Skip to content
Sovyron

GPT-5.6 Luna

gpt-luna1.1M context128k max outputreleased Jul 9, 2026ReasoningTool calling3 subscription plans →

As of Nov 22, 2026, the cheapest GPT-5.6 Luna API price is $0.0123 per 1M input tokens (xxapi) and $0.0738 per 1M output tokens (xxapi). GPT-5.6 Luna is offered by 56 providers in the gpt-luna family, reasoning enabled. OpenAI's own rate is $1.2 per 1M output tokens. It is also included in 3 flat-rate subscription plans, GitHub Copilot Pro from $10/mo.

Cheapest input
$0.0123
Cheapest output
$0.0738
Official (OpenAI)
$1.2
output per 1M tokens
Providers
56
offering this model
Spread
81.2×
max / min output
Free offers
0
free-tier offers

API pricing by provider

Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked. Seeing a wide range? Why the same LLM costs different amounts.

GPT-5.6 Luna API prices by provider in USD per 1M tokens, updated Nov 22, 2026
xxapigpt-5.6-lunaCheapest†$0.0123Cheapest$0.0738$0.0012$0.01541.1M—
Outer Labsgpt-5.6-luna†$0.12$0.72$0.012—1.1M—
Kenarigpt-5-6-luna$0.2$1.14$0.02$0.25711.1M5d agoout −0.2%
302.AIgpt-5.6-luna$0.2$1.2$0.02—1.1M—
Abacusgpt-5.6-luna$0.2$1.2$0.02—1.0M31d ago
AIHubMixgpt-5.6-luna†$0.2$1.2$0.02$0.251.1M31d ago
AI/ML APIopenai/gpt-5.6-luna$0.2$1.2$0.02$0.251.1M30d agoout −23.1%
Aixyopenai/gpt-5.6-luna†$0.2$1.2$0.02$0.251.1M—
Amazon Bedrockglobalglobal.openai.gpt-5.6-luna†$0.2$1.2$0.02$0.251.1M—
Azuregpt-5.6-luna†$0.2$1.2$0.02$0.251.1M—
Azure Cognitive Servicesgpt-5.6-luna†$0.2$1.2$0.02$0.251.1M33d ago
CheapestTokengpt-5.6-luna†$0.2$1.2$0.02$0.251.1M—
Cloudflare AI Gatewayopenai/gpt-5.6-luna†$0.2$1.2$0.02$0.251.1M—
CommandCodegpt-5.6-luna†$0.2$1.2$0.02$0.251.1M—
CrossModelopenai/gpt-5.6-luna†$0.2$1.2$0.02$0.251.1M—
Databricksdatabricks-gpt-5-6-luna†$0.2$1.2$0.02$0.251.1M31d ago
DigitalOceanopenai-gpt-5.6-luna†$0.2$1.2$0.02$0.251.1M—
Eden AIopenai/gpt-5.6-luna†$0.2$1.2$0.02$0.251.1M—
FrogBotgpt-5-6-luna$0.2$1.2$0.02$0.251.1M—
Impossiblopenai/gpt-5.6-luna†$0.2$1.2$0.02$0.251.1M—
Kilo Gatewayopenai/gpt-5.6-luna$0.2$1.2$0.02$0.251.1M3d agoout −33.3%
Kilo Gatewayopenai/gpt-5.6-luna-pro$0.2$1.2$0.02$0.251.1M3d agoout −33.3%
DevPass (LLM Gateway)gpt-5.6-luna$0.2$1.2$0.02$0.251.1M—
LLM Gatewayazure/gpt-5.6-luna$0.2$1.2$0.02$0.251.1M—
LLM Gatewayopenai/gpt-5.6-luna$0.2$1.2$0.02$0.251.1M—
LowRouterauto/openai/gpt-5.6-luna†$0.2$1.2$0.02$0.251.1M—
Merge Gatewayopenai/gpt-5.6-luna†$0.2$1.2$0.02$0.251.1M—
Moneogpt-5-6-luna$0.2$1.2——128k—
NanoGPTopenai/gpt-5.6-luna$0.2$1.2$0.02$0.251.1M—
NEAR AI Cloudopenai/gpt-5.6-luna$0.2$1.2$0.02—1.1M—
Neongpt-5-6-luna†$0.2$1.2$0.02$0.251.1M—
Ofoxopenai/gpt-5.6-luna†$0.2$1.2$0.02$0.251.1M—
OpenAIgpt-5.6-luna†$0.2$1.2$0.02$0.251.1M—
OpenCodegpt-5.6-luna†$0.2$1.2$0.02$0.251.1M—
OpenCode Gogpt-5.6-luna†$0.2$1.2$0.02$0.251.1M—
OpenRouteropenai/gpt-5.6-luna†$0.2$1.2$0.02$0.251.1M—
Oppergpt-5.6-luna†$0.2$1.2$0.02$0.251.0M—
OrcaRouteropenai/gpt-5.6-luna†$0.2$1.2$0.02$0.251.1M—
Perplexity Agentopenai/gpt-5.6-luna†$0.2$1.2$0.02$0.251.1M—
Prime Inferenceopenai/gpt-5.6-luna$0.2$1.2——1.1M—
Requestygpt-5.6-luna†$0.2$1.2$0.02$0.251.1M—
SandBaseopenai/gpt-5.6-luna†$0.2$1.2$0.02—1.1M—
SAP AI Coregpt-5.6-luna†$0.2$1.2$0.02—1.1M31d ago
Snowflake Cortexopenai-gpt-5.6-luna†$0.2$1.2$0.02$0.251.1M—
Standard Computeopenai/gpt-5.6-luna†$0.2$1.2$0.02$0.251.1M—
Venice AIopenai-gpt-56-luna†$0.2$1.2$0.02$0.251.0M37d ago
Vercel AI Gatewayopenai/gpt-5.6-luna†$0.2$1.2$0.02$0.251.1M—
ZenMuxopenai/gpt-5.6-luna†$0.2$1.2$0.02$0.251.1M31d ago
ZeroGPUgpt-5.6-luna$0.2$1.2$0.2—272k—
Bumo Routergpt-5.6-luna†$0.212$1.272$0.0212$0.2651.1M—
Amazon Bedrockindiain.openai.gpt-5.6-luna†$0.22$1.32$0.022$0.2751.1M—
Amazon Bedrockopenai.gpt-5.6-luna†$0.22$1.32$0.022$0.2751.1M—
Amazon Bedrockusus.openai.gpt-5.6-luna†$0.22$1.32$0.022$0.2751.1M—
Requestyeugpt-5.6-luna@eu†$0.22$1.32$0.022$0.2751.1M—
Cortecsgpt-5.6-luna$0.227$1.364$0.031$0.291.1M3d agoout +3.3%
Bothubgpt-5.6-luna$0.2677$1.6064——1.1M31d ago
Gisoogpt-5.6-luna$0.28$1.68$0.028—1.1M—
routing.rungpt-5.6-luna$0.7$4.2——1.0M—
AI-ROUTERgpt-5.6-luna$1$6$0.1$1.251.1M—
Vivgridgpt-5.6-luna$1$6$0.1$1.251.1M—

