Input
- Official OpenAI
- $1
- Here, from (−60%)
- $0.4
- Here, best (−70%)
- $0.3
gpt-5.6-luna
GPT-5.6 Luna API — price per token
GPT-5.6 Luna is the fast, economical tier of the GPT-5.6 line — built for high-volume, latency-sensitive work at one fifth of the flagship price.
Pricing per 1M tokens
| Rate | Official OpenAI | Here, from (−60%) | Here, best (−70%) |
|---|---|---|---|
| Input | $1 | $0.4 | $0.3 |
| Cached input | $0.1 | $0.04 | $0.03 |
| Cache write | $1.25 | $0.5 | $0.375 |
| Output | $6 | $2.4 | $1.8 |
Cached input
- Official OpenAI
- $0.1
- Here, from (−60%)
- $0.04
- Here, best (−70%)
- $0.03
Cache write
- Official OpenAI
- $1.25
- Here, from (−60%)
- $0.5
- Here, best (−70%)
- $0.375
Output
- Official OpenAI
- $6
- Here, from (−60%)
- $2.4
- Here, best (−70%)
- $1.8
Every request is metered at the official rate first, then your progressive B2C discount (60% at the start, up to 70% as cumulative top-ups grow) is subtracted before it touches your prepaid balance. Context window: 272K tokens. Max output: 32K tokens. Reasoning efforts: none, low, medium, high, xhigh, max.
Best for
- Classification, extraction and summarization at scale.
- Latency-sensitive chat and routing layers.
- Cheap pre-processing before a Sol or Terra call.
Good to know
- Same reasoning-effort range as the flagship, including max.
- Text and image input, text output. SSE streaming on both Responses and Chat Completions.
- Requests above 272K input tokens bill at OpenAI long-context rates: 2× input and 1.5× output on the whole request.
How to use GPT-5.6 Luna
Create a free account, generate one key, and point any OpenAI-compatible tool at https://openai.api.apitoken.sale/v1 with model ID gpt-5.6-luna — Responses and Chat Completions both work, authenticated with Authorization: Bearer. New accounts include $10 of API usage at official prices — enough to test the model before topping up.
Frequently asked questions
How much does the GPT-5.6 Luna API cost?
Officially $1 per 1M input tokens and $6 per 1M output tokens, with cached input at $0.10. With the apiToken.sale discount that starts at $0.40/$2.40 and reaches $0.30/$1.80 — the cheapest way to run GPT-5.6.
What is Luna good for?
High-volume, low-latency work: classification, extraction, summarization, routing and simple chat. For complex reasoning, step up to Terra or Sol.
What is the model ID?
gpt-5.6-luna. It works on the same apiToken.sale key, balance and OpenAI-compatible endpoint as every other GPT model.
Run GPT-5.6 Luna on the OpenAI-compatible API at up to 70% off — instant key, prepaid balance, card or crypto.