modelbenchmark.io

GPT-5.6 Terra

OpenAI · gpt-5-6-terra

Compare

Balanced GPT-5.6 model for capable, cost-efficient everyday work

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
$2.00
Output
$12.00
Cache read
$0.20
Cache write
$2.50

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Batch inputopenai$1.00
Batch outputopenai$6.00
Priority inputazure$4.00
Priority inputazure$4.40
Priority outputazure$24.00
Priority outputazure$26.40

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$0.40
272KCache write$5.00
272KInput$4.00
272KOutput$18.00

Quality

8 benchmarks · 2 sources

Composite
90th
percentile of 334 scored models
Rank
36 / 334
±0.08 sd
Evidence
8 × 2
3 or more benchmarks, from 2 or more sources
Effort range
17.9
points between effort settings
reasoning89th3/4 bench
math95th3/7 bench
knowledge52nd1/1 bench
general73rd1/1 bench

By reasoning effort

every setting placed on the same scale as the leaderboard

SettingCompositeBenchmarks behind it
max94th8
low83rd4
medium26th1

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
FrontierMath-Tiers-1-3-v286.0 ±2.1maxEpoch AI2026-07-09
Chess Puzzles54.0 ±5.0maxEpoch AI2026-07-09
22.0 ±4.2lowEpoch AI2026-08-07
Settings differ by 32.0 points on this benchmark.
FrontierMath-Tier-4-v270.7 ±7.2maxEpoch AI2026-07-09
OTIS Mock AIME 2024-202599.7 ±0.3maxEpoch AI2026-07-09
88.9 ±4.7lowEpoch AI2026-08-07
Settings differ by 10.8 points on this benchmark.
GPQA diamond93.3 ±1.5maxEpoch AI2026-07-09
87.4 ±2.4lowEpoch AI2026-08-07
Settings differ by 5.9 points on this benchmark.
LiveBench78.6max · 23 runsLiveBench2026-06-25
SimpleQA Verified43.2 ±1.6maxEpoch AI2026-08-10
Mystery Game Puzzles35.0 ±4.8maxEpoch AI2026-07-28
19.0 ±3.9lowEpoch AI2026-08-27
10.0 ±3.0mediumEpoch AI2026-08-28
Settings differ by 25.0 points on this benchmark.

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

Available from 44 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
openaivendor$2.00$12.00$0.20$2.50
1.1M
922K
128K
kenarifreefree1.1M128K
routing-run$1.50$9.001M128K
xpersona$1.50$2.00$0.15372K128K
302ai$2.00$12.001.1M128K
amazon-bedrock · global$2.00$12.00$0.20$2.501.1M128K
azure
$2.00
$2.20
$12.00
$13.20
$0.20
$0.22
$2.50
$2.75
1.1M
922K
128K2028-01-11
bedrock_converse · global$2.00$12.00$0.20$2.501M128K
cloudflare-ai-gateway$2.00$12.00$0.20$2.501.1M128K
crossmodel$2.00$12.00$0.20$2.501.1M128K
edenai$2.00$12.00$0.20$2.501.1M128K
github-copilot$2.00$12.00$0.20$2.501.1M128K
impossibl$2.00$12.00$0.20$2.501.1M128K
kilo$2.00$12.00$0.20$2.501.1M128K
llmgateway$2.00$12.00$0.20$2.501.1M128K
llmgateway-providers$2.00$12.00$0.20$2.501.1M128K
merge-gateway$2.00$12.00$0.20$2.501.1M128K
nano-gpt$2.00$12.00$0.20$2.501.1M128K
neon$2.00$12.00$0.20$2.501.1M128K
ofox$2.00$12.00$0.20$2.501.1M128K
openrouter$2.00$12.00$0.20$2.50
1.1M
922K
128K
opper$2.00$12.00$0.20$2.501.1M128K
orcarouter$2.00$12.00$0.20$2.501.1M128K
perplexity$2.00$12.00$0.20
requesty$2.00$12.00$0.201.1M128K
vercel$2.00$12.00$0.20$2.501.1M128K
amazon-bedrock$2.20$13.20$0.22$2.751.1M128K
amazon-bedrock · in$2.20$13.20$0.22$2.751.1M128K
amazon-bedrock · us$2.20$13.20$0.22$2.751.1M128K
bedrock_converse · us$2.20$13.20$0.22$2.751M128K
bedrock_mantle · bedrock-mantle
$2.20
$2.64
$13.20
$15.84
$0.22
$0.264
$2.75
$3.30
1.1M128K
cortecs$2.20$13.199$0.219$2.7491.1M128K
llmgateway-providers · aws-mantle$2.20$13.20$0.22$2.75279K128K
abacus$2.50$15.00$0.251M128K
ai-router$2.50$15.00$0.25$3.1251.1M128K
aihubmix$2.50$15.00$0.25$3.1251.1M128K
azure-cognitive-services$2.50$15.00$0.25$3.1251.1M128K
databricks$2.50$15.00$0.25$3.125
1.1M
922K
128K
opencode$2.50$15.00$0.25$3.1251.1M128K
pioneer$2.50$15.00$0.25$3.1251.1M128K
sap-ai-core$2.50$15.00$0.251.1M128K
vivgrid$2.50$15.00$0.25$3.1251.1M128K
zenmux$2.50$15.00$0.25$3.1251.1M128K
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$0.22
2026-09-04bedrock_mantle · bedrock-mantleCache read$0.22
2026-09-02databricksCache read$0.25
2026-09-06databricksCache read$0.25
2026-09-02neonCache read$0.25
2026-09-02neonCache read$0.20
2026-09-02openrouterCache read$0.20
2026-09-06openrouterCache read$0.20
2026-09-02bedrock_mantle · bedrock-mantleCache write$2.75
2026-09-04bedrock_mantle · bedrock-mantleCache write$2.75
2026-09-02bedrock_mantle · bedrock-mantleInput$2.20
2026-09-04bedrock_mantle · bedrock-mantleInput$2.20
2026-09-02databricksInput$2.50
2026-09-06databricksInput$2.50
2026-09-02neonInput$2.50
2026-09-02neonInput$2.00
2026-09-02openrouterInput$2.00
2026-09-06openrouterInput$2.00
2026-09-02bedrock_mantle · bedrock-mantleOutput$13.20
2026-09-04bedrock_mantle · bedrock-mantleOutput$13.20
2026-09-02databricksOutput$15.00
2026-09-06databricksOutput$15.00
2026-09-02neonOutput$15.00
2026-09-02neonOutput$12.00
2026-09-02openrouterOutput$12.00
2026-09-06openrouterOutput$12.00

Other listings of this model

same model, different key

More from OpenAI

most-hosted first