OpenAI

gpt-6.1-sol

Made by OpenAI. Released 2026-09-29. Accessibility not recorded. Cheapest standard rate we hold: $10 per million output tokens, at short context.

What it costs

Tier	Kind	In	Out	Cached in	From
batch	text · long	$2	$7.50	$0.10	seller
batch	text · short	$1	$5	$0.05	seller
fast	text · long	$8	$30	$0.40	seller
fast	text · short	$4	$20	$0.20	seller
flex	text · long	$2	$7.50	$0.10	seller
flex	text · short	$1	$5	$0.05	seller
standard	text · long	$4	$15	$0.20	seller
standard	text · short	$2	$10	$0.10	seller

per million tokens, US dollars. * marks a rate from a single registry or two that disagree — the best available number rather than a confirmed one. Every other row is confirmed against a seller or a licensed index.

What it scores, by house

Benchmark	House	Score	Evaluated	Scaffold
chess puzzles	Epoch AI	0.7±0.05	2026-10-13	max
ebr bench	Epoch AI	0.5±0.06	2026-09-29	max
frontiermath erdos	Epoch AI	0.0±0.03	2026-10-01	max
frontiermath tier 4 v2	Epoch AI	1.0±0.00	2026-09-29	max
frontiermath tiers 1 3 v2	Epoch AI	0.9±0.01	2026-09-29	max
furniture assembly	Epoch AI	0.8±0.05	2026-09-29	max
gpqa diamond	Epoch AI	1.0±0.01	2026-09-29	max
mirrorcode	Epoch AI	0.6±0.11	2026-10-05	max
mystery game puzzles	Epoch AI	0.8±0.04	2026-09-29	max
otis mock aime 2024 2025near its ceiling	Epoch AI	1.0±0.00	2026-09-29	max
simpleqa verified	Epoch AI	0.7±0.01	2026-09-29	max
spireclimb	Epoch AI	0.2±0.04	2026-11-04	max
spireclimb sts1 a20 heart	Epoch AI	0.2±0.05	2026-11-04	max
spireclimb sts2 a10	Epoch AI	0.3±0.05	2026-09-30	max
ale bench	collected by Epoch AI	2744	—	max
apex agents	collected by Epoch AI	0.7	—	max
arc aginear its ceiling	collected by Epoch AI	1.0	—	max
arc aginear its ceiling	collected by Epoch AI	1.0	—	xhigh
arc aginear its ceiling	collected by Epoch AI	0.9	—	low
arc aginear its ceiling	collected by Epoch AI	1.0	—	high
arc aginear its ceiling	collected by Epoch AI	1.0	—	medium
arc agi 2	collected by Epoch AI	0.8	—	low
arc agi 2	collected by Epoch AI	0.9	—	max
arc agi 2	collected by Epoch AI	0.9	—	xhigh
arc agi 2	collected by Epoch AI	0.9	—	high
arc agi 2	collected by Epoch AI	0.9	—	medium
blueprint bench 2	collected by Epoch AI	0.4	—	unknown
critpt	collected by Epoch AI	0.2	—	low
critpt	collected by Epoch AI	0.3	—	xhigh
critpt	collected by Epoch AI	0.3	—	medium
critpt	collected by Epoch AI	0.3	—	high
critpt	collected by Epoch AI	0.3	—	max
dtbenchnear its ceiling	collected by Epoch AI	1.0	—	max
frontiercode	collected by Epoch AI	0.5	—	codex
gdp pdf	collected by Epoch AI	0.3	—	max
lmca	collected by Epoch AI	62.8	—	max
posttrainbench	collected by Epoch AI	0.4	—	Codex CLI
proofbench	collected by Epoch AI	1.0	—	unknown
scicode	collected by Epoch AI	0.5	—	medium
scicode	collected by Epoch AI	0.6	—	xhigh
scicode	collected by Epoch AI	0.6	—	high
scicode	collected by Epoch AI	0.5	—	low
scicode	collected by Epoch AI	0.5	—	max
simplebench	collected by Epoch AI	0.8	—	unknown
vending bench 2	collected by Epoch AI	12861	—	unknown
webdev arena	collected by Epoch AI	1759	—	max
weirdml v3	collected by Epoch AI	0.4	—	codex_cli

These scores are not comparable between houses and are not added up. A score is dated by when it was evaluated, not when the model was released, and a score without its scaffold is not a measurement — which is why both are printed.

Every rate we hold · Why there is no single best model · Everything from OpenAI