AiCostCompare

GPT-5.6 Luna

by OpenAI · openai/gpt-5.6-luna · #231 cheapest of 325 paid models

Prices updated Jul 22, 2026, 1:31 AM UTC · refreshed hourly

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...

Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5Gemini 3.6 Flash

Pricing

Input

$1.00

per 1M tokens

Output

$6.00

per 1M tokens

Blended (3:1)

$2.25

3 input : 1 output

Cache read

$0.10

per 1M cached tokens

Cache write

$1.25

per 1M tokens

Cache & batch economics

Effective prices for GPT-5.6 Luna with prompt caching.

Cache hit rateEffective blended $/1MExample request*vs no cache
0%$2.25$0.108
50%$1.91$0.063−42%
90%$1.64$0.027−75%

*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates for this provider’s batch API. Confirm on the vendor’s pricing page.

What a request costs

WorkloadInput tokensOutput tokensCost / requestCost / 1K requests
Short chat message500300$0.0023$2.30
Document summary8,0001,000$0.014$14.00
Codebase question (RAG)30,0002,000$0.042$42.00
Long-context analysis150,0005,000$0.18$180.00

Performance

Intelligence Index

51.2

AA composite quality

Coding Index

71.4

Math Index

Agentic Index

45.6

Output speed

203 tok/s

median

Time to first token

102.47s

median

Time to first answer

102.47s

after reasoning tokens

Artificial Analysis benchmarks

BenchmarkScore
GPQA Diamond91.1%
Humanity's Last Exam37.2%
SciCode52.5%
AA-LCR (Long Context Reasoning)74.0%
Terminal-Bench 2.180.9%
τ³-Bench Banking27.2%

Specs

Context window

1.05M

tokens

Max output

128K

tokens

Input modalities

file, image, text

Tokenizer

GPT