modelbenchmark.io

GPT-5.6 Luna

OpenAI · gpt-5-6-luna

Compare

Cost-efficient GPT-5.6 model for fast, high-volume workloads

Specification

openai listing

Context
1.1M
Max output
128K
Released
2026-07-09
Knowledge cutoff
2026-02-16
Retires
2028-01-11
Open weights
no
Input
text, image, pdf
Output
text

Price

US dollars per million tokens · openai list price

Input
$0.20
Output
$1.20
Cache read
$0.02
Cache write
$0.25

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Batch inputopenai$0.10
Batch outputopenai$0.60
Priority inputazure$0.40
Priority inputazure$0.44
Priority outputazure$2.40
Priority outputazure$2.64

Batch input is 50% below the interactive input price at the same listing.

Long-context price tiers

the rate above each context threshold

AbovePrice$/M
272KCache read$0.04
272KCache write$0.50
272KInput$0.40
272KOutput$1.80

Quality

8 benchmarks · 2 sources

Composite
80th
percentile of 334 scored models
Rank
68 / 334
±0.08 sd
Evidence
8 × 2
3 or more benchmarks, from 2 or more sources
Effort range
19.0
points between effort settings
reasoning81st3/4 bench
math90th3/7 bench
knowledge49th1/1 bench
general34th1/1 bench

By reasoning effort

every setting placed on the same scale as the leaderboard

SettingCompositeBenchmarks behind it
max88th8
low68th5
medium32nd1

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
FrontierMath-Tier-4-v261.0 ±7.7maxEpoch AI2026-07-09
GPQA diamond91.6 ±1.7maxEpoch AI2026-07-09
82.3 ±2.7lowEpoch AI2026-08-07
Settings differ by 9.3 points on this benchmark.
Chess Puzzles40.0 ±4.9maxEpoch AI2026-07-09
21.0 ±4.1lowEpoch AI2026-08-07
Settings differ by 19.0 points on this benchmark.
OTIS Mock AIME 2024-202598.3 ±1.2maxEpoch AI2026-07-09
66.7 ±7.1lowEpoch AI2026-08-07
Settings differ by 31.6 points on this benchmark.
FrontierMath-Tiers-1-3-v282.1 ±2.3maxEpoch AI2026-07-09
41.4 ±2.9lowEpoch AI2026-08-29
Settings differ by 40.7 points on this benchmark.
SimpleQA Verified41.0 ±1.6maxEpoch AI2026-08-10
Mystery Game Puzzles21.0 ±4.1maxEpoch AI2026-07-28
17.0 ±3.8lowEpoch AI2026-08-27
12.0 ±3.3mediumEpoch AI2026-08-27
Settings differ by 9.0 points on this benchmark.
LiveBench73.7max · 23 runsLiveBench2026-06-25

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 45 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
openaivendor$0.20$1.20$0.02$0.25
1.1M
922K
128K
kenarifreefree1.1M128K
bothub$0.06$0.371.1M128K
302ai$0.20$1.201.1M128K
amazon-bedrock · global$0.20$1.20$0.02$0.251.1M128K
azure
$0.20
$0.22
$1.20
$1.32
$0.02
$0.022
$0.25
$0.275
1.1M
922K
128K2028-01-11
bedrock_converse · global$0.20$1.20$0.02$0.251M128K
cloudflare-ai-gateway$0.20$1.20$0.02$0.251.1M128K
crossmodel$0.20$1.20$0.02$0.251.1M128K
edenai$0.20$1.20$0.02$0.251.1M128K
github-copilot$0.20$1.20$0.02$0.251.1M128K
impossibl$0.20$1.20$0.02$0.251.1M128K
kilo$0.20$1.20$0.02$0.251.1M128K
llmgateway$0.20$1.20$0.02$0.251.1M128K
llmgateway-providers$0.20$1.20$0.02$0.251.1M128K
merge-gateway$0.20$1.20$0.02$0.251.1M128K
nano-gpt$0.20$1.20$0.02$0.251.1M128K
neon$0.20$1.20$0.02$0.251.1M128K
ofox$0.20$1.20$0.02$0.251.1M128K
opencode$0.20$1.20$0.02$0.251.1M128K
opencode-go$0.20$1.20$0.02$0.251.1M128K
openrouter$0.20$1.20$0.02$0.25
1.1M
922K
128K
opper$0.20$1.20$0.02$0.251.1M128K
orcarouter$0.20$1.20$0.02$0.251.1M128K
perplexity$0.20$1.20$0.02
requesty$0.20$1.20$0.021.1M128K
vercel$0.20$1.20$0.02$0.251.1M128K
cortecs$0.219$1.32$0.022$0.2751.1M128K
amazon-bedrock$0.22$1.32$0.022$0.2751.1M128K
amazon-bedrock · in$0.22$1.32$0.022$0.2751.1M128K
amazon-bedrock · us$0.22$1.32$0.022$0.2751.1M128K
bedrock_converse · us$0.22$1.32$0.022$0.2751M128K
bedrock_mantle · bedrock-mantle
$0.22
$0.264
$1.32
$1.584
$0.022
$0.0264
$0.275
$0.33
1.1M128K
llmgateway-providers · aws-mantle$0.22$1.32$0.022$0.275279K128K
routing-run$0.70$4.201M128K
abacus$1.00$6.00$0.101M128K
ai-router$1.00$6.00$0.10$1.251.1M128K
aihubmix$1.00$6.00$0.10$1.251.1M128K
azure-cognitive-services$1.00$6.00$0.10$1.251.1M128K
databricks$1.00$6.00$0.10$1.25
400K
922K
128K
pioneer$1.00$6.00$0.10$1.251.1M128K
sap-ai-core$1.00$6.00$0.101.1M128K
vivgrid$1.00$6.00$0.10$1.251.1M128K
zenmux$1.00$6.00$0.10$1.251.1M128K
chatgpt · chatgpt1.1M128K

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02bedrock_mantle · bedrock-mantleCache read$0.022
2026-09-04bedrock_mantle · bedrock-mantleCache read$0.022
2026-09-02databricksCache read$0.10
2026-09-06databricksCache read$0.10
2026-09-02neonCache read$0.10
2026-09-02neonCache read$0.02
2026-09-02openrouterCache read$0.02
2026-09-06openrouterCache read$0.02
2026-09-02bedrock_mantle · bedrock-mantleCache write$0.275
2026-09-04bedrock_mantle · bedrock-mantleCache write$0.275
2026-09-02bedrock_mantle · bedrock-mantleInput$0.22
2026-09-04bedrock_mantle · bedrock-mantleInput$0.22
2026-09-02databricksInput$1.00
2026-09-06databricksInput$1.00
2026-09-02neonInput$1.00
2026-09-02neonInput$0.20
2026-09-02openrouterInput$0.20
2026-09-06openrouterInput$0.20
2026-09-02bedrock_mantle · bedrock-mantleOutput$1.32
2026-09-04bedrock_mantle · bedrock-mantleOutput$1.32
2026-09-02databricksOutput$6.00
2026-09-06databricksOutput$6.00
2026-09-02neonOutput$6.00
2026-09-02neonOutput$1.20
2026-09-02openrouterOutput$1.20
2026-09-06openrouterOutput$1.20

Other listings of this model

same model, different key

More from OpenAI

most-hosted first