modelbenchmark.io

GPT-6 Sol

OpenAI · gpt-6-sol

Compare

OpenAI model for complex coding and agentic workflows

Specification

openai listing

Context
1.1M
Max output
128K
Released
2026-09-22
Knowledge cutoff
2026-04-20
Retires
2028-03-11
Open weights
no
Input
text, image, pdf
Output
text

Price

US dollars per million tokens · openai list price

Input
$2.00
Output
$10.00
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$5.00
Priority inputazure$4.00
Priority inputazure$4.40
Priority outputazure$20.00
Priority outputazure$22.00
Priority outputdatabricks$19.9997

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 creation input token cost above 12hr$10.00
272KCache read$0.40
272KCache write$5.00
272KInput$4.00
272KOutput$15.00

Quality

13 benchmarks · 2 sources

Composite
92nd
percentile of 344 scored models
Rank
29 / 344
±0.07 sd
Evidence
13 × 2
3 or more benchmarks, from 2 or more sources
Effort range
—
one configuration only
reasoning96th4/4 bench
math97th3/7 bench
knowledge83rd1/1 bench
general82nd1/1 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
Mystery Game Puzzles56.0 ±5.0maxEpoch AI2026-09-22
FrontierMath-Tier-4-v290.0 ±5.2maxEpoch AI2026-09-22
FrontierMath-Tiers-1-3-v289.8 ±1.8maxEpoch AI2026-09-22
Chess Puzzles56.0 ±5.0maxEpoch AI2026-10-13
GPQA diamond94.3 ±1.5maxEpoch AI2026-09-22
OTIS Mock AIME 2024-2025100.0 ±0.0maxEpoch AI2026-09-22
EBR-bench53.3 ±4.6maxEpoch AI2026-09-22
SimpleQA Verified60.7 ±1.5maxEpoch AI2026-09-22
LiveBench79.8max · 23 runsLiveBench2026-06-25
Furniture Assembly58.3 ±6.4maxEpoch AI2026-09-23
SpireClimb (Slay the Spire 2, Ascension 10)13.3 ±4.0maxEpoch AI2026-09-22
SpireClimb7.5 ±2.1maxEpoch AI2026-09-24
SpireClimb (Slay the Spire 1, Ascension 20 Heart)1.7 ±1.7maxEpoch AI2026-09-24

