Models

GPT-5.6 Luna

openai ↗ · 1050K ctx · 5 providers · updated 2026-08-04 22:15 UTC

Cheapest
$0.225 via OpenRouter
Avg price
$0.765 /1M
providers
5
Tokens (24h)
553B
Volume (24h)
$124.5K est.
(3 × $0.100 + $0.600) ÷ 4 = $0.225/1M — the $/1M figure blends input and output at 3:1 — that is the only way models with two different rates can be ranked on one axis. Your actual rate depends on your own input:output mix — input only $0.100, 3:1 $0.225, 1:1 $0.350, output only $0.600 per 1M.

The board shows this model's cheapest measured offer ($0.225/1M); the smaller figure under it is the mean of the 5 offers listed below ($0.765/1M). Add those up and divide — it matches. 24h token volume (553B) is sourced from OpenRouter public rankings — today's only public source of absolute per-model token counts (Vercel AI Gateway publishes share-of-traffic percentages); as more sources come online, the per-router breakdown will sum to this total here.

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
openrouter-best OpenRouter $0.100$0.600 API-measured
openai Pricebook (LiteLLM) $0.200$1.20 Official list
0g-network 0G Router $0.200$1.20 API-measured
requesty Requesty $0.200$1.20 API-measured
azure Pricebook (LiteLLM) $1.00$6.00 Official list

Volume trend

611B 24d d-23 · 23B tokensd-22 · 23B tokensd-21 · 43B tokensd-20 · 40B tokensd-19 · 52B tokensd-18 · 45B tokensd-17 · 46B tokensd-16 · 24B tokensd-15 · 26B tokensd-14 · 48B tokensd-13 · 53B tokensd-12 · 60B tokensd-11 · 67B tokensd-10 · 55B tokensd-9 · 29B tokensd-8 · 32B tokensd-7 · 45B tokensd-6 · 69B tokensd-5 · 77B tokensd-4 · 108B tokensd-3 · 475B tokensd-2 · 561B tokensd-1 · 611B tokensd-0 · 553B tokens

Last 24 days: 23B → 553B (+2260%); range 23B–611B tokens/day. Source: OpenRouter public rankings; refreshed hourly.

Data & method

Cheapest ranked by blended = (3×in + out) ÷ 4; performance columns show only when a source provides them, never estimated. “Official list” = LiteLLM open pricebook (MIT); “API-measured” = provider/aggregator public APIs. Machine-readable data: /api/v1/models/gpt-5.6-luna.json. Free reuse requires attribution to tkx.org.

About

GPT-5.6-Luna is a large language model designed for natural language processing tasks. It is served by multiple inference providers on AI model marketplaces, offering a versatile tool for developers to integrate advanced language capabilities into their applications.

AI-generated summary from public information — is this yours?

FAQ

How much does GPT-5.6 Luna cost?

Cheapest measured offer right now: $0.1/1M input, $0.6/1M output via openrouter-best — across 5 tracked providers, refreshed hourly.

Who serves GPT-5.6 Luna?

5 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.

How heavily is GPT-5.6 Luna used?

GPT-5.6 Luna routed 553B tokens in the last 24h. The daily bars above show routed volume over recent days. Source: OpenRouter public rankings — one of the few routers publishing per-model usage; TKX refreshes hourly.

Related analysis

Back to rankings