New blogMaking an AI Agent You Can Trust With Money
logo

★ OpenAI · Small / fast

GPT-6 Luna API Pricing Calculator

$0.10 per 1M input tokens, $0.50 per 1M output. OpenAI's cheapest current model. Bulk tagging, extraction, routing and lightweight chat.

  • Runs in your browser
  • No signup
  • Updated 7 Nov 2026

Price card · GPT-6 Luna

OpenAI

Input
$0.10 / 1M
Output
$0.50 / 1M
Cached input
$0.01 / 1M
Batch
50% off
Context window
1.05M tokens
Tier
Small / fast

Workload

tok
tok
%

Repeated system prompt or docs

%

Jobs that can wait hours

Models

Anthropic
OpenAI
Google
Mistral
DeepSeek

$ per 1M tokens, input / output

Monthly cost · 30 days

Cheapest
$105
GPT-6 Luna
Priciest
$144
Mistral Small 4
Spread
1.4×
priciest vs cheapest
Per 1K users / mo
GPT-6 LunaCheapest
$105$52.50
Claude Haiku 5.5Cheapest
$105$52.50
Mistral Small 4
$144$72.00
Per 1K users assumesrequests per user per day.

Where the money is

If 60% of your traffic is simple enough for GPT-6 Luna, routing it there instead of Mistral Small 4 saves about $23.40/month.

Caching half your input on Mistral Small 4 (a shared system prompt or document) would cut about $40.50/month.

You're looking at $105–$144/month.

Most AI products I audit can cut that 30–60% with routing, caching and shorter prompts.

Get a cost-cutting audit
01

What GPT-6 Luna costs in practice

List prices per million tokens are hard to reason about. Here is what common request types cost on GPT-6 Luna, with no caching or batch discount applied.

GPT-6 Luna cost by request type
Request typeTokens in / outPer callPer 1K callsPer 1M calls
Classification or routing call400 / 10$0.00005$0.0450$45.00
Support chat reply1,500 / 250$0.00028$0.2750$275
RAG answer over your docs6,000 / 400$0.00080$0.8000$800
Long document summary40,000 / 1,000$0.00450$4.50$4,500
02

Pricing notes

OpenAI's cheapest current model. Bulk tagging, extraction, routing and lightweight chat.

  • Prompts over 272K input tokens are billed at 2x input and 1.5x output for the whole request.
  • Cache writes are billed at $0.125 per 1M tokens (not modelled here).

Source: developers.openai.com, pricing. Verified 7 Nov 2026.

03

Compare

Or compare all 14 models in the full calculator.

04

How the math works

Every provider bills input tokens (your prompt, system prompt and retrieved documents) and output tokens (the reply) separately, per million. Output is usually 4–5× the input price, so chatty apps are output-heavy and RAG apps are input-heavy.

cost per request = (fresh_in × input_price
+ cached_in × cached_price
+ out × output_price) / 1,000,000
× (1 − batched_share × batch_discount)
monthly = cost per request × requests per day × 30

Two adjustments are applied automatically. Introductory prices (currently on some Gemini models) are used until their end date. Long-prompt surcharges kick in when your average input crosses the provider's threshold: 272K tokens on current OpenAI models, 100K on Claude Haiku 5.5.

Not modelled: cache-write premiums, priority or fast tiers, regional surcharges, image and audio tokens, and reasoning tokens a model spends before answering (they bill as output, so add them to your output estimate if you use extended thinking).

05

GPT-6 Luna questions

How much does GPT-6 Luna cost per 1M tokens?
GPT-6 Luna costs $0.10 per 1M input tokens and $0.50 per 1M output tokens, with cached input at $0.01 per 1M. Batch requests get 50% off.
What is the GPT-6 Luna context window?
1.05M tokens, with up to 128,000 output tokens per request. A large window does not mean you should fill it: every token you send is billed, so retrieve only what the request needs.
Do long prompts cost more on GPT-6 Luna?
Yes. Requests with more than 272,000 input tokens are billed at 2× the input rate and 1.5× the output rate for the whole request. The calculator applies this automatically when your average input crosses the threshold.
Is GPT-6 Luna cheaper than Claude Haiku 5.5?
For a typical request of 2,000 input and 300 output tokens they cost about the same ($0.00035 vs $0.00035 per call). Caching, batch support and output length will decide which is cheaper for you.
What is prompt caching and should I use it?
When the start of your prompt (system prompt, tool definitions, a long document) repeats across requests, providers can serve it from cache at a fraction of the input price, often 90–99% off. If your requests share a large fixed prefix, caching is usually the single biggest saving available. Put the stable content first and the variable content last.
Why does my real bill differ from this estimate?
Usually because of tokens you are not counting: reasoning or thinking tokens (billed as output), retries, tool-call round trips, and cache-write premiums. Compare the estimate against the usage page in your provider console for a week and adjust the averages.
06

More from the workbench

01 · Plan & scopeMVP Cost EstimatorPick features and who builds it. Get an hour-by-hour estimate, not an agency teaser.03 · Money & fundraisingRunway & Burn CalculatorMonths of cash left, the date it hits zero, and whether you are default alive.04 · Money & fundraisingSaaS Metrics CalculatorsLTV, CAC, churn, NRR, burn multiple and more, each with the formula and benchmarks.

Fine print

Tools: on the house.
Engineer: by the hour.

Knowing your AI bill was free. Cutting it in half isn't, but I'm cheaper than the overspend.

I'm Himanshu, an AI and full-stack engineer. I build MVPs, AI agents and the growth plumbing around them for early-stage startups.

Hire me →My projects