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

Available from 54 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
openaivendor$2.00$10.00$0.20$2.50
1.1M
922K
128K—
xxapi$0.1231$0.6154$0.0123$0.15381.1M128K—
void-api$0.495$2.46$0.0345$0.481.1M128K—
uplinkswitch$0.60$3.00$0.12—1.1M128K—
korouter$0.74$3.70$0.074$0.9251.1M128K—
kunavo$0.80$4.00$0.08$1.001.1M128K—
outerlabs$1.20$6.00$0.12—1.1M128K—
302ai$2.00$10.00$0.20$2.501.1M128K—
aihubmix$2.00$10.00$0.20$2.501.1M128K—
aimlapi$2.00$10.00$0.20$2.501.1M128K—
aixy$2.00$10.00$0.20$2.501.1M128K—
amazon-bedrock · global$2.00$10.00$0.20$2.501.1M128K—
azure
$2.00
$2.20
$2.40
$10.00
$11.00
$12.00
$0.20
$0.22
$0.24
$2.50
$2.75
$3.00
1.1M
922K
128K2028-03-11
azure_ai$2.00$10.00$0.20$2.50922K128K—
azure-cognitive-services$2.00$10.00$0.20$2.501.1M128K—
bedrock_converse$2.00$10.00$0.20$2.50922K128K—
bedrock_converse · global$2.00$10.00$0.20$2.50922K128K—
boundless$2.00$10.00$0.20—1.1M128K—
cheapest-token$2.00$8.00$0.20$2.501.1M128K—
cloudflare-ai-gateway$2.00$10.00$0.20$2.501.1M128K—
commandcode$2.00$10.00$0.20$2.501.1M128K—
crossmodel$2.00$10.00$0.20$2.501.1M128K—
databricks$2.00$10.00$0.20$2.50922K128K—
edenai$2.00$10.00$0.20$2.501.1M128K—
fastrouter$2.00$10.00$0.20$2.50400K128K—
frogbot$2.00$10.00$0.20$2.501.1M128K—
github_copilot · github-copilot$2.00$10.00$0.20$2.50922K128K—
github-copilot$2.00$10.00$0.20$2.501.1M128K—
gmi · gmi$2.00$10.00$0.20—1.1M——
kilo$2.00$10.00$0.20$2.501.1M128K—
llmgateway$2.00$10.00$0.20$2.501.1M128K—
llmgateway-providers$2.00$10.00$0.20$2.501.1M128K—
lowrouter · auto$2.00$10.00$0.20$2.501.1M128K—
merge-gateway$2.00$10.00$0.20$2.501.1M128K—
nano-gpt$2.00$10.00$0.20$2.501.1M128K—
nearai$2.00$10.00$0.20—1.1M128K—
neon$2.00$10.00$0.20$2.501.1M128K—
ofox$2.00$10.00$0.20$2.501.1M128K—
opencode$2.00$10.00$0.20$2.501.1M128K—
openrouter$2.00$10.00$0.20$2.501.1M128K—
perplexity$2.00$10.00$0.20————
perplexity-agent$2.00$10.00$0.20$2.501.1M128K—
prime$2.00$10.00——1.1M128K—
requesty$2.00$10.00$0.20$2.501.1M128K—
synthorai$2.00$10.00$0.20—1.1M128K—
vercel$2.00$10.00$0.20$2.501.1M128K—
vivgrid$2.00$10.00$0.20$2.501.1M128K—
zenmux$2.00$10.00$0.20$2.501.1M128K—
amazon-bedrock$2.20$11.00$0.22$2.751.1M128K—
amazon-bedrock · us$2.20$11.00$0.22$2.751.1M128K—
bedrock_converse · us$2.20$11.00$0.22$2.75922K128K—
bedrock_mantle · bedrock-mantle$2.20$11.00$0.22$2.75922K128K—
cortecs$2.40$11.999$0.24$3.001.1M128K—
chatgpt · chatgpt————922K128K—

Price history

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

DateHostField$/M
2026-09-23azureCache read$0.20
2026-09-24azureCache read$0.20
2026-09-23openrouterCache read$0.20
2026-10-10openrouterCache read$0.20
2026-09-23azureCache write$2.50
2026-09-24azureCache write$2.50
2026-09-23openrouterCache write$2.50
2026-10-10openrouterCache write$2.50
2026-09-23azureInput$2.00
2026-09-24azureInput$2.00
2026-09-23openrouterInput$2.00
2026-10-10openrouterInput$2.00
2026-09-23azureOutput$10.00
2026-09-24azureOutput$10.00
2026-09-23openrouterOutput$10.00
2026-10-10openrouterOutput$10.00
2026-09-24ofoxCache read$0.16
2026-10-17ofoxCache read$0.20
2026-09-24ofoxCache write$2.00
2026-10-17ofoxCache write$2.50
2026-09-24ofoxInput$1.60
2026-10-17ofoxInput$2.00
2026-09-24ofoxOutput$8.00
2026-10-17ofoxOutput$10.00
2026-10-13aimlapiCache read$0.26
2026-10-23aimlapiCache read$0.20
2026-10-13aimlapiInput$2.60
2026-10-23aimlapiInput$2.00
2026-10-13aimlapiOutput$13.00
2026-10-23aimlapiOutput$10.00
2026-10-21aimlapiCache write$3.25
2026-10-23aimlapiCache write$2.50

Other listings of this model

same model, different key

More from OpenAI

most-hosted first