-5.5OpenAI$3.73 / $22.35$5.28 / $31.65
29% lower
GPT-5.6 TerraOpenAI$1.49 / $8.94$2.11 / $12.66
29% lower
GPT-5.6 LunaOpenAI$0.15 / $0.89$0.21 / $1.27
29% lower

§ 05

Compare and set up

Head to head

Use it in

Current SayGM rates (opens in a new tab)

§ 06

GPT-5.6 Luna questions

How much does GPT-5.6 Luna cost on SayGM?

As of October 2026, $0.15 per million input tokens and $0.89 per million output tokens, with no top-up fee. Prices are set per epoch and capped at list, so check saygm.com for the live rate.

Is GPT-5.6 Luna cheaper on SayGM or OpenRouter?

SayGM is about 29 percent cheaper at an 80/20 input to output mix once OpenRouter's 5.5 percent fee is included.

Which API does SayGM use for GPT-5.6 Luna?

The model's native API. OpenAI features such as caching, tool use and structured output work unchanged. Any OpenAI-compatible SDK works by changing the base URL.