GPT-5.6 Luna price history

Output price per 1M tokens since tracking began on Sep 10, 2026, for the 6 cheapest of 13 providers whose rate moved. Each step is a recorded change. All recent price changes.

GPT-5.6 Luna output price per 1M tokens by provider, Sep 10, 2026 to Nov 22, 2026$0$2.5$5$7.5$10Sep 10, 2026Oct 17, 2026Nov 22, 2026
Kenari$1.14Abacus$1.2AIHubMix$1.2AI/ML API$1.2Azure Cognitive Services$1.2Databricks$1.2
GPT-5.6 Luna price changes by provider, newest first, USD per 1M tokens
DateProvider1M input1M outputChange
Kilo Gateway$0.4 → $0.2$1.8 → $1.2−33.3%
Kilo Gateway$0.4 → $0.2$1.8 → $1.2−33.3%
Cortecs$0.219 → $0.227$1.32 → $1.364+3.3%
Kilo Gateway$0.2 → $0.4$1.2 → $1.8+50%
Kilo Gateway$0.2 → $0.4$1.2 → $1.8+50%
Kenari$0.2$1.1429 → $1.14−0.2%
AI/ML API$0.26 → $0.2$1.56 → $1.2−23.1%
Bothub$0.06 → $0.2677$0.37 → $1.6064+334.2%
Abacus$1 → $0.2$6 → $1.2−80%
AIHubMix$1 → $0.2$6 → $1.2−80%
Databricks$1 → $0.2$6 → $1.2−80%
SAP AI Core$1 → $0.2$6 → $1.2−80%
ZenMux$1 → $0.2$6 → $1.2−80%
Kenarifree → $0.2free → $1.1429—
Azure Cognitive Services$1 → $0.2$6 → $1.2−80%
Venice AI$0.25 → $0.2$1.5 → $1.2−20%

Subscription plans (not per-token)

Billed per month, not per token — never counted as the cheapest offer.

GitHub Copilotplan$0.2$1.21.1M

GPT-5.6 Luna pricing FAQ

What is the cheapest GPT-5.6 Luna API?

As of Nov 22, 2026, xxapi has the lowest GPT-5.6 Luna output price at $0.0738 per 1M tokens, and xxapi has the lowest input price at $0.0123 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

How much does GPT-5.6 Luna cost on OpenAI?

OpenAI charges $0.2 per 1M input tokens and $1.2 per 1M output tokens for GPT-5.6 Luna.

How many providers offer GPT-5.6 Luna?

56 providers list GPT-5.6 Luna on Sovyron; 60 of them sell it at a metered per-token price.

Is GPT-5.6 Luna free?

No provider in the Sovyron catalog lists a free tier for GPT-5.6 Luna.

Is GPT-5.6 Luna included in a subscription plan?

Yes. 3 flat-rate plans include it; the cheapest is GitHub Copilot Pro at $10/month.

What is the context window of GPT-5.6 Luna?

GPT-5.6 Luna supports a 1.1M-token context window and up to 128k output tokens.

Token cost calculator

What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not. See how much prompt caching saves and why output tokens cost more than input tokens.

Estimated

—