modelbenchmark.io

GPT-4.1

OpenAI · gpt-4-1

Compare

Long-lived GPT workhorse for coding, instruction following, and production apps

Specification

openai listing

Context
1M
Max output
33K
Released
2025-04-14
Knowledge cutoff
2024-04
Retires
2027-04-14
Open weights
no
Input
text, image, pdf
Output
text

Price

US dollars per million tokens · openai list price

Input
$2.00
Output
$8.00
Cache read
$0.50
Cache write
$2.00

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Batch inputazure$1.00
Batch inputazure$1.10
Batch outputazure$4.00
Batch outputazure$4.40
Priority inputopenai$3.50
Priority outputopenai$14.00

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

Quality

10 benchmarks · 3 sources

Composite
41st
percentile of 334 scored models
Rank
196 / 334
±0.04 sd
Evidence
10 × 3
3 or more benchmarks, from 2 or more sources
Effort range
9.0
points between effort settings
coding34th2/3 bench
reasoning48th2/4 bench
math36th5/7 bench
knowledge28th1/1 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
MATH level 583.0 ±0.8defaultEpoch AI2025-04-14
Aider polyglot52.4default · aider diffAider2025-04-14
GPQA diamond66.9 ±2.8defaultEpoch AI2025-04-14
OTIS Mock AIME 2024-202538.3 ±6.3defaultEpoch AI2025-04-14
SimpleQA Verified31.1 ±1.5defaultEpoch AI2026-08-31
FrontierMath-Tier-4-2025-07-010.0 ±0.0default · 2 runsEpoch AI2025-07-01
SWE-Bench verified48.5 ±2.3defaultEpoch AI2026-02-08
39.6default · mini-SWE-agentSWE-bench
Sources and settings disagree by 8.9 points. Both figures stand.
Chess Puzzles6.0 ±2.4defaultEpoch AI2026-08-07
FrontierMath-v12.8 ±0.0default · 2 runsEpoch AI2025-04-14
FrontierMath-Tiers-1-3-v26.0 ±1.4defaultEpoch AI2026-08-27

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

Available from 29 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
openaivendor$2.00$8.00$0.501M33K
poe$1.80$7.20$0.451M33K
302ai$2.00$8.001M33K
abacus$2.00$8.00$0.501M33K
azure
$2.00
$2.20
$8.00
$8.80
$0.50
$0.55
1M33K2027-04-14
azure-cognitive-services$2.00$8.00$0.501M33K
cloudflare-ai-gateway$2.00$8.00$0.501M33K
edenai$2.00$8.00$0.501M33K
fastrouter$2.00$8.00$0.501M33K
helicone$2.00$8.00$0.501M33K
impossibl$2.00$8.00$0.501M33K
kilo$2.00$8.00$0.501M33K
llmgateway$2.00$8.00$0.501M33K
llmgateway-providers$2.00$8.00$0.501M33K
merge-gateway$2.00$8.00$0.501M33K
nano-gpt$2.00$8.00$0.501M33K
nearai$2.00$8.00$0.501M33K
ofox$2.00$8.00$0.501M33K
openrouter$2.00$8.00$0.501M33K
orcarouter$2.00$8.00$0.501M33K
pioneer$2.00$8.00$1.00$2.001M33K
replicate · replicate$2.00$8.00
sap-ai-core$2.00$8.00$0.321M33K
vercel$2.00$8.00$0.501M33K
vercel_ai_gateway · vercel-ai-gateway$2.00$8.00$0.50free1M33K
cortecs$2.192$8.769$0.5461M33K
anyapi1M33K
github_copilot · github-copilot128K16K
model-oracle-ai1M33K

More from OpenAI

most-hosted first